claude-skills/engineering/skill-doctor/agents
Claude 40f7025250
feat(engineering): rebuild warpdotdev skill-doctor as evidence-gated grading plugin
Rebuild of warpdotdev/common-skills' skill-doctor (MIT, pinned f3b58c81) as a
full engineering/ plugin: harvest local Claude Code + Codex sessions scoped to
one repo, judge condensed transcripts against the two verbatim-preserved
rubrics (labels only), then run a deterministic aggregation gate and render a
self-contained zero-JS HTML report. 20 numbered deviations recorded in the
plugin README (authoritative list).

- new score_aggregator.py gate: derives every number from the rubric label
  tables, rejects scores for unsampled sessions, length-checks reasons,
  refuses suggestions that cite no scored session or carry no diff (exit 4)
- collector hardening: always-on 12-pattern secret redaction with per-label
  counts, chmod 0700/0600 artifacts, plugin-layout skill discovery,
  slash-command usage detection; Warp sqlite/protobuf path dropped
- renderer replaced: pure-CSS diffs + native <details> collapse instead of a
  1,531-line prebuilt JS bundle; dark-mode, print-to-PDF; vendor CTA removed
- cs-skill-doctor agent, /cs:skill-doctor command, 3 references citing 7
  sources each, 3 handoff-shape assets; SKILL.md 6/6 PASS on write-a-skill
- counters trued: skills 378, tools 698, refs 820, agents 110, commands 130,
  plugins 95 (derive_counters --check passing)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017yFdbrdBnFL8Gw7DLrdg19
2026-08-24 18:54:08 +00:00
..
cs-skill-doctor.md feat(engineering): rebuild warpdotdev skill-doctor as evidence-gated grading plugin 2026-08-24 18:54:08 +00:00