mirror of https://github.com/obra/superpowers.git synced 2026-09-03 12:15:39 +00:00

Files

T

Jesse Vincent affa7fa4e2 feat: add diagnosing-superpowers skill

Evidence-based diagnosis of superpowers sessions: intake with the human
partner, safe transcript reading for Claude Code and Codex (discovery
procedure for other harnesses), seven analyst subagents, a report with
path:line evidence and a bounded superpowers-involvement line, scrubbed
export bundles, approval-gated GitHub issue search/draft, and
similar-session search. Includes spec, plan, structure test, and README
and docs index lines.

Developed RED-GREEN-REFACTOR per writing-skills: 46 scored scenario runs
across five SKILL.md versions, all twelve scenarios clean against the
final version, micro-tests control 5/5 to skill 0/5 on both
baseline-failing prohibitions, and one end-to-end run. Eval records are
kept by the maintainer outside the repo.

Claude-Session: https://claude.ai/code/session_01DyaGKhTXvHNs2JgPhDktz7

2026-08-31 10:03:57 -07:00

1.7 KiB

Raw Blame History

Other harnesses: discover, then report what you found

This file is for any harness without a verified reference in this directory. You know your own harness better than this file does. Use that knowledge, and write down exactly what you found so the report reader can judge it.

Procedure

Ask the harness. Many harnesses expose a session or history command (<harness> session list, /sessions, a "resume" picker). Use it to get the session id and, if shown, the file path.
Look under the harness's config directory (~/.<harness>/, ~/.config/<harness>/, ~/.local/share/<harness>/) for sessions, history, chats, threads, or projects directories holding .jsonl or .json files.
Confirm a candidate by extracting its first human message with a size-safe command (head -c 2000, or jq on the first record) and matching it to what your human partner remembers. Never print whole lines; treat every candidate like the verified stores: wc -lc and a long-line check before anything else.
Map the fields you need by reading a handful of records with jq -c 'keys' or head -c: human prompt, assistant text, tool call and result, model, harness version, timestamps, subagent linkage, compaction.
Record in the case file and the report's coverage notes: the store path, the layout you inferred, which of the fields above you could and could not find, and your confidence. Field-level claims in the report are marked "inferred from the file, not a documented format".
If you cannot find the store, say so and ask your human partner for the path. Do not guess a layout from another harness.

1.7 KiB Raw Blame History

Other harnesses: discover, then report what you found

Procedure

1.7 KiB

Raw Blame History