init repo
This commit is contained in:
Summer Shen
@@ -0,0 +1,149 @@
|
|||||||
|
---
|
||||||
|
description: Implement tasks from an OpenSpec change (Experimental)
|
||||||
|
---
|
||||||
|
|
||||||
|
Implement tasks from an OpenSpec change.
|
||||||
|
|
||||||
|
**Input**: Optionally specify a change name (e.g., `/opsx:apply add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **Select the change**
|
||||||
|
|
||||||
|
If a name is provided, use it. Otherwise:
|
||||||
|
- Infer from conversation context if the user mentioned a change
|
||||||
|
- Auto-select if only one active change exists
|
||||||
|
- If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
|
||||||
|
|
||||||
|
Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
|
||||||
|
|
||||||
|
2. **Check status to understand the schema**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>" --json
|
||||||
|
```
|
||||||
|
Parse the JSON to understand:
|
||||||
|
- `schemaName`: The workflow being used (e.g., "spec-driven")
|
||||||
|
- Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
|
||||||
|
|
||||||
|
3. **Get apply instructions**
|
||||||
|
|
||||||
|
```bash
|
||||||
|
openspec instructions apply --change "<name>" --json
|
||||||
|
```
|
||||||
|
|
||||||
|
This returns:
|
||||||
|
- Context file paths (varies by schema)
|
||||||
|
- Progress (total, complete, remaining)
|
||||||
|
- Task list with status
|
||||||
|
- Dynamic instruction based on current state
|
||||||
|
|
||||||
|
**Handle states:**
|
||||||
|
- If `state: "blocked"` (missing artifacts): show message, suggest using `/opsx:continue`
|
||||||
|
- If `state: "all_done"`: congratulate, suggest archive
|
||||||
|
- Otherwise: proceed to implementation
|
||||||
|
|
||||||
|
4. **Read context files**
|
||||||
|
|
||||||
|
Read the files listed in `contextFiles` from the apply instructions output.
|
||||||
|
The files depend on the schema being used:
|
||||||
|
- **spec-driven**: proposal, specs, design, tasks
|
||||||
|
- Other schemas: follow the contextFiles from CLI output
|
||||||
|
|
||||||
|
5. **Show current progress**
|
||||||
|
|
||||||
|
Display:
|
||||||
|
- Schema being used
|
||||||
|
- Progress: "N/M tasks complete"
|
||||||
|
- Remaining tasks overview
|
||||||
|
- Dynamic instruction from CLI
|
||||||
|
|
||||||
|
6. **Implement tasks (loop until done or blocked)**
|
||||||
|
|
||||||
|
For each pending task:
|
||||||
|
- Show which task is being worked on
|
||||||
|
- Make the code changes required
|
||||||
|
- Keep changes minimal and focused
|
||||||
|
- Mark task complete in the tasks file: `- [ ]` → `- [x]`
|
||||||
|
- Continue to next task
|
||||||
|
|
||||||
|
**Pause if:**
|
||||||
|
- Task is unclear → ask for clarification
|
||||||
|
- Implementation reveals a design issue → suggest updating artifacts
|
||||||
|
- Error or blocker encountered → report and wait for guidance
|
||||||
|
- User interrupts
|
||||||
|
|
||||||
|
7. **On completion or pause, show status**
|
||||||
|
|
||||||
|
Display:
|
||||||
|
- Tasks completed this session
|
||||||
|
- Overall progress: "N/M tasks complete"
|
||||||
|
- If all done: suggest archive
|
||||||
|
- If paused: explain why and wait for guidance
|
||||||
|
|
||||||
|
**Output During Implementation**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementing: <change-name> (schema: <schema-name>)
|
||||||
|
|
||||||
|
Working on task 3/7: <task description>
|
||||||
|
[...implementation happening...]
|
||||||
|
✓ Task complete
|
||||||
|
|
||||||
|
Working on task 4/7: <task description>
|
||||||
|
[...implementation happening...]
|
||||||
|
✓ Task complete
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Completion**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementation Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Progress:** 7/7 tasks complete ✓
|
||||||
|
|
||||||
|
### Completed This Session
|
||||||
|
- [x] Task 1
|
||||||
|
- [x] Task 2
|
||||||
|
...
|
||||||
|
|
||||||
|
All tasks complete! You can archive this change with `/opsx:archive`.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Pause (Issue Encountered)**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementation Paused
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Progress:** 4/7 tasks complete
|
||||||
|
|
||||||
|
### Issue Encountered
|
||||||
|
<description of the issue>
|
||||||
|
|
||||||
|
**Options:**
|
||||||
|
1. <option 1>
|
||||||
|
2. <option 2>
|
||||||
|
3. Other approach
|
||||||
|
|
||||||
|
What would you like to do?
|
||||||
|
```
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Keep going through tasks until done or blocked
|
||||||
|
- Always read context files before starting (from the apply instructions output)
|
||||||
|
- If task is ambiguous, pause and ask before implementing
|
||||||
|
- If implementation reveals issues, pause and suggest artifact updates
|
||||||
|
- Keep code changes minimal and scoped to each task
|
||||||
|
- Update task checkbox immediately after completing each task
|
||||||
|
- Pause on errors, blockers, or unclear requirements - don't guess
|
||||||
|
- Use contextFiles from CLI output, don't assume specific file names
|
||||||
|
|
||||||
|
**Fluid Workflow Integration**
|
||||||
|
|
||||||
|
This skill supports the "actions on a change" model:
|
||||||
|
|
||||||
|
- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
|
||||||
|
- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
|
||||||
@@ -0,0 +1,154 @@
|
|||||||
|
---
|
||||||
|
description: Archive a completed change in the experimental workflow
|
||||||
|
---
|
||||||
|
|
||||||
|
Archive a completed change in the experimental workflow.
|
||||||
|
|
||||||
|
**Input**: Optionally specify a change name after `/opsx:archive` (e.g., `/opsx:archive add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **If no change name provided, prompt for selection**
|
||||||
|
|
||||||
|
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||||
|
|
||||||
|
Show only active changes (not already archived).
|
||||||
|
Include the schema used for each change if available.
|
||||||
|
|
||||||
|
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||||
|
|
||||||
|
2. **Check artifact completion status**
|
||||||
|
|
||||||
|
Run `openspec status --change "<name>" --json` to check artifact completion.
|
||||||
|
|
||||||
|
Parse the JSON to understand:
|
||||||
|
- `schemaName`: The workflow being used
|
||||||
|
- `artifacts`: List of artifacts with their status (`done` or other)
|
||||||
|
|
||||||
|
**If any artifacts are not `done`:**
|
||||||
|
- Display warning listing incomplete artifacts
|
||||||
|
- Prompt user for confirmation to continue
|
||||||
|
- Proceed if user confirms
|
||||||
|
|
||||||
|
3. **Check task completion status**
|
||||||
|
|
||||||
|
Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
|
||||||
|
|
||||||
|
Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
|
||||||
|
|
||||||
|
**If incomplete tasks found:**
|
||||||
|
- Display warning showing count of incomplete tasks
|
||||||
|
- Prompt user for confirmation to continue
|
||||||
|
- Proceed if user confirms
|
||||||
|
|
||||||
|
**If no tasks file exists:** Proceed without task-related warning.
|
||||||
|
|
||||||
|
4. **Assess delta spec sync state**
|
||||||
|
|
||||||
|
Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
|
||||||
|
|
||||||
|
**If delta specs exist:**
|
||||||
|
- Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
|
||||||
|
- Determine what changes would be applied (adds, modifications, removals, renames)
|
||||||
|
- Show a combined summary before prompting
|
||||||
|
|
||||||
|
**Prompt options:**
|
||||||
|
- If changes needed: "Sync now (recommended)", "Archive without syncing"
|
||||||
|
- If already synced: "Archive now", "Sync anyway", "Cancel"
|
||||||
|
|
||||||
|
If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
|
||||||
|
|
||||||
|
5. **Perform the archive**
|
||||||
|
|
||||||
|
Create the archive directory if it doesn't exist:
|
||||||
|
```bash
|
||||||
|
mkdir -p openspec/changes/archive
|
||||||
|
```
|
||||||
|
|
||||||
|
Generate target name using current date: `YYYY-MM-DD-<change-name>`
|
||||||
|
|
||||||
|
**Check if target already exists:**
|
||||||
|
- If yes: Fail with error, suggest renaming existing archive or using different date
|
||||||
|
- If no: Move the change directory to archive
|
||||||
|
|
||||||
|
```bash
|
||||||
|
mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
|
||||||
|
```
|
||||||
|
|
||||||
|
6. **Display summary**
|
||||||
|
|
||||||
|
Show archive completion summary including:
|
||||||
|
- Change name
|
||||||
|
- Schema that was used
|
||||||
|
- Archive location
|
||||||
|
- Spec sync status (synced / sync skipped / no delta specs)
|
||||||
|
- Note about any warnings (incomplete artifacts/tasks)
|
||||||
|
|
||||||
|
**Output On Success**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
**Specs:** ✓ Synced to main specs
|
||||||
|
|
||||||
|
All artifacts complete. All tasks complete.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Success (No Delta Specs)**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
**Specs:** No delta specs
|
||||||
|
|
||||||
|
All artifacts complete. All tasks complete.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Success With Warnings**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Complete (with warnings)
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
**Specs:** Sync skipped (user chose to skip)
|
||||||
|
|
||||||
|
**Warnings:**
|
||||||
|
- Archived with 2 incomplete artifacts
|
||||||
|
- Archived with 3 incomplete tasks
|
||||||
|
- Delta spec sync was skipped (user chose to skip)
|
||||||
|
|
||||||
|
Review the archive if this was not intentional.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Error (Archive Exists)**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Failed
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Target:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
|
||||||
|
Target archive directory already exists.
|
||||||
|
|
||||||
|
**Options:**
|
||||||
|
1. Rename the existing archive
|
||||||
|
2. Delete the existing archive if it's a duplicate
|
||||||
|
3. Wait until a different date to archive
|
||||||
|
```
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Always prompt for change selection if not provided
|
||||||
|
- Use artifact graph (openspec status --json) for completion checking
|
||||||
|
- Don't block archive on warnings - just inform and confirm
|
||||||
|
- Preserve .openspec.yaml when moving to archive (it moves with the directory)
|
||||||
|
- Show clear summary of what happened
|
||||||
|
- If sync is requested, use the Skill tool to invoke `openspec-sync-specs` (agent-driven)
|
||||||
|
- If delta specs exist, always run the sync assessment and show the combined summary before prompting
|
||||||
@@ -0,0 +1,170 @@
|
|||||||
|
---
|
||||||
|
description: Enter explore mode - think through ideas, investigate problems, clarify requirements
|
||||||
|
---
|
||||||
|
|
||||||
|
Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
|
||||||
|
|
||||||
|
**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
|
||||||
|
|
||||||
|
**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
|
||||||
|
|
||||||
|
**Input**: The argument after `/opsx:explore` is whatever the user wants to think about. Could be:
|
||||||
|
- A vague idea: "real-time collaboration"
|
||||||
|
- A specific problem: "the auth system is getting unwieldy"
|
||||||
|
- A change name: "add-dark-mode" (to explore in context of that change)
|
||||||
|
- A comparison: "postgres vs sqlite for this"
|
||||||
|
- Nothing (just enter explore mode)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## The Stance
|
||||||
|
|
||||||
|
- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
|
||||||
|
- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
|
||||||
|
- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
|
||||||
|
- **Adaptive** - Follow interesting threads, pivot when new information emerges
|
||||||
|
- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
|
||||||
|
- **Grounded** - Explore the actual codebase when relevant, don't just theorize
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What You Might Do
|
||||||
|
|
||||||
|
Depending on what the user brings, you might:
|
||||||
|
|
||||||
|
**Explore the problem space**
|
||||||
|
- Ask clarifying questions that emerge from what they said
|
||||||
|
- Challenge assumptions
|
||||||
|
- Reframe the problem
|
||||||
|
- Find analogies
|
||||||
|
|
||||||
|
**Investigate the codebase**
|
||||||
|
- Map existing architecture relevant to the discussion
|
||||||
|
- Find integration points
|
||||||
|
- Identify patterns already in use
|
||||||
|
- Surface hidden complexity
|
||||||
|
|
||||||
|
**Compare options**
|
||||||
|
- Brainstorm multiple approaches
|
||||||
|
- Build comparison tables
|
||||||
|
- Sketch tradeoffs
|
||||||
|
- Recommend a path (if asked)
|
||||||
|
|
||||||
|
**Visualize**
|
||||||
|
```
|
||||||
|
┌─────────────────────────────────────────┐
|
||||||
|
│ Use ASCII diagrams liberally │
|
||||||
|
├─────────────────────────────────────────┤
|
||||||
|
│ │
|
||||||
|
│ ┌────────┐ ┌────────┐ │
|
||||||
|
│ │ State │────────▶│ State │ │
|
||||||
|
│ │ A │ │ B │ │
|
||||||
|
│ └────────┘ └────────┘ │
|
||||||
|
│ │
|
||||||
|
│ System diagrams, state machines, │
|
||||||
|
│ data flows, architecture sketches, │
|
||||||
|
│ dependency graphs, comparison tables │
|
||||||
|
│ │
|
||||||
|
└─────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
**Surface risks and unknowns**
|
||||||
|
- Identify what could go wrong
|
||||||
|
- Find gaps in understanding
|
||||||
|
- Suggest spikes or investigations
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## OpenSpec Awareness
|
||||||
|
|
||||||
|
You have full context of the OpenSpec system. Use it naturally, don't force it.
|
||||||
|
|
||||||
|
### Check for context
|
||||||
|
|
||||||
|
At the start, quickly check what exists:
|
||||||
|
```bash
|
||||||
|
openspec list --json
|
||||||
|
```
|
||||||
|
|
||||||
|
This tells you:
|
||||||
|
- If there are active changes
|
||||||
|
- Their names, schemas, and status
|
||||||
|
- What the user might be working on
|
||||||
|
|
||||||
|
If the user mentioned a specific change name, read its artifacts for context.
|
||||||
|
|
||||||
|
### When no change exists
|
||||||
|
|
||||||
|
Think freely. When insights crystallize, you might offer:
|
||||||
|
|
||||||
|
- "This feels solid enough to start a change. Want me to create a proposal?"
|
||||||
|
- Or keep exploring - no pressure to formalize
|
||||||
|
|
||||||
|
### When a change exists
|
||||||
|
|
||||||
|
If the user mentions a change or you detect one is relevant:
|
||||||
|
|
||||||
|
1. **Read existing artifacts for context**
|
||||||
|
- `openspec/changes/<name>/proposal.md`
|
||||||
|
- `openspec/changes/<name>/design.md`
|
||||||
|
- `openspec/changes/<name>/tasks.md`
|
||||||
|
- etc.
|
||||||
|
|
||||||
|
2. **Reference them naturally in conversation**
|
||||||
|
- "Your design mentions using Redis, but we just realized SQLite fits better..."
|
||||||
|
- "The proposal scopes this to premium users, but we're now thinking everyone..."
|
||||||
|
|
||||||
|
3. **Offer to capture when decisions are made**
|
||||||
|
|
||||||
|
| Insight Type | Where to Capture |
|
||||||
|
|--------------|------------------|
|
||||||
|
| New requirement discovered | `specs/<capability>/spec.md` |
|
||||||
|
| Requirement changed | `specs/<capability>/spec.md` |
|
||||||
|
| Design decision made | `design.md` |
|
||||||
|
| Scope changed | `proposal.md` |
|
||||||
|
| New work identified | `tasks.md` |
|
||||||
|
| Assumption invalidated | Relevant artifact |
|
||||||
|
|
||||||
|
Example offers:
|
||||||
|
- "That's a design decision. Capture it in design.md?"
|
||||||
|
- "This is a new requirement. Add it to specs?"
|
||||||
|
- "This changes scope. Update the proposal?"
|
||||||
|
|
||||||
|
4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What You Don't Have To Do
|
||||||
|
|
||||||
|
- Follow a script
|
||||||
|
- Ask the same questions every time
|
||||||
|
- Produce a specific artifact
|
||||||
|
- Reach a conclusion
|
||||||
|
- Stay on topic if a tangent is valuable
|
||||||
|
- Be brief (this is thinking time)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Ending Discovery
|
||||||
|
|
||||||
|
There's no required ending. Discovery might:
|
||||||
|
|
||||||
|
- **Flow into a proposal**: "Ready to start? I can create a change proposal."
|
||||||
|
- **Result in artifact updates**: "Updated design.md with these decisions"
|
||||||
|
- **Just provide clarity**: User has what they need, moves on
|
||||||
|
- **Continue later**: "We can pick this up anytime"
|
||||||
|
|
||||||
|
When things crystallize, you might offer a summary - but it's optional. Sometimes the thinking IS the value.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Guardrails
|
||||||
|
|
||||||
|
- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
|
||||||
|
- **Don't fake understanding** - If something is unclear, dig deeper
|
||||||
|
- **Don't rush** - Discovery is thinking time, not task time
|
||||||
|
- **Don't force structure** - Let patterns emerge naturally
|
||||||
|
- **Don't auto-capture** - Offer to save insights, don't just do it
|
||||||
|
- **Do visualize** - A good diagram is worth many paragraphs
|
||||||
|
- **Do explore the codebase** - Ground discussions in reality
|
||||||
|
- **Do question assumptions** - Including the user's and your own
|
||||||
@@ -0,0 +1,103 @@
|
|||||||
|
---
|
||||||
|
description: Propose a new change - create it and generate all artifacts in one step
|
||||||
|
---
|
||||||
|
|
||||||
|
Propose a new change - create the change and generate all artifacts in one step.
|
||||||
|
|
||||||
|
I'll create a change with artifacts:
|
||||||
|
- proposal.md (what & why)
|
||||||
|
- design.md (how)
|
||||||
|
- tasks.md (implementation steps)
|
||||||
|
|
||||||
|
When ready to implement, run /opsx:apply
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
**Input**: The argument after `/opsx:propose` is the change name (kebab-case), OR a description of what the user wants to build.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **If no input provided, ask what they want to build**
|
||||||
|
|
||||||
|
Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
|
||||||
|
> "What change do you want to work on? Describe what you want to build or fix."
|
||||||
|
|
||||||
|
From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
|
||||||
|
|
||||||
|
**IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
|
||||||
|
|
||||||
|
2. **Create the change directory**
|
||||||
|
```bash
|
||||||
|
openspec new change "<name>"
|
||||||
|
```
|
||||||
|
This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
|
||||||
|
|
||||||
|
3. **Get the artifact build order**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>" --json
|
||||||
|
```
|
||||||
|
Parse the JSON to get:
|
||||||
|
- `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
|
||||||
|
- `artifacts`: list of all artifacts with their status and dependencies
|
||||||
|
|
||||||
|
4. **Create artifacts in sequence until apply-ready**
|
||||||
|
|
||||||
|
Use the **TodoWrite tool** to track progress through the artifacts.
|
||||||
|
|
||||||
|
Loop through artifacts in dependency order (artifacts with no pending dependencies first):
|
||||||
|
|
||||||
|
a. **For each artifact that is `ready` (dependencies satisfied)**:
|
||||||
|
- Get instructions:
|
||||||
|
```bash
|
||||||
|
openspec instructions <artifact-id> --change "<name>" --json
|
||||||
|
```
|
||||||
|
- The instructions JSON includes:
|
||||||
|
- `context`: Project background (constraints for you - do NOT include in output)
|
||||||
|
- `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
|
||||||
|
- `template`: The structure to use for your output file
|
||||||
|
- `instruction`: Schema-specific guidance for this artifact type
|
||||||
|
- `outputPath`: Where to write the artifact
|
||||||
|
- `dependencies`: Completed artifacts to read for context
|
||||||
|
- Read any completed dependency files for context
|
||||||
|
- Create the artifact file using `template` as the structure
|
||||||
|
- Apply `context` and `rules` as constraints - but do NOT copy them into the file
|
||||||
|
- Show brief progress: "Created <artifact-id>"
|
||||||
|
|
||||||
|
b. **Continue until all `applyRequires` artifacts are complete**
|
||||||
|
- After creating each artifact, re-run `openspec status --change "<name>" --json`
|
||||||
|
- Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
|
||||||
|
- Stop when all `applyRequires` artifacts are done
|
||||||
|
|
||||||
|
c. **If an artifact requires user input** (unclear context):
|
||||||
|
- Use **AskUserQuestion tool** to clarify
|
||||||
|
- Then continue with creation
|
||||||
|
|
||||||
|
5. **Show final status**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>"
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output**
|
||||||
|
|
||||||
|
After completing all artifacts, summarize:
|
||||||
|
- Change name and location
|
||||||
|
- List of artifacts created with brief descriptions
|
||||||
|
- What's ready: "All artifacts created! Ready for implementation."
|
||||||
|
- Prompt: "Run `/opsx:apply` to start implementing."
|
||||||
|
|
||||||
|
**Artifact Creation Guidelines**
|
||||||
|
|
||||||
|
- Follow the `instruction` field from `openspec instructions` for each artifact type
|
||||||
|
- The schema defines what each artifact should contain - follow it
|
||||||
|
- Read dependency artifacts for context before creating new ones
|
||||||
|
- Use `template` as the structure for your output file - fill in its sections
|
||||||
|
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
|
||||||
|
- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
|
||||||
|
- These guide what you write, but should never appear in the output
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
|
||||||
|
- Always read dependency artifacts before creating a new one
|
||||||
|
- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
|
||||||
|
- If a change with that name already exists, ask if user wants to continue it or create a new one
|
||||||
|
- Verify each artifact file exists after writing before proceeding to next
|
||||||
@@ -0,0 +1,156 @@
|
|||||||
|
---
|
||||||
|
name: openspec-apply-change
|
||||||
|
description: Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
|
||||||
|
license: MIT
|
||||||
|
compatibility: Requires openspec CLI.
|
||||||
|
metadata:
|
||||||
|
author: openspec
|
||||||
|
version: "1.0"
|
||||||
|
generatedBy: "1.2.0"
|
||||||
|
---
|
||||||
|
|
||||||
|
Implement tasks from an OpenSpec change.
|
||||||
|
|
||||||
|
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **Select the change**
|
||||||
|
|
||||||
|
If a name is provided, use it. Otherwise:
|
||||||
|
- Infer from conversation context if the user mentioned a change
|
||||||
|
- Auto-select if only one active change exists
|
||||||
|
- If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
|
||||||
|
|
||||||
|
Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
|
||||||
|
|
||||||
|
2. **Check status to understand the schema**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>" --json
|
||||||
|
```
|
||||||
|
Parse the JSON to understand:
|
||||||
|
- `schemaName`: The workflow being used (e.g., "spec-driven")
|
||||||
|
- Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
|
||||||
|
|
||||||
|
3. **Get apply instructions**
|
||||||
|
|
||||||
|
```bash
|
||||||
|
openspec instructions apply --change "<name>" --json
|
||||||
|
```
|
||||||
|
|
||||||
|
This returns:
|
||||||
|
- Context file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)
|
||||||
|
- Progress (total, complete, remaining)
|
||||||
|
- Task list with status
|
||||||
|
- Dynamic instruction based on current state
|
||||||
|
|
||||||
|
**Handle states:**
|
||||||
|
- If `state: "blocked"` (missing artifacts): show message, suggest using openspec-continue-change
|
||||||
|
- If `state: "all_done"`: congratulate, suggest archive
|
||||||
|
- Otherwise: proceed to implementation
|
||||||
|
|
||||||
|
4. **Read context files**
|
||||||
|
|
||||||
|
Read the files listed in `contextFiles` from the apply instructions output.
|
||||||
|
The files depend on the schema being used:
|
||||||
|
- **spec-driven**: proposal, specs, design, tasks
|
||||||
|
- Other schemas: follow the contextFiles from CLI output
|
||||||
|
|
||||||
|
5. **Show current progress**
|
||||||
|
|
||||||
|
Display:
|
||||||
|
- Schema being used
|
||||||
|
- Progress: "N/M tasks complete"
|
||||||
|
- Remaining tasks overview
|
||||||
|
- Dynamic instruction from CLI
|
||||||
|
|
||||||
|
6. **Implement tasks (loop until done or blocked)**
|
||||||
|
|
||||||
|
For each pending task:
|
||||||
|
- Show which task is being worked on
|
||||||
|
- Make the code changes required
|
||||||
|
- Keep changes minimal and focused
|
||||||
|
- Mark task complete in the tasks file: `- [ ]` → `- [x]`
|
||||||
|
- Continue to next task
|
||||||
|
|
||||||
|
**Pause if:**
|
||||||
|
- Task is unclear → ask for clarification
|
||||||
|
- Implementation reveals a design issue → suggest updating artifacts
|
||||||
|
- Error or blocker encountered → report and wait for guidance
|
||||||
|
- User interrupts
|
||||||
|
|
||||||
|
7. **On completion or pause, show status**
|
||||||
|
|
||||||
|
Display:
|
||||||
|
- Tasks completed this session
|
||||||
|
- Overall progress: "N/M tasks complete"
|
||||||
|
- If all done: suggest archive
|
||||||
|
- If paused: explain why and wait for guidance
|
||||||
|
|
||||||
|
**Output During Implementation**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementing: <change-name> (schema: <schema-name>)
|
||||||
|
|
||||||
|
Working on task 3/7: <task description>
|
||||||
|
[...implementation happening...]
|
||||||
|
✓ Task complete
|
||||||
|
|
||||||
|
Working on task 4/7: <task description>
|
||||||
|
[...implementation happening...]
|
||||||
|
✓ Task complete
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Completion**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementation Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Progress:** 7/7 tasks complete ✓
|
||||||
|
|
||||||
|
### Completed This Session
|
||||||
|
- [x] Task 1
|
||||||
|
- [x] Task 2
|
||||||
|
...
|
||||||
|
|
||||||
|
All tasks complete! Ready to archive this change.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Pause (Issue Encountered)**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementation Paused
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Progress:** 4/7 tasks complete
|
||||||
|
|
||||||
|
### Issue Encountered
|
||||||
|
<description of the issue>
|
||||||
|
|
||||||
|
**Options:**
|
||||||
|
1. <option 1>
|
||||||
|
2. <option 2>
|
||||||
|
3. Other approach
|
||||||
|
|
||||||
|
What would you like to do?
|
||||||
|
```
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Keep going through tasks until done or blocked
|
||||||
|
- Always read context files before starting (from the apply instructions output)
|
||||||
|
- If task is ambiguous, pause and ask before implementing
|
||||||
|
- If implementation reveals issues, pause and suggest artifact updates
|
||||||
|
- Keep code changes minimal and scoped to each task
|
||||||
|
- Update task checkbox immediately after completing each task
|
||||||
|
- Pause on errors, blockers, or unclear requirements - don't guess
|
||||||
|
- Use contextFiles from CLI output, don't assume specific file names
|
||||||
|
|
||||||
|
**Fluid Workflow Integration**
|
||||||
|
|
||||||
|
This skill supports the "actions on a change" model:
|
||||||
|
|
||||||
|
- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
|
||||||
|
- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
|
||||||
@@ -0,0 +1,114 @@
|
|||||||
|
---
|
||||||
|
name: openspec-archive-change
|
||||||
|
description: Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
|
||||||
|
license: MIT
|
||||||
|
compatibility: Requires openspec CLI.
|
||||||
|
metadata:
|
||||||
|
author: openspec
|
||||||
|
version: "1.0"
|
||||||
|
generatedBy: "1.2.0"
|
||||||
|
---
|
||||||
|
|
||||||
|
Archive a completed change in the experimental workflow.
|
||||||
|
|
||||||
|
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **If no change name provided, prompt for selection**
|
||||||
|
|
||||||
|
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||||
|
|
||||||
|
Show only active changes (not already archived).
|
||||||
|
Include the schema used for each change if available.
|
||||||
|
|
||||||
|
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||||
|
|
||||||
|
2. **Check artifact completion status**
|
||||||
|
|
||||||
|
Run `openspec status --change "<name>" --json` to check artifact completion.
|
||||||
|
|
||||||
|
Parse the JSON to understand:
|
||||||
|
- `schemaName`: The workflow being used
|
||||||
|
- `artifacts`: List of artifacts with their status (`done` or other)
|
||||||
|
|
||||||
|
**If any artifacts are not `done`:**
|
||||||
|
- Display warning listing incomplete artifacts
|
||||||
|
- Use **AskUserQuestion tool** to confirm user wants to proceed
|
||||||
|
- Proceed if user confirms
|
||||||
|
|
||||||
|
3. **Check task completion status**
|
||||||
|
|
||||||
|
Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
|
||||||
|
|
||||||
|
Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
|
||||||
|
|
||||||
|
**If incomplete tasks found:**
|
||||||
|
- Display warning showing count of incomplete tasks
|
||||||
|
- Use **AskUserQuestion tool** to confirm user wants to proceed
|
||||||
|
- Proceed if user confirms
|
||||||
|
|
||||||
|
**If no tasks file exists:** Proceed without task-related warning.
|
||||||
|
|
||||||
|
4. **Assess delta spec sync state**
|
||||||
|
|
||||||
|
Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
|
||||||
|
|
||||||
|
**If delta specs exist:**
|
||||||
|
- Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
|
||||||
|
- Determine what changes would be applied (adds, modifications, removals, renames)
|
||||||
|
- Show a combined summary before prompting
|
||||||
|
|
||||||
|
**Prompt options:**
|
||||||
|
- If changes needed: "Sync now (recommended)", "Archive without syncing"
|
||||||
|
- If already synced: "Archive now", "Sync anyway", "Cancel"
|
||||||
|
|
||||||
|
If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
|
||||||
|
|
||||||
|
5. **Perform the archive**
|
||||||
|
|
||||||
|
Create the archive directory if it doesn't exist:
|
||||||
|
```bash
|
||||||
|
mkdir -p openspec/changes/archive
|
||||||
|
```
|
||||||
|
|
||||||
|
Generate target name using current date: `YYYY-MM-DD-<change-name>`
|
||||||
|
|
||||||
|
**Check if target already exists:**
|
||||||
|
- If yes: Fail with error, suggest renaming existing archive or using different date
|
||||||
|
- If no: Move the change directory to archive
|
||||||
|
|
||||||
|
```bash
|
||||||
|
mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
|
||||||
|
```
|
||||||
|
|
||||||
|
6. **Display summary**
|
||||||
|
|
||||||
|
Show archive completion summary including:
|
||||||
|
- Change name
|
||||||
|
- Schema that was used
|
||||||
|
- Archive location
|
||||||
|
- Whether specs were synced (if applicable)
|
||||||
|
- Note about any warnings (incomplete artifacts/tasks)
|
||||||
|
|
||||||
|
**Output On Success**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
**Specs:** ✓ Synced to main specs (or "No delta specs" or "Sync skipped")
|
||||||
|
|
||||||
|
All artifacts complete. All tasks complete.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Always prompt for change selection if not provided
|
||||||
|
- Use artifact graph (openspec status --json) for completion checking
|
||||||
|
- Don't block archive on warnings - just inform and confirm
|
||||||
|
- Preserve .openspec.yaml when moving to archive (it moves with the directory)
|
||||||
|
- Show clear summary of what happened
|
||||||
|
- If sync is requested, use openspec-sync-specs approach (agent-driven)
|
||||||
|
- If delta specs exist, always run the sync assessment and show the combined summary before prompting
|
||||||
@@ -0,0 +1,288 @@
|
|||||||
|
---
|
||||||
|
name: openspec-explore
|
||||||
|
description: Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
|
||||||
|
license: MIT
|
||||||
|
compatibility: Requires openspec CLI.
|
||||||
|
metadata:
|
||||||
|
author: openspec
|
||||||
|
version: "1.0"
|
||||||
|
generatedBy: "1.2.0"
|
||||||
|
---
|
||||||
|
|
||||||
|
Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
|
||||||
|
|
||||||
|
**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
|
||||||
|
|
||||||
|
**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## The Stance
|
||||||
|
|
||||||
|
- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
|
||||||
|
- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
|
||||||
|
- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
|
||||||
|
- **Adaptive** - Follow interesting threads, pivot when new information emerges
|
||||||
|
- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
|
||||||
|
- **Grounded** - Explore the actual codebase when relevant, don't just theorize
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What You Might Do
|
||||||
|
|
||||||
|
Depending on what the user brings, you might:
|
||||||
|
|
||||||
|
**Explore the problem space**
|
||||||
|
- Ask clarifying questions that emerge from what they said
|
||||||
|
- Challenge assumptions
|
||||||
|
- Reframe the problem
|
||||||
|
- Find analogies
|
||||||
|
|
||||||
|
**Investigate the codebase**
|
||||||
|
- Map existing architecture relevant to the discussion
|
||||||
|
- Find integration points
|
||||||
|
- Identify patterns already in use
|
||||||
|
- Surface hidden complexity
|
||||||
|
|
||||||
|
**Compare options**
|
||||||
|
- Brainstorm multiple approaches
|
||||||
|
- Build comparison tables
|
||||||
|
- Sketch tradeoffs
|
||||||
|
- Recommend a path (if asked)
|
||||||
|
|
||||||
|
**Visualize**
|
||||||
|
```
|
||||||
|
┌─────────────────────────────────────────┐
|
||||||
|
│ Use ASCII diagrams liberally │
|
||||||
|
├─────────────────────────────────────────┤
|
||||||
|
│ │
|
||||||
|
│ ┌────────┐ ┌────────┐ │
|
||||||
|
│ │ State │────────▶│ State │ │
|
||||||
|
│ │ A │ │ B │ │
|
||||||
|
│ └────────┘ └────────┘ │
|
||||||
|
│ │
|
||||||
|
│ System diagrams, state machines, │
|
||||||
|
│ data flows, architecture sketches, │
|
||||||
|
│ dependency graphs, comparison tables │
|
||||||
|
│ │
|
||||||
|
└─────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
**Surface risks and unknowns**
|
||||||
|
- Identify what could go wrong
|
||||||
|
- Find gaps in understanding
|
||||||
|
- Suggest spikes or investigations
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## OpenSpec Awareness
|
||||||
|
|
||||||
|
You have full context of the OpenSpec system. Use it naturally, don't force it.
|
||||||
|
|
||||||
|
### Check for context
|
||||||
|
|
||||||
|
At the start, quickly check what exists:
|
||||||
|
```bash
|
||||||
|
openspec list --json
|
||||||
|
```
|
||||||
|
|
||||||
|
This tells you:
|
||||||
|
- If there are active changes
|
||||||
|
- Their names, schemas, and status
|
||||||
|
- What the user might be working on
|
||||||
|
|
||||||
|
### When no change exists
|
||||||
|
|
||||||
|
Think freely. When insights crystallize, you might offer:
|
||||||
|
|
||||||
|
- "This feels solid enough to start a change. Want me to create a proposal?"
|
||||||
|
- Or keep exploring - no pressure to formalize
|
||||||
|
|
||||||
|
### When a change exists
|
||||||
|
|
||||||
|
If the user mentions a change or you detect one is relevant:
|
||||||
|
|
||||||
|
1. **Read existing artifacts for context**
|
||||||
|
- `openspec/changes/<name>/proposal.md`
|
||||||
|
- `openspec/changes/<name>/design.md`
|
||||||
|
- `openspec/changes/<name>/tasks.md`
|
||||||
|
- etc.
|
||||||
|
|
||||||
|
2. **Reference them naturally in conversation**
|
||||||
|
- "Your design mentions using Redis, but we just realized SQLite fits better..."
|
||||||
|
- "The proposal scopes this to premium users, but we're now thinking everyone..."
|
||||||
|
|
||||||
|
3. **Offer to capture when decisions are made**
|
||||||
|
|
||||||
|
| Insight Type | Where to Capture |
|
||||||
|
|--------------|------------------|
|
||||||
|
| New requirement discovered | `specs/<capability>/spec.md` |
|
||||||
|
| Requirement changed | `specs/<capability>/spec.md` |
|
||||||
|
| Design decision made | `design.md` |
|
||||||
|
| Scope changed | `proposal.md` |
|
||||||
|
| New work identified | `tasks.md` |
|
||||||
|
| Assumption invalidated | Relevant artifact |
|
||||||
|
|
||||||
|
Example offers:
|
||||||
|
- "That's a design decision. Capture it in design.md?"
|
||||||
|
- "This is a new requirement. Add it to specs?"
|
||||||
|
- "This changes scope. Update the proposal?"
|
||||||
|
|
||||||
|
4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What You Don't Have To Do
|
||||||
|
|
||||||
|
- Follow a script
|
||||||
|
- Ask the same questions every time
|
||||||
|
- Produce a specific artifact
|
||||||
|
- Reach a conclusion
|
||||||
|
- Stay on topic if a tangent is valuable
|
||||||
|
- Be brief (this is thinking time)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Handling Different Entry Points
|
||||||
|
|
||||||
|
**User brings a vague idea:**
|
||||||
|
```
|
||||||
|
User: I'm thinking about adding real-time collaboration
|
||||||
|
|
||||||
|
You: Real-time collab is a big space. Let me think about this...
|
||||||
|
|
||||||
|
COLLABORATION SPECTRUM
|
||||||
|
════════════════════════════════════════════
|
||||||
|
|
||||||
|
Awareness Coordination Sync
|
||||||
|
│ │ │
|
||||||
|
▼ ▼ ▼
|
||||||
|
┌────────┐ ┌────────┐ ┌────────┐
|
||||||
|
│Presence│ │Cursors │ │ CRDT │
|
||||||
|
│ "3 │ │ Multi │ │Conflict│
|
||||||
|
│online" │ │ select │ │ free │
|
||||||
|
└────────┘ └────────┘ └────────┘
|
||||||
|
│ │ │
|
||||||
|
trivial moderate complex
|
||||||
|
|
||||||
|
Where's your head at?
|
||||||
|
```
|
||||||
|
|
||||||
|
**User brings a specific problem:**
|
||||||
|
```
|
||||||
|
User: The auth system is a mess
|
||||||
|
|
||||||
|
You: [reads codebase]
|
||||||
|
|
||||||
|
┌─────────────────────────────────────────────┐
|
||||||
|
│ CURRENT AUTH FLOW │
|
||||||
|
└─────────────────────────────────────────────┘
|
||||||
|
│
|
||||||
|
┌─────────────┼─────────────┐
|
||||||
|
▼ ▼ ▼
|
||||||
|
┌─────────┐ ┌─────────┐ ┌─────────┐
|
||||||
|
│ Google │ │ GitHub │ │ Email │
|
||||||
|
│ OAuth │ │ OAuth │ │ Magic │
|
||||||
|
└────┬────┘ └────┬────┘ └────┬────┘
|
||||||
|
│ │ │
|
||||||
|
└─────────────┼─────────────┘
|
||||||
|
▼
|
||||||
|
┌───────────┐
|
||||||
|
│ Session │
|
||||||
|
└─────┬─────┘
|
||||||
|
│
|
||||||
|
▼
|
||||||
|
┌───────────┐
|
||||||
|
│ Perms │
|
||||||
|
└───────────┘
|
||||||
|
|
||||||
|
I see three tangles. Which one's burning?
|
||||||
|
```
|
||||||
|
|
||||||
|
**User is stuck mid-implementation:**
|
||||||
|
```
|
||||||
|
User: /opsx:explore add-auth-system
|
||||||
|
The OAuth integration is more complex than expected
|
||||||
|
|
||||||
|
You: [reads change artifacts]
|
||||||
|
|
||||||
|
You're on task 4: "Implement OAuth flow"
|
||||||
|
|
||||||
|
Let me trace what's involved...
|
||||||
|
|
||||||
|
[draws diagram, explores options, suggests paths]
|
||||||
|
|
||||||
|
Want to update the design to reflect this?
|
||||||
|
Or add a spike task to investigate?
|
||||||
|
```
|
||||||
|
|
||||||
|
**User wants to compare options:**
|
||||||
|
```
|
||||||
|
User: Should we use Postgres or SQLite?
|
||||||
|
|
||||||
|
You: Generic answer is boring. What's the context?
|
||||||
|
|
||||||
|
User: A CLI tool that tracks local dev environments
|
||||||
|
|
||||||
|
You: That changes everything.
|
||||||
|
|
||||||
|
┌─────────────────────────────────────────────────┐
|
||||||
|
│ CLI TOOL DATA STORAGE │
|
||||||
|
└─────────────────────────────────────────────────┘
|
||||||
|
|
||||||
|
Key constraints:
|
||||||
|
• No daemon running
|
||||||
|
• Must work offline
|
||||||
|
• Single user
|
||||||
|
|
||||||
|
SQLite Postgres
|
||||||
|
Deployment embedded ✓ needs server ✗
|
||||||
|
Offline yes ✓ no ✗
|
||||||
|
Single file yes ✓ no ✗
|
||||||
|
|
||||||
|
SQLite. Not even close.
|
||||||
|
|
||||||
|
Unless... is there a sync component?
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Ending Discovery
|
||||||
|
|
||||||
|
There's no required ending. Discovery might:
|
||||||
|
|
||||||
|
- **Flow into a proposal**: "Ready to start? I can create a change proposal."
|
||||||
|
- **Result in artifact updates**: "Updated design.md with these decisions"
|
||||||
|
- **Just provide clarity**: User has what they need, moves on
|
||||||
|
- **Continue later**: "We can pick this up anytime"
|
||||||
|
|
||||||
|
When it feels like things are crystallizing, you might summarize:
|
||||||
|
|
||||||
|
```
|
||||||
|
## What We Figured Out
|
||||||
|
|
||||||
|
**The problem**: [crystallized understanding]
|
||||||
|
|
||||||
|
**The approach**: [if one emerged]
|
||||||
|
|
||||||
|
**Open questions**: [if any remain]
|
||||||
|
|
||||||
|
**Next steps** (if ready):
|
||||||
|
- Create a change proposal
|
||||||
|
- Keep exploring: just keep talking
|
||||||
|
```
|
||||||
|
|
||||||
|
But this summary is optional. Sometimes the thinking IS the value.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Guardrails
|
||||||
|
|
||||||
|
- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
|
||||||
|
- **Don't fake understanding** - If something is unclear, dig deeper
|
||||||
|
- **Don't rush** - Discovery is thinking time, not task time
|
||||||
|
- **Don't force structure** - Let patterns emerge naturally
|
||||||
|
- **Don't auto-capture** - Offer to save insights, don't just do it
|
||||||
|
- **Do visualize** - A good diagram is worth many paragraphs
|
||||||
|
- **Do explore the codebase** - Ground discussions in reality
|
||||||
|
- **Do question assumptions** - Including the user's and your own
|
||||||
@@ -0,0 +1,110 @@
|
|||||||
|
---
|
||||||
|
name: openspec-propose
|
||||||
|
description: Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
|
||||||
|
license: MIT
|
||||||
|
compatibility: Requires openspec CLI.
|
||||||
|
metadata:
|
||||||
|
author: openspec
|
||||||
|
version: "1.0"
|
||||||
|
generatedBy: "1.2.0"
|
||||||
|
---
|
||||||
|
|
||||||
|
Propose a new change - create the change and generate all artifacts in one step.
|
||||||
|
|
||||||
|
I'll create a change with artifacts:
|
||||||
|
- proposal.md (what & why)
|
||||||
|
- design.md (how)
|
||||||
|
- tasks.md (implementation steps)
|
||||||
|
|
||||||
|
When ready to implement, run /opsx:apply
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **If no clear input provided, ask what they want to build**
|
||||||
|
|
||||||
|
Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
|
||||||
|
> "What change do you want to work on? Describe what you want to build or fix."
|
||||||
|
|
||||||
|
From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
|
||||||
|
|
||||||
|
**IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
|
||||||
|
|
||||||
|
2. **Create the change directory**
|
||||||
|
```bash
|
||||||
|
openspec new change "<name>"
|
||||||
|
```
|
||||||
|
This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
|
||||||
|
|
||||||
|
3. **Get the artifact build order**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>" --json
|
||||||
|
```
|
||||||
|
Parse the JSON to get:
|
||||||
|
- `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
|
||||||
|
- `artifacts`: list of all artifacts with their status and dependencies
|
||||||
|
|
||||||
|
4. **Create artifacts in sequence until apply-ready**
|
||||||
|
|
||||||
|
Use the **TodoWrite tool** to track progress through the artifacts.
|
||||||
|
|
||||||
|
Loop through artifacts in dependency order (artifacts with no pending dependencies first):
|
||||||
|
|
||||||
|
a. **For each artifact that is `ready` (dependencies satisfied)**:
|
||||||
|
- Get instructions:
|
||||||
|
```bash
|
||||||
|
openspec instructions <artifact-id> --change "<name>" --json
|
||||||
|
```
|
||||||
|
- The instructions JSON includes:
|
||||||
|
- `context`: Project background (constraints for you - do NOT include in output)
|
||||||
|
- `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
|
||||||
|
- `template`: The structure to use for your output file
|
||||||
|
- `instruction`: Schema-specific guidance for this artifact type
|
||||||
|
- `outputPath`: Where to write the artifact
|
||||||
|
- `dependencies`: Completed artifacts to read for context
|
||||||
|
- Read any completed dependency files for context
|
||||||
|
- Create the artifact file using `template` as the structure
|
||||||
|
- Apply `context` and `rules` as constraints - but do NOT copy them into the file
|
||||||
|
- Show brief progress: "Created <artifact-id>"
|
||||||
|
|
||||||
|
b. **Continue until all `applyRequires` artifacts are complete**
|
||||||
|
- After creating each artifact, re-run `openspec status --change "<name>" --json`
|
||||||
|
- Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
|
||||||
|
- Stop when all `applyRequires` artifacts are done
|
||||||
|
|
||||||
|
c. **If an artifact requires user input** (unclear context):
|
||||||
|
- Use **AskUserQuestion tool** to clarify
|
||||||
|
- Then continue with creation
|
||||||
|
|
||||||
|
5. **Show final status**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>"
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output**
|
||||||
|
|
||||||
|
After completing all artifacts, summarize:
|
||||||
|
- Change name and location
|
||||||
|
- List of artifacts created with brief descriptions
|
||||||
|
- What's ready: "All artifacts created! Ready for implementation."
|
||||||
|
- Prompt: "Run `/opsx:apply` or ask me to implement to start working on the tasks."
|
||||||
|
|
||||||
|
**Artifact Creation Guidelines**
|
||||||
|
|
||||||
|
- Follow the `instruction` field from `openspec instructions` for each artifact type
|
||||||
|
- The schema defines what each artifact should contain - follow it
|
||||||
|
- Read dependency artifacts for context before creating new ones
|
||||||
|
- Use `template` as the structure for your output file - fill in its sections
|
||||||
|
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
|
||||||
|
- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
|
||||||
|
- These guide what you write, but should never appear in the output
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
|
||||||
|
- Always read dependency artifacts before creating a new one
|
||||||
|
- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
|
||||||
|
- If a change with that name already exists, ask if user wants to continue it or create a new one
|
||||||
|
- Verify each artifact file exists after writing before proceeding to next
|
||||||
+10
@@ -0,0 +1,10 @@
|
|||||||
|
# Python-generated files
|
||||||
|
__pycache__/
|
||||||
|
*.py[oc]
|
||||||
|
build/
|
||||||
|
dist/
|
||||||
|
wheels/
|
||||||
|
*.egg-info
|
||||||
|
|
||||||
|
# Virtual environments
|
||||||
|
.venv
|
||||||
@@ -0,0 +1,149 @@
|
|||||||
|
---
|
||||||
|
description: Implement tasks from an OpenSpec change (Experimental)
|
||||||
|
---
|
||||||
|
|
||||||
|
Implement tasks from an OpenSpec change.
|
||||||
|
|
||||||
|
**Input**: Optionally specify a change name (e.g., `/opsx-apply add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **Select the change**
|
||||||
|
|
||||||
|
If a name is provided, use it. Otherwise:
|
||||||
|
- Infer from conversation context if the user mentioned a change
|
||||||
|
- Auto-select if only one active change exists
|
||||||
|
- If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
|
||||||
|
|
||||||
|
Always announce: "Using change: <name>" and how to override (e.g., `/opsx-apply <other>`).
|
||||||
|
|
||||||
|
2. **Check status to understand the schema**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>" --json
|
||||||
|
```
|
||||||
|
Parse the JSON to understand:
|
||||||
|
- `schemaName`: The workflow being used (e.g., "spec-driven")
|
||||||
|
- Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
|
||||||
|
|
||||||
|
3. **Get apply instructions**
|
||||||
|
|
||||||
|
```bash
|
||||||
|
openspec instructions apply --change "<name>" --json
|
||||||
|
```
|
||||||
|
|
||||||
|
This returns:
|
||||||
|
- Context file paths (varies by schema)
|
||||||
|
- Progress (total, complete, remaining)
|
||||||
|
- Task list with status
|
||||||
|
- Dynamic instruction based on current state
|
||||||
|
|
||||||
|
**Handle states:**
|
||||||
|
- If `state: "blocked"` (missing artifacts): show message, suggest using `/opsx-continue`
|
||||||
|
- If `state: "all_done"`: congratulate, suggest archive
|
||||||
|
- Otherwise: proceed to implementation
|
||||||
|
|
||||||
|
4. **Read context files**
|
||||||
|
|
||||||
|
Read the files listed in `contextFiles` from the apply instructions output.
|
||||||
|
The files depend on the schema being used:
|
||||||
|
- **spec-driven**: proposal, specs, design, tasks
|
||||||
|
- Other schemas: follow the contextFiles from CLI output
|
||||||
|
|
||||||
|
5. **Show current progress**
|
||||||
|
|
||||||
|
Display:
|
||||||
|
- Schema being used
|
||||||
|
- Progress: "N/M tasks complete"
|
||||||
|
- Remaining tasks overview
|
||||||
|
- Dynamic instruction from CLI
|
||||||
|
|
||||||
|
6. **Implement tasks (loop until done or blocked)**
|
||||||
|
|
||||||
|
For each pending task:
|
||||||
|
- Show which task is being worked on
|
||||||
|
- Make the code changes required
|
||||||
|
- Keep changes minimal and focused
|
||||||
|
- Mark task complete in the tasks file: `- [ ]` → `- [x]`
|
||||||
|
- Continue to next task
|
||||||
|
|
||||||
|
**Pause if:**
|
||||||
|
- Task is unclear → ask for clarification
|
||||||
|
- Implementation reveals a design issue → suggest updating artifacts
|
||||||
|
- Error or blocker encountered → report and wait for guidance
|
||||||
|
- User interrupts
|
||||||
|
|
||||||
|
7. **On completion or pause, show status**
|
||||||
|
|
||||||
|
Display:
|
||||||
|
- Tasks completed this session
|
||||||
|
- Overall progress: "N/M tasks complete"
|
||||||
|
- If all done: suggest archive
|
||||||
|
- If paused: explain why and wait for guidance
|
||||||
|
|
||||||
|
**Output During Implementation**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementing: <change-name> (schema: <schema-name>)
|
||||||
|
|
||||||
|
Working on task 3/7: <task description>
|
||||||
|
[...implementation happening...]
|
||||||
|
✓ Task complete
|
||||||
|
|
||||||
|
Working on task 4/7: <task description>
|
||||||
|
[...implementation happening...]
|
||||||
|
✓ Task complete
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Completion**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementation Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Progress:** 7/7 tasks complete ✓
|
||||||
|
|
||||||
|
### Completed This Session
|
||||||
|
- [x] Task 1
|
||||||
|
- [x] Task 2
|
||||||
|
...
|
||||||
|
|
||||||
|
All tasks complete! You can archive this change with `/opsx-archive`.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Pause (Issue Encountered)**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementation Paused
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Progress:** 4/7 tasks complete
|
||||||
|
|
||||||
|
### Issue Encountered
|
||||||
|
<description of the issue>
|
||||||
|
|
||||||
|
**Options:**
|
||||||
|
1. <option 1>
|
||||||
|
2. <option 2>
|
||||||
|
3. Other approach
|
||||||
|
|
||||||
|
What would you like to do?
|
||||||
|
```
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Keep going through tasks until done or blocked
|
||||||
|
- Always read context files before starting (from the apply instructions output)
|
||||||
|
- If task is ambiguous, pause and ask before implementing
|
||||||
|
- If implementation reveals issues, pause and suggest artifact updates
|
||||||
|
- Keep code changes minimal and scoped to each task
|
||||||
|
- Update task checkbox immediately after completing each task
|
||||||
|
- Pause on errors, blockers, or unclear requirements - don't guess
|
||||||
|
- Use contextFiles from CLI output, don't assume specific file names
|
||||||
|
|
||||||
|
**Fluid Workflow Integration**
|
||||||
|
|
||||||
|
This skill supports the "actions on a change" model:
|
||||||
|
|
||||||
|
- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
|
||||||
|
- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
|
||||||
@@ -0,0 +1,154 @@
|
|||||||
|
---
|
||||||
|
description: Archive a completed change in the experimental workflow
|
||||||
|
---
|
||||||
|
|
||||||
|
Archive a completed change in the experimental workflow.
|
||||||
|
|
||||||
|
**Input**: Optionally specify a change name after `/opsx-archive` (e.g., `/opsx-archive add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **If no change name provided, prompt for selection**
|
||||||
|
|
||||||
|
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||||
|
|
||||||
|
Show only active changes (not already archived).
|
||||||
|
Include the schema used for each change if available.
|
||||||
|
|
||||||
|
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||||
|
|
||||||
|
2. **Check artifact completion status**
|
||||||
|
|
||||||
|
Run `openspec status --change "<name>" --json` to check artifact completion.
|
||||||
|
|
||||||
|
Parse the JSON to understand:
|
||||||
|
- `schemaName`: The workflow being used
|
||||||
|
- `artifacts`: List of artifacts with their status (`done` or other)
|
||||||
|
|
||||||
|
**If any artifacts are not `done`:**
|
||||||
|
- Display warning listing incomplete artifacts
|
||||||
|
- Prompt user for confirmation to continue
|
||||||
|
- Proceed if user confirms
|
||||||
|
|
||||||
|
3. **Check task completion status**
|
||||||
|
|
||||||
|
Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
|
||||||
|
|
||||||
|
Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
|
||||||
|
|
||||||
|
**If incomplete tasks found:**
|
||||||
|
- Display warning showing count of incomplete tasks
|
||||||
|
- Prompt user for confirmation to continue
|
||||||
|
- Proceed if user confirms
|
||||||
|
|
||||||
|
**If no tasks file exists:** Proceed without task-related warning.
|
||||||
|
|
||||||
|
4. **Assess delta spec sync state**
|
||||||
|
|
||||||
|
Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
|
||||||
|
|
||||||
|
**If delta specs exist:**
|
||||||
|
- Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
|
||||||
|
- Determine what changes would be applied (adds, modifications, removals, renames)
|
||||||
|
- Show a combined summary before prompting
|
||||||
|
|
||||||
|
**Prompt options:**
|
||||||
|
- If changes needed: "Sync now (recommended)", "Archive without syncing"
|
||||||
|
- If already synced: "Archive now", "Sync anyway", "Cancel"
|
||||||
|
|
||||||
|
If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
|
||||||
|
|
||||||
|
5. **Perform the archive**
|
||||||
|
|
||||||
|
Create the archive directory if it doesn't exist:
|
||||||
|
```bash
|
||||||
|
mkdir -p openspec/changes/archive
|
||||||
|
```
|
||||||
|
|
||||||
|
Generate target name using current date: `YYYY-MM-DD-<change-name>`
|
||||||
|
|
||||||
|
**Check if target already exists:**
|
||||||
|
- If yes: Fail with error, suggest renaming existing archive or using different date
|
||||||
|
- If no: Move the change directory to archive
|
||||||
|
|
||||||
|
```bash
|
||||||
|
mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
|
||||||
|
```
|
||||||
|
|
||||||
|
6. **Display summary**
|
||||||
|
|
||||||
|
Show archive completion summary including:
|
||||||
|
- Change name
|
||||||
|
- Schema that was used
|
||||||
|
- Archive location
|
||||||
|
- Spec sync status (synced / sync skipped / no delta specs)
|
||||||
|
- Note about any warnings (incomplete artifacts/tasks)
|
||||||
|
|
||||||
|
**Output On Success**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
**Specs:** ✓ Synced to main specs
|
||||||
|
|
||||||
|
All artifacts complete. All tasks complete.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Success (No Delta Specs)**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
**Specs:** No delta specs
|
||||||
|
|
||||||
|
All artifacts complete. All tasks complete.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Success With Warnings**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Complete (with warnings)
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
**Specs:** Sync skipped (user chose to skip)
|
||||||
|
|
||||||
|
**Warnings:**
|
||||||
|
- Archived with 2 incomplete artifacts
|
||||||
|
- Archived with 3 incomplete tasks
|
||||||
|
- Delta spec sync was skipped (user chose to skip)
|
||||||
|
|
||||||
|
Review the archive if this was not intentional.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Error (Archive Exists)**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Failed
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Target:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
|
||||||
|
Target archive directory already exists.
|
||||||
|
|
||||||
|
**Options:**
|
||||||
|
1. Rename the existing archive
|
||||||
|
2. Delete the existing archive if it's a duplicate
|
||||||
|
3. Wait until a different date to archive
|
||||||
|
```
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Always prompt for change selection if not provided
|
||||||
|
- Use artifact graph (openspec status --json) for completion checking
|
||||||
|
- Don't block archive on warnings - just inform and confirm
|
||||||
|
- Preserve .openspec.yaml when moving to archive (it moves with the directory)
|
||||||
|
- Show clear summary of what happened
|
||||||
|
- If sync is requested, use the Skill tool to invoke `openspec-sync-specs` (agent-driven)
|
||||||
|
- If delta specs exist, always run the sync assessment and show the combined summary before prompting
|
||||||
@@ -0,0 +1,170 @@
|
|||||||
|
---
|
||||||
|
description: Enter explore mode - think through ideas, investigate problems, clarify requirements
|
||||||
|
---
|
||||||
|
|
||||||
|
Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
|
||||||
|
|
||||||
|
**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
|
||||||
|
|
||||||
|
**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
|
||||||
|
|
||||||
|
**Input**: The argument after `/opsx-explore` is whatever the user wants to think about. Could be:
|
||||||
|
- A vague idea: "real-time collaboration"
|
||||||
|
- A specific problem: "the auth system is getting unwieldy"
|
||||||
|
- A change name: "add-dark-mode" (to explore in context of that change)
|
||||||
|
- A comparison: "postgres vs sqlite for this"
|
||||||
|
- Nothing (just enter explore mode)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## The Stance
|
||||||
|
|
||||||
|
- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
|
||||||
|
- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
|
||||||
|
- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
|
||||||
|
- **Adaptive** - Follow interesting threads, pivot when new information emerges
|
||||||
|
- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
|
||||||
|
- **Grounded** - Explore the actual codebase when relevant, don't just theorize
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What You Might Do
|
||||||
|
|
||||||
|
Depending on what the user brings, you might:
|
||||||
|
|
||||||
|
**Explore the problem space**
|
||||||
|
- Ask clarifying questions that emerge from what they said
|
||||||
|
- Challenge assumptions
|
||||||
|
- Reframe the problem
|
||||||
|
- Find analogies
|
||||||
|
|
||||||
|
**Investigate the codebase**
|
||||||
|
- Map existing architecture relevant to the discussion
|
||||||
|
- Find integration points
|
||||||
|
- Identify patterns already in use
|
||||||
|
- Surface hidden complexity
|
||||||
|
|
||||||
|
**Compare options**
|
||||||
|
- Brainstorm multiple approaches
|
||||||
|
- Build comparison tables
|
||||||
|
- Sketch tradeoffs
|
||||||
|
- Recommend a path (if asked)
|
||||||
|
|
||||||
|
**Visualize**
|
||||||
|
```
|
||||||
|
┌─────────────────────────────────────────┐
|
||||||
|
│ Use ASCII diagrams liberally │
|
||||||
|
├─────────────────────────────────────────┤
|
||||||
|
│ │
|
||||||
|
│ ┌────────┐ ┌────────┐ │
|
||||||
|
│ │ State │────────▶│ State │ │
|
||||||
|
│ │ A │ │ B │ │
|
||||||
|
│ └────────┘ └────────┘ │
|
||||||
|
│ │
|
||||||
|
│ System diagrams, state machines, │
|
||||||
|
│ data flows, architecture sketches, │
|
||||||
|
│ dependency graphs, comparison tables │
|
||||||
|
│ │
|
||||||
|
└─────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
**Surface risks and unknowns**
|
||||||
|
- Identify what could go wrong
|
||||||
|
- Find gaps in understanding
|
||||||
|
- Suggest spikes or investigations
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## OpenSpec Awareness
|
||||||
|
|
||||||
|
You have full context of the OpenSpec system. Use it naturally, don't force it.
|
||||||
|
|
||||||
|
### Check for context
|
||||||
|
|
||||||
|
At the start, quickly check what exists:
|
||||||
|
```bash
|
||||||
|
openspec list --json
|
||||||
|
```
|
||||||
|
|
||||||
|
This tells you:
|
||||||
|
- If there are active changes
|
||||||
|
- Their names, schemas, and status
|
||||||
|
- What the user might be working on
|
||||||
|
|
||||||
|
If the user mentioned a specific change name, read its artifacts for context.
|
||||||
|
|
||||||
|
### When no change exists
|
||||||
|
|
||||||
|
Think freely. When insights crystallize, you might offer:
|
||||||
|
|
||||||
|
- "This feels solid enough to start a change. Want me to create a proposal?"
|
||||||
|
- Or keep exploring - no pressure to formalize
|
||||||
|
|
||||||
|
### When a change exists
|
||||||
|
|
||||||
|
If the user mentions a change or you detect one is relevant:
|
||||||
|
|
||||||
|
1. **Read existing artifacts for context**
|
||||||
|
- `openspec/changes/<name>/proposal.md`
|
||||||
|
- `openspec/changes/<name>/design.md`
|
||||||
|
- `openspec/changes/<name>/tasks.md`
|
||||||
|
- etc.
|
||||||
|
|
||||||
|
2. **Reference them naturally in conversation**
|
||||||
|
- "Your design mentions using Redis, but we just realized SQLite fits better..."
|
||||||
|
- "The proposal scopes this to premium users, but we're now thinking everyone..."
|
||||||
|
|
||||||
|
3. **Offer to capture when decisions are made**
|
||||||
|
|
||||||
|
| Insight Type | Where to Capture |
|
||||||
|
|--------------|------------------|
|
||||||
|
| New requirement discovered | `specs/<capability>/spec.md` |
|
||||||
|
| Requirement changed | `specs/<capability>/spec.md` |
|
||||||
|
| Design decision made | `design.md` |
|
||||||
|
| Scope changed | `proposal.md` |
|
||||||
|
| New work identified | `tasks.md` |
|
||||||
|
| Assumption invalidated | Relevant artifact |
|
||||||
|
|
||||||
|
Example offers:
|
||||||
|
- "That's a design decision. Capture it in design.md?"
|
||||||
|
- "This is a new requirement. Add it to specs?"
|
||||||
|
- "This changes scope. Update the proposal?"
|
||||||
|
|
||||||
|
4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What You Don't Have To Do
|
||||||
|
|
||||||
|
- Follow a script
|
||||||
|
- Ask the same questions every time
|
||||||
|
- Produce a specific artifact
|
||||||
|
- Reach a conclusion
|
||||||
|
- Stay on topic if a tangent is valuable
|
||||||
|
- Be brief (this is thinking time)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Ending Discovery
|
||||||
|
|
||||||
|
There's no required ending. Discovery might:
|
||||||
|
|
||||||
|
- **Flow into a proposal**: "Ready to start? I can create a change proposal."
|
||||||
|
- **Result in artifact updates**: "Updated design.md with these decisions"
|
||||||
|
- **Just provide clarity**: User has what they need, moves on
|
||||||
|
- **Continue later**: "We can pick this up anytime"
|
||||||
|
|
||||||
|
When things crystallize, you might offer a summary - but it's optional. Sometimes the thinking IS the value.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Guardrails
|
||||||
|
|
||||||
|
- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
|
||||||
|
- **Don't fake understanding** - If something is unclear, dig deeper
|
||||||
|
- **Don't rush** - Discovery is thinking time, not task time
|
||||||
|
- **Don't force structure** - Let patterns emerge naturally
|
||||||
|
- **Don't auto-capture** - Offer to save insights, don't just do it
|
||||||
|
- **Do visualize** - A good diagram is worth many paragraphs
|
||||||
|
- **Do explore the codebase** - Ground discussions in reality
|
||||||
|
- **Do question assumptions** - Including the user's and your own
|
||||||
@@ -0,0 +1,103 @@
|
|||||||
|
---
|
||||||
|
description: Propose a new change - create it and generate all artifacts in one step
|
||||||
|
---
|
||||||
|
|
||||||
|
Propose a new change - create the change and generate all artifacts in one step.
|
||||||
|
|
||||||
|
I'll create a change with artifacts:
|
||||||
|
- proposal.md (what & why)
|
||||||
|
- design.md (how)
|
||||||
|
- tasks.md (implementation steps)
|
||||||
|
|
||||||
|
When ready to implement, run /opsx-apply
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
**Input**: The argument after `/opsx-propose` is the change name (kebab-case), OR a description of what the user wants to build.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **If no input provided, ask what they want to build**
|
||||||
|
|
||||||
|
Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
|
||||||
|
> "What change do you want to work on? Describe what you want to build or fix."
|
||||||
|
|
||||||
|
From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
|
||||||
|
|
||||||
|
**IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
|
||||||
|
|
||||||
|
2. **Create the change directory**
|
||||||
|
```bash
|
||||||
|
openspec new change "<name>"
|
||||||
|
```
|
||||||
|
This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
|
||||||
|
|
||||||
|
3. **Get the artifact build order**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>" --json
|
||||||
|
```
|
||||||
|
Parse the JSON to get:
|
||||||
|
- `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
|
||||||
|
- `artifacts`: list of all artifacts with their status and dependencies
|
||||||
|
|
||||||
|
4. **Create artifacts in sequence until apply-ready**
|
||||||
|
|
||||||
|
Use the **TodoWrite tool** to track progress through the artifacts.
|
||||||
|
|
||||||
|
Loop through artifacts in dependency order (artifacts with no pending dependencies first):
|
||||||
|
|
||||||
|
a. **For each artifact that is `ready` (dependencies satisfied)**:
|
||||||
|
- Get instructions:
|
||||||
|
```bash
|
||||||
|
openspec instructions <artifact-id> --change "<name>" --json
|
||||||
|
```
|
||||||
|
- The instructions JSON includes:
|
||||||
|
- `context`: Project background (constraints for you - do NOT include in output)
|
||||||
|
- `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
|
||||||
|
- `template`: The structure to use for your output file
|
||||||
|
- `instruction`: Schema-specific guidance for this artifact type
|
||||||
|
- `outputPath`: Where to write the artifact
|
||||||
|
- `dependencies`: Completed artifacts to read for context
|
||||||
|
- Read any completed dependency files for context
|
||||||
|
- Create the artifact file using `template` as the structure
|
||||||
|
- Apply `context` and `rules` as constraints - but do NOT copy them into the file
|
||||||
|
- Show brief progress: "Created <artifact-id>"
|
||||||
|
|
||||||
|
b. **Continue until all `applyRequires` artifacts are complete**
|
||||||
|
- After creating each artifact, re-run `openspec status --change "<name>" --json`
|
||||||
|
- Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
|
||||||
|
- Stop when all `applyRequires` artifacts are done
|
||||||
|
|
||||||
|
c. **If an artifact requires user input** (unclear context):
|
||||||
|
- Use **AskUserQuestion tool** to clarify
|
||||||
|
- Then continue with creation
|
||||||
|
|
||||||
|
5. **Show final status**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>"
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output**
|
||||||
|
|
||||||
|
After completing all artifacts, summarize:
|
||||||
|
- Change name and location
|
||||||
|
- List of artifacts created with brief descriptions
|
||||||
|
- What's ready: "All artifacts created! Ready for implementation."
|
||||||
|
- Prompt: "Run `/opsx-apply` to start implementing."
|
||||||
|
|
||||||
|
**Artifact Creation Guidelines**
|
||||||
|
|
||||||
|
- Follow the `instruction` field from `openspec instructions` for each artifact type
|
||||||
|
- The schema defines what each artifact should contain - follow it
|
||||||
|
- Read dependency artifacts for context before creating new ones
|
||||||
|
- Use `template` as the structure for your output file - fill in its sections
|
||||||
|
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
|
||||||
|
- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
|
||||||
|
- These guide what you write, but should never appear in the output
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
|
||||||
|
- Always read dependency artifacts before creating a new one
|
||||||
|
- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
|
||||||
|
- If a change with that name already exists, ask if user wants to continue it or create a new one
|
||||||
|
- Verify each artifact file exists after writing before proceeding to next
|
||||||
@@ -0,0 +1,156 @@
|
|||||||
|
---
|
||||||
|
name: openspec-apply-change
|
||||||
|
description: Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
|
||||||
|
license: MIT
|
||||||
|
compatibility: Requires openspec CLI.
|
||||||
|
metadata:
|
||||||
|
author: openspec
|
||||||
|
version: "1.0"
|
||||||
|
generatedBy: "1.2.0"
|
||||||
|
---
|
||||||
|
|
||||||
|
Implement tasks from an OpenSpec change.
|
||||||
|
|
||||||
|
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **Select the change**
|
||||||
|
|
||||||
|
If a name is provided, use it. Otherwise:
|
||||||
|
- Infer from conversation context if the user mentioned a change
|
||||||
|
- Auto-select if only one active change exists
|
||||||
|
- If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
|
||||||
|
|
||||||
|
Always announce: "Using change: <name>" and how to override (e.g., `/opsx-apply <other>`).
|
||||||
|
|
||||||
|
2. **Check status to understand the schema**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>" --json
|
||||||
|
```
|
||||||
|
Parse the JSON to understand:
|
||||||
|
- `schemaName`: The workflow being used (e.g., "spec-driven")
|
||||||
|
- Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
|
||||||
|
|
||||||
|
3. **Get apply instructions**
|
||||||
|
|
||||||
|
```bash
|
||||||
|
openspec instructions apply --change "<name>" --json
|
||||||
|
```
|
||||||
|
|
||||||
|
This returns:
|
||||||
|
- Context file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)
|
||||||
|
- Progress (total, complete, remaining)
|
||||||
|
- Task list with status
|
||||||
|
- Dynamic instruction based on current state
|
||||||
|
|
||||||
|
**Handle states:**
|
||||||
|
- If `state: "blocked"` (missing artifacts): show message, suggest using openspec-continue-change
|
||||||
|
- If `state: "all_done"`: congratulate, suggest archive
|
||||||
|
- Otherwise: proceed to implementation
|
||||||
|
|
||||||
|
4. **Read context files**
|
||||||
|
|
||||||
|
Read the files listed in `contextFiles` from the apply instructions output.
|
||||||
|
The files depend on the schema being used:
|
||||||
|
- **spec-driven**: proposal, specs, design, tasks
|
||||||
|
- Other schemas: follow the contextFiles from CLI output
|
||||||
|
|
||||||
|
5. **Show current progress**
|
||||||
|
|
||||||
|
Display:
|
||||||
|
- Schema being used
|
||||||
|
- Progress: "N/M tasks complete"
|
||||||
|
- Remaining tasks overview
|
||||||
|
- Dynamic instruction from CLI
|
||||||
|
|
||||||
|
6. **Implement tasks (loop until done or blocked)**
|
||||||
|
|
||||||
|
For each pending task:
|
||||||
|
- Show which task is being worked on
|
||||||
|
- Make the code changes required
|
||||||
|
- Keep changes minimal and focused
|
||||||
|
- Mark task complete in the tasks file: `- [ ]` → `- [x]`
|
||||||
|
- Continue to next task
|
||||||
|
|
||||||
|
**Pause if:**
|
||||||
|
- Task is unclear → ask for clarification
|
||||||
|
- Implementation reveals a design issue → suggest updating artifacts
|
||||||
|
- Error or blocker encountered → report and wait for guidance
|
||||||
|
- User interrupts
|
||||||
|
|
||||||
|
7. **On completion or pause, show status**
|
||||||
|
|
||||||
|
Display:
|
||||||
|
- Tasks completed this session
|
||||||
|
- Overall progress: "N/M tasks complete"
|
||||||
|
- If all done: suggest archive
|
||||||
|
- If paused: explain why and wait for guidance
|
||||||
|
|
||||||
|
**Output During Implementation**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementing: <change-name> (schema: <schema-name>)
|
||||||
|
|
||||||
|
Working on task 3/7: <task description>
|
||||||
|
[...implementation happening...]
|
||||||
|
✓ Task complete
|
||||||
|
|
||||||
|
Working on task 4/7: <task description>
|
||||||
|
[...implementation happening...]
|
||||||
|
✓ Task complete
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Completion**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementation Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Progress:** 7/7 tasks complete ✓
|
||||||
|
|
||||||
|
### Completed This Session
|
||||||
|
- [x] Task 1
|
||||||
|
- [x] Task 2
|
||||||
|
...
|
||||||
|
|
||||||
|
All tasks complete! Ready to archive this change.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output On Pause (Issue Encountered)**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Implementation Paused
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Progress:** 4/7 tasks complete
|
||||||
|
|
||||||
|
### Issue Encountered
|
||||||
|
<description of the issue>
|
||||||
|
|
||||||
|
**Options:**
|
||||||
|
1. <option 1>
|
||||||
|
2. <option 2>
|
||||||
|
3. Other approach
|
||||||
|
|
||||||
|
What would you like to do?
|
||||||
|
```
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Keep going through tasks until done or blocked
|
||||||
|
- Always read context files before starting (from the apply instructions output)
|
||||||
|
- If task is ambiguous, pause and ask before implementing
|
||||||
|
- If implementation reveals issues, pause and suggest artifact updates
|
||||||
|
- Keep code changes minimal and scoped to each task
|
||||||
|
- Update task checkbox immediately after completing each task
|
||||||
|
- Pause on errors, blockers, or unclear requirements - don't guess
|
||||||
|
- Use contextFiles from CLI output, don't assume specific file names
|
||||||
|
|
||||||
|
**Fluid Workflow Integration**
|
||||||
|
|
||||||
|
This skill supports the "actions on a change" model:
|
||||||
|
|
||||||
|
- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
|
||||||
|
- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
|
||||||
@@ -0,0 +1,114 @@
|
|||||||
|
---
|
||||||
|
name: openspec-archive-change
|
||||||
|
description: Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
|
||||||
|
license: MIT
|
||||||
|
compatibility: Requires openspec CLI.
|
||||||
|
metadata:
|
||||||
|
author: openspec
|
||||||
|
version: "1.0"
|
||||||
|
generatedBy: "1.2.0"
|
||||||
|
---
|
||||||
|
|
||||||
|
Archive a completed change in the experimental workflow.
|
||||||
|
|
||||||
|
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **If no change name provided, prompt for selection**
|
||||||
|
|
||||||
|
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||||
|
|
||||||
|
Show only active changes (not already archived).
|
||||||
|
Include the schema used for each change if available.
|
||||||
|
|
||||||
|
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||||
|
|
||||||
|
2. **Check artifact completion status**
|
||||||
|
|
||||||
|
Run `openspec status --change "<name>" --json` to check artifact completion.
|
||||||
|
|
||||||
|
Parse the JSON to understand:
|
||||||
|
- `schemaName`: The workflow being used
|
||||||
|
- `artifacts`: List of artifacts with their status (`done` or other)
|
||||||
|
|
||||||
|
**If any artifacts are not `done`:**
|
||||||
|
- Display warning listing incomplete artifacts
|
||||||
|
- Use **AskUserQuestion tool** to confirm user wants to proceed
|
||||||
|
- Proceed if user confirms
|
||||||
|
|
||||||
|
3. **Check task completion status**
|
||||||
|
|
||||||
|
Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
|
||||||
|
|
||||||
|
Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
|
||||||
|
|
||||||
|
**If incomplete tasks found:**
|
||||||
|
- Display warning showing count of incomplete tasks
|
||||||
|
- Use **AskUserQuestion tool** to confirm user wants to proceed
|
||||||
|
- Proceed if user confirms
|
||||||
|
|
||||||
|
**If no tasks file exists:** Proceed without task-related warning.
|
||||||
|
|
||||||
|
4. **Assess delta spec sync state**
|
||||||
|
|
||||||
|
Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
|
||||||
|
|
||||||
|
**If delta specs exist:**
|
||||||
|
- Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
|
||||||
|
- Determine what changes would be applied (adds, modifications, removals, renames)
|
||||||
|
- Show a combined summary before prompting
|
||||||
|
|
||||||
|
**Prompt options:**
|
||||||
|
- If changes needed: "Sync now (recommended)", "Archive without syncing"
|
||||||
|
- If already synced: "Archive now", "Sync anyway", "Cancel"
|
||||||
|
|
||||||
|
If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
|
||||||
|
|
||||||
|
5. **Perform the archive**
|
||||||
|
|
||||||
|
Create the archive directory if it doesn't exist:
|
||||||
|
```bash
|
||||||
|
mkdir -p openspec/changes/archive
|
||||||
|
```
|
||||||
|
|
||||||
|
Generate target name using current date: `YYYY-MM-DD-<change-name>`
|
||||||
|
|
||||||
|
**Check if target already exists:**
|
||||||
|
- If yes: Fail with error, suggest renaming existing archive or using different date
|
||||||
|
- If no: Move the change directory to archive
|
||||||
|
|
||||||
|
```bash
|
||||||
|
mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
|
||||||
|
```
|
||||||
|
|
||||||
|
6. **Display summary**
|
||||||
|
|
||||||
|
Show archive completion summary including:
|
||||||
|
- Change name
|
||||||
|
- Schema that was used
|
||||||
|
- Archive location
|
||||||
|
- Whether specs were synced (if applicable)
|
||||||
|
- Note about any warnings (incomplete artifacts/tasks)
|
||||||
|
|
||||||
|
**Output On Success**
|
||||||
|
|
||||||
|
```
|
||||||
|
## Archive Complete
|
||||||
|
|
||||||
|
**Change:** <change-name>
|
||||||
|
**Schema:** <schema-name>
|
||||||
|
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||||
|
**Specs:** ✓ Synced to main specs (or "No delta specs" or "Sync skipped")
|
||||||
|
|
||||||
|
All artifacts complete. All tasks complete.
|
||||||
|
```
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Always prompt for change selection if not provided
|
||||||
|
- Use artifact graph (openspec status --json) for completion checking
|
||||||
|
- Don't block archive on warnings - just inform and confirm
|
||||||
|
- Preserve .openspec.yaml when moving to archive (it moves with the directory)
|
||||||
|
- Show clear summary of what happened
|
||||||
|
- If sync is requested, use openspec-sync-specs approach (agent-driven)
|
||||||
|
- If delta specs exist, always run the sync assessment and show the combined summary before prompting
|
||||||
@@ -0,0 +1,288 @@
|
|||||||
|
---
|
||||||
|
name: openspec-explore
|
||||||
|
description: Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
|
||||||
|
license: MIT
|
||||||
|
compatibility: Requires openspec CLI.
|
||||||
|
metadata:
|
||||||
|
author: openspec
|
||||||
|
version: "1.0"
|
||||||
|
generatedBy: "1.2.0"
|
||||||
|
---
|
||||||
|
|
||||||
|
Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
|
||||||
|
|
||||||
|
**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
|
||||||
|
|
||||||
|
**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## The Stance
|
||||||
|
|
||||||
|
- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
|
||||||
|
- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
|
||||||
|
- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
|
||||||
|
- **Adaptive** - Follow interesting threads, pivot when new information emerges
|
||||||
|
- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
|
||||||
|
- **Grounded** - Explore the actual codebase when relevant, don't just theorize
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What You Might Do
|
||||||
|
|
||||||
|
Depending on what the user brings, you might:
|
||||||
|
|
||||||
|
**Explore the problem space**
|
||||||
|
- Ask clarifying questions that emerge from what they said
|
||||||
|
- Challenge assumptions
|
||||||
|
- Reframe the problem
|
||||||
|
- Find analogies
|
||||||
|
|
||||||
|
**Investigate the codebase**
|
||||||
|
- Map existing architecture relevant to the discussion
|
||||||
|
- Find integration points
|
||||||
|
- Identify patterns already in use
|
||||||
|
- Surface hidden complexity
|
||||||
|
|
||||||
|
**Compare options**
|
||||||
|
- Brainstorm multiple approaches
|
||||||
|
- Build comparison tables
|
||||||
|
- Sketch tradeoffs
|
||||||
|
- Recommend a path (if asked)
|
||||||
|
|
||||||
|
**Visualize**
|
||||||
|
```
|
||||||
|
┌─────────────────────────────────────────┐
|
||||||
|
│ Use ASCII diagrams liberally │
|
||||||
|
├─────────────────────────────────────────┤
|
||||||
|
│ │
|
||||||
|
│ ┌────────┐ ┌────────┐ │
|
||||||
|
│ │ State │────────▶│ State │ │
|
||||||
|
│ │ A │ │ B │ │
|
||||||
|
│ └────────┘ └────────┘ │
|
||||||
|
│ │
|
||||||
|
│ System diagrams, state machines, │
|
||||||
|
│ data flows, architecture sketches, │
|
||||||
|
│ dependency graphs, comparison tables │
|
||||||
|
│ │
|
||||||
|
└─────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
**Surface risks and unknowns**
|
||||||
|
- Identify what could go wrong
|
||||||
|
- Find gaps in understanding
|
||||||
|
- Suggest spikes or investigations
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## OpenSpec Awareness
|
||||||
|
|
||||||
|
You have full context of the OpenSpec system. Use it naturally, don't force it.
|
||||||
|
|
||||||
|
### Check for context
|
||||||
|
|
||||||
|
At the start, quickly check what exists:
|
||||||
|
```bash
|
||||||
|
openspec list --json
|
||||||
|
```
|
||||||
|
|
||||||
|
This tells you:
|
||||||
|
- If there are active changes
|
||||||
|
- Their names, schemas, and status
|
||||||
|
- What the user might be working on
|
||||||
|
|
||||||
|
### When no change exists
|
||||||
|
|
||||||
|
Think freely. When insights crystallize, you might offer:
|
||||||
|
|
||||||
|
- "This feels solid enough to start a change. Want me to create a proposal?"
|
||||||
|
- Or keep exploring - no pressure to formalize
|
||||||
|
|
||||||
|
### When a change exists
|
||||||
|
|
||||||
|
If the user mentions a change or you detect one is relevant:
|
||||||
|
|
||||||
|
1. **Read existing artifacts for context**
|
||||||
|
- `openspec/changes/<name>/proposal.md`
|
||||||
|
- `openspec/changes/<name>/design.md`
|
||||||
|
- `openspec/changes/<name>/tasks.md`
|
||||||
|
- etc.
|
||||||
|
|
||||||
|
2. **Reference them naturally in conversation**
|
||||||
|
- "Your design mentions using Redis, but we just realized SQLite fits better..."
|
||||||
|
- "The proposal scopes this to premium users, but we're now thinking everyone..."
|
||||||
|
|
||||||
|
3. **Offer to capture when decisions are made**
|
||||||
|
|
||||||
|
| Insight Type | Where to Capture |
|
||||||
|
|--------------|------------------|
|
||||||
|
| New requirement discovered | `specs/<capability>/spec.md` |
|
||||||
|
| Requirement changed | `specs/<capability>/spec.md` |
|
||||||
|
| Design decision made | `design.md` |
|
||||||
|
| Scope changed | `proposal.md` |
|
||||||
|
| New work identified | `tasks.md` |
|
||||||
|
| Assumption invalidated | Relevant artifact |
|
||||||
|
|
||||||
|
Example offers:
|
||||||
|
- "That's a design decision. Capture it in design.md?"
|
||||||
|
- "This is a new requirement. Add it to specs?"
|
||||||
|
- "This changes scope. Update the proposal?"
|
||||||
|
|
||||||
|
4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What You Don't Have To Do
|
||||||
|
|
||||||
|
- Follow a script
|
||||||
|
- Ask the same questions every time
|
||||||
|
- Produce a specific artifact
|
||||||
|
- Reach a conclusion
|
||||||
|
- Stay on topic if a tangent is valuable
|
||||||
|
- Be brief (this is thinking time)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Handling Different Entry Points
|
||||||
|
|
||||||
|
**User brings a vague idea:**
|
||||||
|
```
|
||||||
|
User: I'm thinking about adding real-time collaboration
|
||||||
|
|
||||||
|
You: Real-time collab is a big space. Let me think about this...
|
||||||
|
|
||||||
|
COLLABORATION SPECTRUM
|
||||||
|
════════════════════════════════════════════
|
||||||
|
|
||||||
|
Awareness Coordination Sync
|
||||||
|
│ │ │
|
||||||
|
▼ ▼ ▼
|
||||||
|
┌────────┐ ┌────────┐ ┌────────┐
|
||||||
|
│Presence│ │Cursors │ │ CRDT │
|
||||||
|
│ "3 │ │ Multi │ │Conflict│
|
||||||
|
│online" │ │ select │ │ free │
|
||||||
|
└────────┘ └────────┘ └────────┘
|
||||||
|
│ │ │
|
||||||
|
trivial moderate complex
|
||||||
|
|
||||||
|
Where's your head at?
|
||||||
|
```
|
||||||
|
|
||||||
|
**User brings a specific problem:**
|
||||||
|
```
|
||||||
|
User: The auth system is a mess
|
||||||
|
|
||||||
|
You: [reads codebase]
|
||||||
|
|
||||||
|
┌─────────────────────────────────────────────┐
|
||||||
|
│ CURRENT AUTH FLOW │
|
||||||
|
└─────────────────────────────────────────────┘
|
||||||
|
│
|
||||||
|
┌─────────────┼─────────────┐
|
||||||
|
▼ ▼ ▼
|
||||||
|
┌─────────┐ ┌─────────┐ ┌─────────┐
|
||||||
|
│ Google │ │ GitHub │ │ Email │
|
||||||
|
│ OAuth │ │ OAuth │ │ Magic │
|
||||||
|
└────┬────┘ └────┬────┘ └────┬────┘
|
||||||
|
│ │ │
|
||||||
|
└─────────────┼─────────────┘
|
||||||
|
▼
|
||||||
|
┌───────────┐
|
||||||
|
│ Session │
|
||||||
|
└─────┬─────┘
|
||||||
|
│
|
||||||
|
▼
|
||||||
|
┌───────────┐
|
||||||
|
│ Perms │
|
||||||
|
└───────────┘
|
||||||
|
|
||||||
|
I see three tangles. Which one's burning?
|
||||||
|
```
|
||||||
|
|
||||||
|
**User is stuck mid-implementation:**
|
||||||
|
```
|
||||||
|
User: /opsx-explore add-auth-system
|
||||||
|
The OAuth integration is more complex than expected
|
||||||
|
|
||||||
|
You: [reads change artifacts]
|
||||||
|
|
||||||
|
You're on task 4: "Implement OAuth flow"
|
||||||
|
|
||||||
|
Let me trace what's involved...
|
||||||
|
|
||||||
|
[draws diagram, explores options, suggests paths]
|
||||||
|
|
||||||
|
Want to update the design to reflect this?
|
||||||
|
Or add a spike task to investigate?
|
||||||
|
```
|
||||||
|
|
||||||
|
**User wants to compare options:**
|
||||||
|
```
|
||||||
|
User: Should we use Postgres or SQLite?
|
||||||
|
|
||||||
|
You: Generic answer is boring. What's the context?
|
||||||
|
|
||||||
|
User: A CLI tool that tracks local dev environments
|
||||||
|
|
||||||
|
You: That changes everything.
|
||||||
|
|
||||||
|
┌─────────────────────────────────────────────────┐
|
||||||
|
│ CLI TOOL DATA STORAGE │
|
||||||
|
└─────────────────────────────────────────────────┘
|
||||||
|
|
||||||
|
Key constraints:
|
||||||
|
• No daemon running
|
||||||
|
• Must work offline
|
||||||
|
• Single user
|
||||||
|
|
||||||
|
SQLite Postgres
|
||||||
|
Deployment embedded ✓ needs server ✗
|
||||||
|
Offline yes ✓ no ✗
|
||||||
|
Single file yes ✓ no ✗
|
||||||
|
|
||||||
|
SQLite. Not even close.
|
||||||
|
|
||||||
|
Unless... is there a sync component?
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Ending Discovery
|
||||||
|
|
||||||
|
There's no required ending. Discovery might:
|
||||||
|
|
||||||
|
- **Flow into a proposal**: "Ready to start? I can create a change proposal."
|
||||||
|
- **Result in artifact updates**: "Updated design.md with these decisions"
|
||||||
|
- **Just provide clarity**: User has what they need, moves on
|
||||||
|
- **Continue later**: "We can pick this up anytime"
|
||||||
|
|
||||||
|
When it feels like things are crystallizing, you might summarize:
|
||||||
|
|
||||||
|
```
|
||||||
|
## What We Figured Out
|
||||||
|
|
||||||
|
**The problem**: [crystallized understanding]
|
||||||
|
|
||||||
|
**The approach**: [if one emerged]
|
||||||
|
|
||||||
|
**Open questions**: [if any remain]
|
||||||
|
|
||||||
|
**Next steps** (if ready):
|
||||||
|
- Create a change proposal
|
||||||
|
- Keep exploring: just keep talking
|
||||||
|
```
|
||||||
|
|
||||||
|
But this summary is optional. Sometimes the thinking IS the value.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Guardrails
|
||||||
|
|
||||||
|
- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
|
||||||
|
- **Don't fake understanding** - If something is unclear, dig deeper
|
||||||
|
- **Don't rush** - Discovery is thinking time, not task time
|
||||||
|
- **Don't force structure** - Let patterns emerge naturally
|
||||||
|
- **Don't auto-capture** - Offer to save insights, don't just do it
|
||||||
|
- **Do visualize** - A good diagram is worth many paragraphs
|
||||||
|
- **Do explore the codebase** - Ground discussions in reality
|
||||||
|
- **Do question assumptions** - Including the user's and your own
|
||||||
@@ -0,0 +1,110 @@
|
|||||||
|
---
|
||||||
|
name: openspec-propose
|
||||||
|
description: Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
|
||||||
|
license: MIT
|
||||||
|
compatibility: Requires openspec CLI.
|
||||||
|
metadata:
|
||||||
|
author: openspec
|
||||||
|
version: "1.0"
|
||||||
|
generatedBy: "1.2.0"
|
||||||
|
---
|
||||||
|
|
||||||
|
Propose a new change - create the change and generate all artifacts in one step.
|
||||||
|
|
||||||
|
I'll create a change with artifacts:
|
||||||
|
- proposal.md (what & why)
|
||||||
|
- design.md (how)
|
||||||
|
- tasks.md (implementation steps)
|
||||||
|
|
||||||
|
When ready to implement, run /opsx-apply
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
|
||||||
|
|
||||||
|
**Steps**
|
||||||
|
|
||||||
|
1. **If no clear input provided, ask what they want to build**
|
||||||
|
|
||||||
|
Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
|
||||||
|
> "What change do you want to work on? Describe what you want to build or fix."
|
||||||
|
|
||||||
|
From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
|
||||||
|
|
||||||
|
**IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
|
||||||
|
|
||||||
|
2. **Create the change directory**
|
||||||
|
```bash
|
||||||
|
openspec new change "<name>"
|
||||||
|
```
|
||||||
|
This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
|
||||||
|
|
||||||
|
3. **Get the artifact build order**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>" --json
|
||||||
|
```
|
||||||
|
Parse the JSON to get:
|
||||||
|
- `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
|
||||||
|
- `artifacts`: list of all artifacts with their status and dependencies
|
||||||
|
|
||||||
|
4. **Create artifacts in sequence until apply-ready**
|
||||||
|
|
||||||
|
Use the **TodoWrite tool** to track progress through the artifacts.
|
||||||
|
|
||||||
|
Loop through artifacts in dependency order (artifacts with no pending dependencies first):
|
||||||
|
|
||||||
|
a. **For each artifact that is `ready` (dependencies satisfied)**:
|
||||||
|
- Get instructions:
|
||||||
|
```bash
|
||||||
|
openspec instructions <artifact-id> --change "<name>" --json
|
||||||
|
```
|
||||||
|
- The instructions JSON includes:
|
||||||
|
- `context`: Project background (constraints for you - do NOT include in output)
|
||||||
|
- `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
|
||||||
|
- `template`: The structure to use for your output file
|
||||||
|
- `instruction`: Schema-specific guidance for this artifact type
|
||||||
|
- `outputPath`: Where to write the artifact
|
||||||
|
- `dependencies`: Completed artifacts to read for context
|
||||||
|
- Read any completed dependency files for context
|
||||||
|
- Create the artifact file using `template` as the structure
|
||||||
|
- Apply `context` and `rules` as constraints - but do NOT copy them into the file
|
||||||
|
- Show brief progress: "Created <artifact-id>"
|
||||||
|
|
||||||
|
b. **Continue until all `applyRequires` artifacts are complete**
|
||||||
|
- After creating each artifact, re-run `openspec status --change "<name>" --json`
|
||||||
|
- Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
|
||||||
|
- Stop when all `applyRequires` artifacts are done
|
||||||
|
|
||||||
|
c. **If an artifact requires user input** (unclear context):
|
||||||
|
- Use **AskUserQuestion tool** to clarify
|
||||||
|
- Then continue with creation
|
||||||
|
|
||||||
|
5. **Show final status**
|
||||||
|
```bash
|
||||||
|
openspec status --change "<name>"
|
||||||
|
```
|
||||||
|
|
||||||
|
**Output**
|
||||||
|
|
||||||
|
After completing all artifacts, summarize:
|
||||||
|
- Change name and location
|
||||||
|
- List of artifacts created with brief descriptions
|
||||||
|
- What's ready: "All artifacts created! Ready for implementation."
|
||||||
|
- Prompt: "Run `/opsx-apply` or ask me to implement to start working on the tasks."
|
||||||
|
|
||||||
|
**Artifact Creation Guidelines**
|
||||||
|
|
||||||
|
- Follow the `instruction` field from `openspec instructions` for each artifact type
|
||||||
|
- The schema defines what each artifact should contain - follow it
|
||||||
|
- Read dependency artifacts for context before creating new ones
|
||||||
|
- Use `template` as the structure for your output file - fill in its sections
|
||||||
|
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
|
||||||
|
- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
|
||||||
|
- These guide what you write, but should never appear in the output
|
||||||
|
|
||||||
|
**Guardrails**
|
||||||
|
- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
|
||||||
|
- Always read dependency artifacts before creating a new one
|
||||||
|
- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
|
||||||
|
- If a change with that name already exists, ask if user wants to continue it or create a new one
|
||||||
|
- Verify each artifact file exists after writing before proceeding to next
|
||||||
@@ -0,0 +1 @@
|
|||||||
|
3.13
|
||||||
@@ -0,0 +1,2 @@
|
|||||||
|
schema: spec-driven
|
||||||
|
created: 2026-03-30
|
||||||
@@ -0,0 +1,147 @@
|
|||||||
|
## Context
|
||||||
|
|
||||||
|
本项目是一个全新的 Python 项目（greenfield），目标是构建一个基于 LlamaIndex Workflow 的 Agent，能够动态加载和执行 SKILL。
|
||||||
|
|
||||||
|
**当前状态：**
|
||||||
|
- 项目仅有 `src/llama_agent_skills/__init__.py` 中一个空的 `main()` 入口
|
||||||
|
- 无任何现有依赖（`pyproject.toml` 的 `dependencies = []`）
|
||||||
|
- `.opencode/skills/` 和 `.github/skills/` 下有 4 个 SKILL.md 示例文件，定义了 SKILL 的标准格式
|
||||||
|
|
||||||
|
**SKILL 格式（已有约定）：**
|
||||||
|
- YAML frontmatter：`name`、`description`、`license`、`metadata`（author、version）
|
||||||
|
- Markdown 正文：自由格式的指令文本，包含 Steps、Guardrails、Input/Output 等段落
|
||||||
|
|
||||||
|
**LlamaIndex Workflow 关键能力（调研结论）：**
|
||||||
|
- `Workflow` 基类：事件驱动、`@step` 装饰器、`Context` 状态管理
|
||||||
|
- `AgentWorkflow.from_tools_or_functions()`：接受 `tools` 列表和 `system_prompt`
|
||||||
|
- `FunctionAgent`：支持 `system_prompt`、`tools`、`can_handoff_to`
|
||||||
|
- 工具列表存储为实例变量 `self.tools`，可运行时动态增删
|
||||||
|
- `Context.set/get` 提供步骤间状态共享
|
||||||
|
|
||||||
|
**约束：**
|
||||||
|
- 不引入 Shell/subprocess，纯 Python 运行
|
||||||
|
- 脚本类 SKILL 功能暂不支持
|
||||||
|
- 需要支持线上部署场景
|
||||||
|
|
||||||
|
## Goals / Non-Goals
|
||||||
|
|
||||||
|
**Goals:**
|
||||||
|
- 实现 SKILL.md 文件的解析器，能提取 frontmatter 元数据和正文指令
|
||||||
|
- 实现 SKILL 注册表，支持从目录扫描、运行时动态注册/注销
|
||||||
|
- 构建基于 LlamaIndex Workflow 的核心 Agent，将 SKILL 作为 system prompt 的扩展注入
|
||||||
|
- 提供清晰的 Python API，方便程序化创建和运行 Agent
|
||||||
|
- 保持架构简洁，为后续扩展（MCP 工具、多 Agent 协作）留出空间
|
||||||
|
|
||||||
|
**Non-Goals:**
|
||||||
|
- 不实现 Shell/subprocess 执行能力（安全约束）
|
||||||
|
- 不实现 SKILL 内定义的脚本/命令执行功能
|
||||||
|
- 不实现多 Agent 协作/handoff（后续迭代）
|
||||||
|
- 不实现 SKILL 的远程加载（仅支持本地文件系统）
|
||||||
|
- 不实现 Web UI 或 REST API 层
|
||||||
|
- 不实现 MCP server/client 集成（后续迭代）
|
||||||
|
|
||||||
|
## Decisions
|
||||||
|
|
||||||
|
### D1: SKILL 注入方式 — System Prompt 拼接
|
||||||
|
|
||||||
|
**决定：** 将 SKILL 的 Markdown 正文作为 system prompt 的一部分注入 Agent。
|
||||||
|
|
||||||
|
**备选方案：**
|
||||||
|
- A) 将 SKILL 转换为 LlamaIndex `BaseTool`（每个 SKILL 变成一个可调用工具）
|
||||||
|
- B) 将 SKILL 注入 system prompt（当前选择）
|
||||||
|
- C) 将 SKILL 作为 RAG 文档，通过检索注入
|
||||||
|
|
||||||
|
**选择 B 的理由：**
|
||||||
|
- SKILL 本质是「行为指令」而非「可调用函数」，它定义了 Agent 应该如何行动，而不是提供一个新的能力入口
|
||||||
|
- System prompt 注入最自然，与 LlamaIndex 的 `system_prompt` 参数直接对应
|
||||||
|
- 方案 A 需要为每个 SKILL 包装一个工具入口，增加不必要的间接层
|
||||||
|
- 方案 C 引入 RAG 复杂度，对于有限数量的 SKILL 是过度设计
|
||||||
|
- 后续如果 SKILL 需要携带工具定义，可以在 SKILL 格式中扩展 `tools` 字段，注册为真正的工具
|
||||||
|
|
||||||
|
### D2: SKILL.md 解析策略 — python-frontmatter 库
|
||||||
|
|
||||||
|
**决定：** 使用 `python-frontmatter` 库解析 SKILL.md 的 YAML frontmatter + Markdown body。
|
||||||
|
|
||||||
|
**备选方案：**
|
||||||
|
- A) 手写 YAML + Markdown 分割解析器
|
||||||
|
- B) 使用 `python-frontmatter` 库（当前选择）
|
||||||
|
- C) 使用 `pyyaml` + 手动分割 `---` 分隔符
|
||||||
|
|
||||||
|
**选择 B 的理由：**
|
||||||
|
- `python-frontmatter` 是成熟的库，专门处理 frontmatter 格式，边界情况覆盖好
|
||||||
|
- 减少自研代码量和 bug 风险
|
||||||
|
- 自动处理 YAML 类型转换
|
||||||
|
|
||||||
|
### D3: Agent 架构 — 基于 AgentWorkflow 的单 Agent
|
||||||
|
|
||||||
|
**决定：** 使用 `AgentWorkflow.from_tools_or_functions()` 构建单 Agent，通过 `system_prompt` 参数注入 SKILL 上下文。
|
||||||
|
|
||||||
|
**备选方案：**
|
||||||
|
- A) 自定义 `Workflow` 子类，手动实现所有步骤
|
||||||
|
- B) 使用 `AgentWorkflow.from_tools_or_functions()`（当前选择）
|
||||||
|
- C) 使用 `FunctionAgent` + 多 Agent 编排
|
||||||
|
|
||||||
|
**选择 B 的理由：**
|
||||||
|
- `AgentWorkflow` 提供开箱即用的对话循环、工具调用、流式输出
|
||||||
|
- 对于第一版，单 Agent 足够验证 SKILL 注入概念
|
||||||
|
- 如需自定义步骤（如 SKILL 热加载），可以后续继承扩展
|
||||||
|
- 方案 A 需要重写大量 LlamaIndex 已有逻辑
|
||||||
|
- 方案 C 在当前阶段是过度设计
|
||||||
|
|
||||||
|
### D4: 模块结构 — 职责分离
|
||||||
|
|
||||||
|
**决定：** 按职责划分为以下模块：
|
||||||
|
|
||||||
|
```
|
||||||
|
src/llama_agent_skills/
|
||||||
|
├── __init__.py # 包入口 + main()
|
||||||
|
├── skill.py # Skill 数据模型 + SKILL.md 解析器
|
||||||
|
├── registry.py # SkillRegistry（扫描、注册、查询）
|
||||||
|
├── agent.py # Agent 构建与运行（封装 AgentWorkflow）
|
||||||
|
└── config.py # 配置管理（环境变量、默认值）
|
||||||
|
```
|
||||||
|
|
||||||
|
**理由：**
|
||||||
|
- `skill.py` 专注数据解析，与 LlamaIndex 无关，可独立测试
|
||||||
|
- `registry.py` 管理 SKILL 生命周期，依赖 `skill.py` 但不依赖 `agent.py`
|
||||||
|
- `agent.py` 是唯一依赖 LlamaIndex 的模块，负责将 registry 中的 SKILL 组装为 Agent
|
||||||
|
- `config.py` 集中管理配置，避免硬编码散落
|
||||||
|
|
||||||
|
### D5: SKILL 上下文组装策略
|
||||||
|
|
||||||
|
**决定：** 在 Agent 启动时，将所有已注册 SKILL 的正文按固定格式拼接到 system prompt：
|
||||||
|
|
||||||
|
```
|
||||||
|
{base_system_prompt}
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Active Skills
|
||||||
|
|
||||||
|
### Skill: {skill.name}
|
||||||
|
{skill.description}
|
||||||
|
|
||||||
|
{skill.body}
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Skill: {skill2.name}
|
||||||
|
...
|
||||||
|
```
|
||||||
|
|
||||||
|
**理由：**
|
||||||
|
- 结构化的分隔让 LLM 清楚区分不同 SKILL 的指令
|
||||||
|
- 每个 SKILL 带有名称和描述作为标题，便于 LLM 理解上下文切换
|
||||||
|
- 用 `---` 分隔避免 SKILL 间指令混淆
|
||||||
|
|
||||||
|
## Risks / Trade-offs
|
||||||
|
|
||||||
|
- **[System prompt 长度爆炸]** → 当加载多个大型 SKILL 时，system prompt 可能超出 LLM context window。**缓解：** 限制同时加载的 SKILL 数量，后续可引入选择性加载或摘要机制。
|
||||||
|
|
||||||
|
- **[SKILL 间指令冲突]** → 多个 SKILL 可能包含矛盾指令。**缓解：** 第一版不解决，通过文档约定 SKILL 应自包含；后续可增加冲突检测。
|
||||||
|
|
||||||
|
- **[LlamaIndex 版本锁定]** → 依赖 `llama-index-core` 的特定 API（如 `AgentWorkflow`），升级可能 break。**缓解：** 通过 `agent.py` 隔离 LlamaIndex 依赖，仅在该模块中引用 LlamaIndex API。
|
||||||
|
|
||||||
|
- **[无 Shell 限制降低灵活性]** → 部分 SKILL 可能期望执行 CLI 命令（如 `openspec` CLI）。**缓解：** 明确标记为 Non-Goal，后续可通过安全沙箱或 API wrapper 支持。
|
||||||
|
|
||||||
|
- **[SKILL.md 格式无 schema 校验]** → frontmatter 字段错误不会被提前发现。**缓解：** 在 `skill.py` 中做基本校验（必填字段检查），后续可引入 JSON Schema 或 Pydantic 校验。
|
||||||
@@ -0,0 +1,31 @@
|
|||||||
|
## Why
|
||||||
|
|
||||||
|
本项目需要构建一个基于 LlamaIndex Workflow 的 Agent，使其能够动态加载和执行 SKILL（以 SKILL.md 文件定义的结构化指令集）。SKILL 是一种将领域知识、工作流程和约束规则打包为可复用模块的机制，当前项目仅有空壳入口，需要从零实现 Agent 核心和 SKILL 注入能力。为了方便线上部署，设计上避免引入 Shell/子进程调用，脚本类功能暂不支持。
|
||||||
|
|
||||||
|
## What Changes
|
||||||
|
|
||||||
|
- 引入 LlamaIndex Workflow 作为 Agent 运行时框架（新依赖：`llama-index-core`、`llama-index-llms-openai` 等）
|
||||||
|
- 实现 SKILL 加载器：解析 SKILL.md 文件的 YAML frontmatter（name、description、metadata）和 Markdown 正文（instructions、steps、guardrails）
|
||||||
|
- 实现 SKILL 注入机制：将 SKILL 内容动态注入 Agent 的 system prompt，作为行为指令扩展
|
||||||
|
- 构建核心 Agent Workflow：包含 LLM 对话、工具调用、SKILL 上下文管理等步骤
|
||||||
|
- 提供 SKILL 目录扫描与注册 API，支持运行时动态加载/卸载 SKILL
|
||||||
|
- 暂不支持 Shell/脚本执行类工具，保证纯 Python 运行环境安全
|
||||||
|
|
||||||
|
## Capabilities
|
||||||
|
|
||||||
|
### New Capabilities
|
||||||
|
- `skill-loader`: SKILL.md 文件的解析、验证与加载，支持 YAML frontmatter + Markdown body 的标准格式
|
||||||
|
- `agent-workflow`: 基于 LlamaIndex Workflow 的核心 Agent 实现，包含对话管理、工具调用、SKILL 上下文注入
|
||||||
|
- `skill-registry`: SKILL 的注册、发现与生命周期管理，支持运行时动态增删
|
||||||
|
|
||||||
|
### Modified Capabilities
|
||||||
|
|
||||||
|
_无现有 capability 需要修改。_
|
||||||
|
|
||||||
|
## Impact
|
||||||
|
|
||||||
|
- **代码**: 在 `src/llama_agent_skills/` 下新增多个模块（skill loader、agent workflow、skill registry）
|
||||||
|
- **依赖**: 新增 `llama-index-core`、`llama-index-llms-openai`（或其他 LLM provider）、`pyyaml`（用于解析 frontmatter）
|
||||||
|
- **入口**: 改造 `__init__.py` 的 `main()` 函数，提供 Agent 启动入口
|
||||||
|
- **配置**: 可能新增配置文件或环境变量支持（LLM API key、SKILL 目录路径等）
|
||||||
|
- **限制**: 不引入 `subprocess`、`os.system` 等 Shell 调用，确保线上安全运行
|
||||||
@@ -0,0 +1,45 @@
|
|||||||
|
## ADDED Requirements
|
||||||
|
|
||||||
|
### Requirement: Agent 构建与 SKILL 注入
|
||||||
|
系统 SHALL 提供一个 Agent 构建函数/类，接受 SKILL 列表和 LLM 配置，创建一个集成了 SKILL 上下文的 LlamaIndex AgentWorkflow。
|
||||||
|
|
||||||
|
#### Scenario: 使用 SKILL 列表创建 Agent
|
||||||
|
- **WHEN** 调用 Agent 构建函数，传入一个包含 2 个 Skill 实例的列表和 LLM 配置
|
||||||
|
- **THEN** 创建的 AgentWorkflow 的 system prompt 中包含这 2 个 Skill 的 `name`、`description` 和 `body` 内容
|
||||||
|
|
||||||
|
#### Scenario: 无 SKILL 创建 Agent
|
||||||
|
- **WHEN** 调用 Agent 构建函数，传入空的 SKILL 列表
|
||||||
|
- **THEN** 创建的 AgentWorkflow 仅包含基础 system prompt，不含任何 SKILL 上下文
|
||||||
|
|
||||||
|
### Requirement: System Prompt 组装
|
||||||
|
系统 SHALL 按照固定格式将多个 SKILL 的内容组装到 system prompt 中，每个 SKILL 之间用分隔符隔开。
|
||||||
|
|
||||||
|
#### Scenario: 多 SKILL 的 prompt 格式
|
||||||
|
- **WHEN** 注入 2 个名为 "skill-a" 和 "skill-b" 的 SKILL
|
||||||
|
- **THEN** 生成的 system prompt 依次包含基础 prompt、"## Active Skills" 标题、每个 SKILL 的 "### Skill: {name}" 标题及其 body 内容，SKILL 之间用 `---` 分隔
|
||||||
|
|
||||||
|
#### Scenario: SKILL 顺序保持一致
|
||||||
|
- **WHEN** 按 ["skill-b", "skill-a"] 顺序注入 SKILL
|
||||||
|
- **THEN** system prompt 中 skill-b 的内容出现在 skill-a 之前
|
||||||
|
|
||||||
|
### Requirement: Agent 对话执行
|
||||||
|
系统 SHALL 提供运行 Agent 的能力，接受用户输入并返回 LLM 响应。
|
||||||
|
|
||||||
|
#### Scenario: 单轮对话
|
||||||
|
- **WHEN** 向 Agent 发送一条用户消息
|
||||||
|
- **THEN** Agent 调用 LLM 并返回文本响应
|
||||||
|
|
||||||
|
#### Scenario: 带工具的对话
|
||||||
|
- **WHEN** Agent 配置了工具函数，且用户消息触发了工具调用
|
||||||
|
- **THEN** Agent 执行工具调用并将结果整合到最终响应中
|
||||||
|
|
||||||
|
### Requirement: 工具注册
|
||||||
|
系统 SHALL 支持在创建 Agent 时注册 Python 可调用函数作为工具。
|
||||||
|
|
||||||
|
#### Scenario: 注册 Python 函数为工具
|
||||||
|
- **WHEN** 传入一个带 docstring 的 Python 函数到 Agent 构建函数的 `tools` 参数
|
||||||
|
- **THEN** 该函数被注册为 LlamaIndex 工具，Agent 可在对话中调用它
|
||||||
|
|
||||||
|
#### Scenario: 无工具的 Agent
|
||||||
|
- **WHEN** 创建 Agent 时不传入任何工具
|
||||||
|
- **THEN** Agent 正常运行，仅进行对话，不进行工具调用
|
||||||
@@ -0,0 +1,38 @@
|
|||||||
|
## ADDED Requirements
|
||||||
|
|
||||||
|
### Requirement: SKILL.md 文件解析
|
||||||
|
系统 SHALL 能够解析符合标准格式的 SKILL.md 文件，提取 YAML frontmatter 中的元数据和 Markdown 正文中的指令内容。
|
||||||
|
|
||||||
|
#### Scenario: 解析标准 SKILL.md 文件
|
||||||
|
- **WHEN** 提供一个包含 YAML frontmatter（`---` 分隔）和 Markdown 正文的 SKILL.md 文件路径
|
||||||
|
- **THEN** 系统返回一个 Skill 对象，包含 `name`（str）、`description`（str）、`metadata`（dict）和 `body`（str）字段
|
||||||
|
|
||||||
|
#### Scenario: 解析缺少必填字段的 SKILL.md
|
||||||
|
- **WHEN** 提供的 SKILL.md 文件的 frontmatter 中缺少 `name` 字段
|
||||||
|
- **THEN** 系统抛出 `SkillLoadError` 异常，包含明确的错误描述
|
||||||
|
|
||||||
|
#### Scenario: 解析无 frontmatter 的文件
|
||||||
|
- **WHEN** 提供的文件不包含 YAML frontmatter（无 `---` 分隔符）
|
||||||
|
- **THEN** 系统抛出 `SkillLoadError` 异常，提示文件格式不合法
|
||||||
|
|
||||||
|
### Requirement: Skill 数据模型
|
||||||
|
系统 SHALL 提供一个 `Skill` 数据类（dataclass 或 Pydantic model），用于表示解析后的 SKILL 实例。
|
||||||
|
|
||||||
|
#### Scenario: Skill 数据模型包含所有必要字段
|
||||||
|
- **WHEN** 创建一个 Skill 实例
|
||||||
|
- **THEN** 该实例 MUST 包含以下字段：`name`（str，必填）、`description`（str，必填）、`body`（str，必填）、`metadata`（dict，可选，默认空 dict）、`source_path`（Path | None，可选）
|
||||||
|
|
||||||
|
#### Scenario: Skill 实例不可变
|
||||||
|
- **WHEN** 尝试修改已创建的 Skill 实例的 `name` 字段
|
||||||
|
- **THEN** 系统抛出异常（frozen dataclass / immutable model）
|
||||||
|
|
||||||
|
### Requirement: Frontmatter 元数据提取
|
||||||
|
系统 SHALL 从 YAML frontmatter 中提取以下标准字段：`name`、`description`、`license`、`compatibility`、`metadata`（包含 `author`、`version`、`generatedBy`）。
|
||||||
|
|
||||||
|
#### Scenario: 提取完整的 metadata
|
||||||
|
- **WHEN** SKILL.md 的 frontmatter 包含 `metadata: { author: "test", version: "1.0" }`
|
||||||
|
- **THEN** 解析结果的 `metadata` 字段为 `{"author": "test", "version": "1.0"}`
|
||||||
|
|
||||||
|
#### Scenario: metadata 缺失时使用默认值
|
||||||
|
- **WHEN** SKILL.md 的 frontmatter 不包含 `metadata` 字段
|
||||||
|
- **THEN** 解析结果的 `metadata` 字段为空 dict `{}`
|
||||||
@@ -0,0 +1,57 @@
|
|||||||
|
## ADDED Requirements
|
||||||
|
|
||||||
|
### Requirement: SKILL 目录扫描
|
||||||
|
系统 SHALL 能够扫描指定目录，自动发现并加载所有 SKILL.md 文件。
|
||||||
|
|
||||||
|
#### Scenario: 扫描包含多个 SKILL 的目录
|
||||||
|
- **WHEN** 指定一个包含 3 个子目录、每个子目录有一个 SKILL.md 文件的目录路径
|
||||||
|
- **THEN** 系统返回 3 个 Skill 实例的列表
|
||||||
|
|
||||||
|
#### Scenario: 扫描空目录
|
||||||
|
- **WHEN** 指定一个不包含任何 SKILL.md 文件的目录路径
|
||||||
|
- **THEN** 系统返回空列表，不抛出异常
|
||||||
|
|
||||||
|
#### Scenario: 扫描不存在的目录
|
||||||
|
- **WHEN** 指定一个不存在的目录路径
|
||||||
|
- **THEN** 系统抛出 `FileNotFoundError` 异常
|
||||||
|
|
||||||
|
#### Scenario: 跳过无效的 SKILL 文件
|
||||||
|
- **WHEN** 目录中包含 2 个有效 SKILL.md 和 1 个格式错误的 SKILL.md
|
||||||
|
- **THEN** 系统返回 2 个有效 Skill 实例，并通过日志记录无效文件的错误信息
|
||||||
|
|
||||||
|
### Requirement: SKILL 注册表
|
||||||
|
系统 SHALL 提供一个 SkillRegistry 类，用于管理已注册的 SKILL 实例。
|
||||||
|
|
||||||
|
#### Scenario: 注册 SKILL
|
||||||
|
- **WHEN** 调用 `registry.register(skill)` 注册一个 Skill 实例
|
||||||
|
- **THEN** 该 Skill 被存储在注册表中，可通过 `registry.get(skill.name)` 获取
|
||||||
|
|
||||||
|
#### Scenario: 注册同名 SKILL 覆盖
|
||||||
|
- **WHEN** 先后注册两个 `name` 相同但 `body` 不同的 Skill
|
||||||
|
- **THEN** 注册表中保留后注册的 Skill，前一个被覆盖
|
||||||
|
|
||||||
|
#### Scenario: 注销 SKILL
|
||||||
|
- **WHEN** 调用 `registry.unregister("skill-name")`
|
||||||
|
- **THEN** 该 SKILL 从注册表中移除，`registry.get("skill-name")` 返回 None
|
||||||
|
|
||||||
|
#### Scenario: 注销不存在的 SKILL
|
||||||
|
- **WHEN** 调用 `registry.unregister("nonexistent")`
|
||||||
|
- **THEN** 不抛出异常，静默忽略
|
||||||
|
|
||||||
|
### Requirement: 列出所有已注册 SKILL
|
||||||
|
系统 SHALL 提供查询所有已注册 SKILL 的能力。
|
||||||
|
|
||||||
|
#### Scenario: 列出所有 SKILL
|
||||||
|
- **WHEN** 注册了 3 个 SKILL 后调用 `registry.list_skills()`
|
||||||
|
- **THEN** 返回包含 3 个 Skill 实例的列表
|
||||||
|
|
||||||
|
#### Scenario: 空注册表列出 SKILL
|
||||||
|
- **WHEN** 未注册任何 SKILL 时调用 `registry.list_skills()`
|
||||||
|
- **THEN** 返回空列表
|
||||||
|
|
||||||
|
### Requirement: 从目录批量加载到注册表
|
||||||
|
系统 SHALL 提供一个便捷方法，将目录扫描和注册合并为一步操作。
|
||||||
|
|
||||||
|
#### Scenario: 从目录加载所有 SKILL
|
||||||
|
- **WHEN** 调用 `registry.load_from_directory(path)` 传入包含 3 个有效 SKILL.md 的目录
|
||||||
|
- **THEN** 注册表中包含 3 个 SKILL，可通过 `registry.list_skills()` 获取
|
||||||
@@ -0,0 +1,36 @@
|
|||||||
|
## 1. 项目基础设施
|
||||||
|
|
||||||
|
- [x] 1.1 在 `pyproject.toml` 中添加依赖：`llama-index-core`、`llama-index-llms-openai`、`python-frontmatter`
|
||||||
|
- [x] 1.2 创建模块文件结构：`src/llama_agent_skills/skill.py`、`registry.py`、`agent.py`、`config.py`
|
||||||
|
- [x] 1.3 在 `config.py` 中实现配置管理：LLM API key（环境变量）、默认 SKILL 目录路径、基础 system prompt
|
||||||
|
|
||||||
|
## 2. Skill 数据模型与解析器（skill.py）
|
||||||
|
|
||||||
|
- [x] 2.1 实现 `Skill` 数据类（frozen dataclass），包含字段：`name`、`description`、`body`、`metadata`、`source_path`
|
||||||
|
- [x] 2.2 实现 `SkillLoadError` 自定义异常类
|
||||||
|
- [x] 2.3 实现 `load_skill(path: Path) -> Skill` 函数：使用 `python-frontmatter` 解析 SKILL.md，校验必填字段（name、description），提取 metadata 并构造 Skill 实例
|
||||||
|
- [x] 2.4 处理解析错误场景：缺少 frontmatter、缺少必填字段、文件不存在，均抛出 `SkillLoadError`
|
||||||
|
|
||||||
|
## 3. SKILL 注册表（registry.py）
|
||||||
|
|
||||||
|
- [x] 3.1 实现 `SkillRegistry` 类，包含 `register(skill)`、`unregister(name)`、`get(name)`、`list_skills()` 方法
|
||||||
|
- [x] 3.2 实现 `scan_directory(path: Path) -> list[Skill]` 函数：遍历目录下所有 `*/SKILL.md` 文件，调用 `load_skill` 解析，跳过无效文件并记录日志
|
||||||
|
- [x] 3.3 实现 `SkillRegistry.load_from_directory(path)` 便捷方法：调用 `scan_directory` 并批量注册
|
||||||
|
|
||||||
|
## 4. Agent 核心（agent.py）
|
||||||
|
|
||||||
|
- [x] 4.1 实现 `build_system_prompt(base_prompt: str, skills: list[Skill]) -> str` 函数：按设计文档中的格式将 SKILL 内容拼接到 system prompt
|
||||||
|
- [x] 4.2 实现 `create_agent(skills, tools, llm_config) -> AgentWorkflow` 函数：使用 `AgentWorkflow.from_tools_or_functions()` 创建 Agent，传入组装后的 system prompt 和工具列表
|
||||||
|
- [x] 4.3 实现 `run_agent(agent, message) -> str` 异步函数：接受用户输入，运行 Agent 并返回响应文本
|
||||||
|
|
||||||
|
## 5. 入口整合（__init__.py）
|
||||||
|
|
||||||
|
- [x] 5.1 改造 `main()` 函数：从配置读取 SKILL 目录，创建 SkillRegistry 并加载 SKILL，构建 Agent，进入交互式对话循环
|
||||||
|
- [x] 5.2 支持命令行参数或环境变量指定 SKILL 目录路径和 LLM 模型名称
|
||||||
|
|
||||||
|
## 6. 验证与测试
|
||||||
|
|
||||||
|
- [x] 6.1 使用项目中现有的 `.opencode/skills/` 目录下的 SKILL.md 文件作为测试数据，验证 skill loader 能正确解析所有 4 个 SKILL
|
||||||
|
- [x] 6.2 验证 SkillRegistry 的注册、注销、列表功能
|
||||||
|
- [x] 6.3 验证 Agent 创建后的 system prompt 包含所有已加载 SKILL 的内容
|
||||||
|
- [x] 6.4 端到端测试：加载 SKILL → 创建 Agent → 发送消息 → 获取响应
|
||||||
@@ -0,0 +1,20 @@
|
|||||||
|
schema: spec-driven
|
||||||
|
|
||||||
|
# Project context (optional)
|
||||||
|
# This is shown to AI when creating artifacts.
|
||||||
|
# Add your tech stack, conventions, style guides, domain knowledge, etc.
|
||||||
|
# Example:
|
||||||
|
# context: |
|
||||||
|
# Tech stack: TypeScript, React, Node.js
|
||||||
|
# We use conventional commits
|
||||||
|
# Domain: e-commerce platform
|
||||||
|
|
||||||
|
# Per-artifact rules (optional)
|
||||||
|
# Add custom rules for specific artifacts.
|
||||||
|
# Example:
|
||||||
|
# rules:
|
||||||
|
# proposal:
|
||||||
|
# - Keep proposals under 500 words
|
||||||
|
# - Always include a "Non-goals" section
|
||||||
|
# tasks:
|
||||||
|
# - Break tasks into chunks of max 2 hours
|
||||||
@@ -0,0 +1,21 @@
|
|||||||
|
[project]
|
||||||
|
name = "llama-agent-skills"
|
||||||
|
version = "0.1.0"
|
||||||
|
description = "Add your description here"
|
||||||
|
readme = "README.md"
|
||||||
|
authors = [
|
||||||
|
{ name = "Summer Shen", email = "3244742300@qq.com" }
|
||||||
|
]
|
||||||
|
requires-python = ">=3.11"
|
||||||
|
dependencies = [
|
||||||
|
"llama-index-core>=0.12.0",
|
||||||
|
"llama-index-llms-openai>=0.3.0",
|
||||||
|
"python-frontmatter>=1.1.0",
|
||||||
|
]
|
||||||
|
|
||||||
|
[project.scripts]
|
||||||
|
llama-agent-skills = "llama_agent_skills:main"
|
||||||
|
|
||||||
|
[build-system]
|
||||||
|
requires = ["uv_build>=0.9.22,<0.10.0"]
|
||||||
|
build-backend = "uv_build"
|
||||||
@@ -0,0 +1,77 @@
|
|||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import asyncio
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
from llama_agent_skills.agent import create_agent, run_agent
|
||||||
|
from llama_agent_skills.config import Config
|
||||||
|
from llama_agent_skills.registry import SkillRegistry
|
||||||
|
|
||||||
|
|
||||||
|
def _parse_args() -> argparse.Namespace:
|
||||||
|
parser = argparse.ArgumentParser(description="LlamaIndex Agent with SKILL support")
|
||||||
|
parser.add_argument(
|
||||||
|
"--skill-dir",
|
||||||
|
type=Path,
|
||||||
|
action="append",
|
||||||
|
default=None,
|
||||||
|
help="Path to a skill directory (can be specified multiple times)",
|
||||||
|
)
|
||||||
|
parser.add_argument("--model", type=str, default=None, help="LLM model name")
|
||||||
|
return parser.parse_args()
|
||||||
|
|
||||||
|
|
||||||
|
async def _run_interactive(config: Config, registry: SkillRegistry) -> None:
|
||||||
|
skills = registry.list_skills()
|
||||||
|
agent = create_agent(
|
||||||
|
skills=skills,
|
||||||
|
model=config.llm_model,
|
||||||
|
api_key=config.llm_api_key,
|
||||||
|
base_system_prompt=config.base_system_prompt,
|
||||||
|
)
|
||||||
|
|
||||||
|
loaded_names = [s.name for s in skills]
|
||||||
|
print(f"Agent ready. Loaded {len(skills)} skill(s): {loaded_names}")
|
||||||
|
print("Type 'quit' or 'exit' to stop.\n")
|
||||||
|
|
||||||
|
while True:
|
||||||
|
try:
|
||||||
|
user_input = input("You: ").strip()
|
||||||
|
except (EOFError, KeyboardInterrupt):
|
||||||
|
print("\nBye!")
|
||||||
|
break
|
||||||
|
|
||||||
|
if not user_input:
|
||||||
|
continue
|
||||||
|
if user_input.lower() in ("quit", "exit"):
|
||||||
|
print("Bye!")
|
||||||
|
break
|
||||||
|
|
||||||
|
response = await run_agent(agent, user_input)
|
||||||
|
print(f"Agent: {response}\n")
|
||||||
|
|
||||||
|
|
||||||
|
def main() -> None:
|
||||||
|
args = _parse_args()
|
||||||
|
config = Config.from_env()
|
||||||
|
|
||||||
|
if args.model:
|
||||||
|
config = Config(
|
||||||
|
llm_api_key=config.llm_api_key,
|
||||||
|
llm_model=args.model,
|
||||||
|
skill_directories=config.skill_directories,
|
||||||
|
base_system_prompt=config.base_system_prompt,
|
||||||
|
)
|
||||||
|
|
||||||
|
registry = SkillRegistry()
|
||||||
|
|
||||||
|
skill_dirs = args.skill_dir or config.skill_directories
|
||||||
|
for skill_dir in skill_dirs:
|
||||||
|
if skill_dir.is_dir():
|
||||||
|
registry.load_from_directory(skill_dir)
|
||||||
|
else:
|
||||||
|
print(f"Warning: skill directory not found: {skill_dir}", file=sys.stderr)
|
||||||
|
|
||||||
|
asyncio.run(_run_interactive(config, registry))
|
||||||
@@ -0,0 +1,48 @@
|
|||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from typing import Any, Callable
|
||||||
|
|
||||||
|
from llama_index.core.agent.workflow import AgentWorkflow
|
||||||
|
from llama_index.llms.openai import OpenAI
|
||||||
|
|
||||||
|
from llama_agent_skills.skill import Skill
|
||||||
|
|
||||||
|
|
||||||
|
def build_system_prompt(base_prompt: str, skills: list[Skill]) -> str:
|
||||||
|
if not skills:
|
||||||
|
return base_prompt
|
||||||
|
|
||||||
|
parts = [base_prompt, "\n\n---\n\n## Active Skills\n"]
|
||||||
|
for i, skill in enumerate(skills):
|
||||||
|
if i > 0:
|
||||||
|
parts.append("\n---\n")
|
||||||
|
parts.append(
|
||||||
|
f"\n### Skill: {skill.name}\n{skill.description}\n\n{skill.body}\n"
|
||||||
|
)
|
||||||
|
|
||||||
|
return "".join(parts)
|
||||||
|
|
||||||
|
|
||||||
|
def create_agent(
|
||||||
|
skills: list[Skill] | None = None,
|
||||||
|
tools: list[Callable[..., Any]] | None = None,
|
||||||
|
model: str = "gpt-4o-mini",
|
||||||
|
api_key: str | None = None,
|
||||||
|
base_system_prompt: str = "You are a helpful assistant.",
|
||||||
|
) -> AgentWorkflow:
|
||||||
|
system_prompt = build_system_prompt(base_system_prompt, skills or [])
|
||||||
|
|
||||||
|
llm_kwargs: dict[str, Any] = {"model": model}
|
||||||
|
if api_key:
|
||||||
|
llm_kwargs["api_key"] = api_key
|
||||||
|
|
||||||
|
return AgentWorkflow.from_tools_or_functions(
|
||||||
|
tools_or_functions=tools or [],
|
||||||
|
llm=OpenAI(**llm_kwargs),
|
||||||
|
system_prompt=system_prompt,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
async def run_agent(agent: AgentWorkflow, message: str) -> str:
|
||||||
|
response = await agent.run(user_msg=message)
|
||||||
|
return str(response)
|
||||||
@@ -0,0 +1,34 @@
|
|||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import os
|
||||||
|
from dataclasses import dataclass, field
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class Config:
|
||||||
|
llm_api_key: str = ""
|
||||||
|
llm_model: str = "gpt-4o-mini"
|
||||||
|
skill_directories: list[Path] = field(default_factory=list)
|
||||||
|
base_system_prompt: str = "You are a helpful assistant."
|
||||||
|
|
||||||
|
@classmethod
|
||||||
|
def from_env(cls) -> Config:
|
||||||
|
"""Create Config from environment variables.
|
||||||
|
|
||||||
|
OPENAI_API_KEY, LLM_MODEL, SKILL_DIRECTORIES (comma-separated paths),
|
||||||
|
BASE_SYSTEM_PROMPT.
|
||||||
|
"""
|
||||||
|
skill_dirs_raw = os.environ.get("SKILL_DIRECTORIES", "")
|
||||||
|
skill_directories = [
|
||||||
|
Path(d.strip()) for d in skill_dirs_raw.split(",") if d.strip()
|
||||||
|
]
|
||||||
|
|
||||||
|
return cls(
|
||||||
|
llm_api_key=os.environ.get("OPENAI_API_KEY", ""),
|
||||||
|
llm_model=os.environ.get("LLM_MODEL", "gpt-4o-mini"),
|
||||||
|
skill_directories=skill_directories,
|
||||||
|
base_system_prompt=os.environ.get(
|
||||||
|
"BASE_SYSTEM_PROMPT", "You are a helpful assistant."
|
||||||
|
),
|
||||||
|
)
|
||||||
@@ -0,0 +1,44 @@
|
|||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import logging
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
from llama_agent_skills.skill import Skill, SkillLoadError, load_skill
|
||||||
|
|
||||||
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
|
||||||
|
def scan_directory(path: Path) -> list[Skill]:
|
||||||
|
path = Path(path)
|
||||||
|
if not path.is_dir():
|
||||||
|
raise FileNotFoundError(f"Skill directory not found: {path}")
|
||||||
|
|
||||||
|
skills: list[Skill] = []
|
||||||
|
for skill_file in sorted(path.glob("*/SKILL.md")):
|
||||||
|
try:
|
||||||
|
skills.append(load_skill(skill_file))
|
||||||
|
except SkillLoadError:
|
||||||
|
logger.warning("Skipping invalid skill file: %s", skill_file, exc_info=True)
|
||||||
|
|
||||||
|
return skills
|
||||||
|
|
||||||
|
|
||||||
|
class SkillRegistry:
|
||||||
|
def __init__(self) -> None:
|
||||||
|
self._skills: dict[str, Skill] = {}
|
||||||
|
|
||||||
|
def register(self, skill: Skill) -> None:
|
||||||
|
self._skills[skill.name] = skill
|
||||||
|
|
||||||
|
def unregister(self, name: str) -> None:
|
||||||
|
self._skills.pop(name, None)
|
||||||
|
|
||||||
|
def get(self, name: str) -> Skill | None:
|
||||||
|
return self._skills.get(name)
|
||||||
|
|
||||||
|
def list_skills(self) -> list[Skill]:
|
||||||
|
return list(self._skills.values())
|
||||||
|
|
||||||
|
def load_from_directory(self, path: Path) -> None:
|
||||||
|
for skill in scan_directory(path):
|
||||||
|
self.register(skill)
|
||||||
@@ -0,0 +1,52 @@
|
|||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from dataclasses import dataclass, field
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
import frontmatter
|
||||||
|
|
||||||
|
|
||||||
|
class SkillLoadError(Exception):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
_REQUIRED_FIELDS = ("name", "description")
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class Skill:
|
||||||
|
name: str
|
||||||
|
description: str
|
||||||
|
body: str
|
||||||
|
metadata: dict = field(default_factory=dict)
|
||||||
|
source_path: Path | None = None
|
||||||
|
|
||||||
|
|
||||||
|
def load_skill(path: Path) -> Skill:
|
||||||
|
path = Path(path)
|
||||||
|
if not path.is_file():
|
||||||
|
raise SkillLoadError(f"Skill file not found: {path}")
|
||||||
|
|
||||||
|
try:
|
||||||
|
post = frontmatter.load(str(path))
|
||||||
|
except Exception as exc:
|
||||||
|
raise SkillLoadError(f"Failed to parse SKILL file {path}: {exc}") from exc
|
||||||
|
|
||||||
|
if not post.metadata:
|
||||||
|
raise SkillLoadError(
|
||||||
|
f"Invalid SKILL file {path}: missing YAML frontmatter (no '---' delimiters)"
|
||||||
|
)
|
||||||
|
|
||||||
|
for field_name in _REQUIRED_FIELDS:
|
||||||
|
if field_name not in post.metadata:
|
||||||
|
raise SkillLoadError(
|
||||||
|
f"Invalid SKILL file {path}: missing required field '{field_name}'"
|
||||||
|
)
|
||||||
|
|
||||||
|
return Skill(
|
||||||
|
name=post.metadata["name"],
|
||||||
|
description=post.metadata["description"],
|
||||||
|
body=post.content.strip(),
|
||||||
|
metadata=post.metadata.get("metadata", {}),
|
||||||
|
source_path=path,
|
||||||
|
)
|
||||||
Reference in New Issue
Block a user