claude-skills

scriptoriumadmin/claude-skills

Fork 0

mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-09-10 22:41:16 +00:00

Commit graph

Author	SHA1	Message	Date
Claude	d12e2586d0	fix(skill-doctor): address automated review — repo-match transparency, exact-id error dedup - collect_sessions.py: name-only repo matches (worktree/basename fallback, which can match an unrelated same-named repo) are now recorded per session (repo_match), counted in inventory.json, called out in the summary, and excludable via a new --strict-repo flag - score_aggregator.py: never-scored detection tracks session ids in a set instead of substring-matching error text, so a prefix-style id can no longer suppress another session's never-scored error - redact_secrets(): broader patterns no longer stack markers on top of an already-redacted value - session files read through the MAX_FILE_BYTES cap instead of slurped whole - README deviations 21-22 recorded; count trued to 22 in CLAUDE.md and authoring-notes; prefix-id regression + single-marker redaction verified Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017yFdbrdBnFL8Gw7DLrdg19	2026-08-24 20:03:06 +00:00
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

Author

SHA1

Message

Date

Claude

d12e2586d0

fix(skill-doctor): address automated review — repo-match transparency, exact-id error dedup

- collect_sessions.py: name-only repo matches (worktree/basename fallback,
  which can match an unrelated same-named repo) are now recorded per session
  (repo_match), counted in inventory.json, called out in the summary, and
  excludable via a new --strict-repo flag
- score_aggregator.py: never-scored detection tracks session ids in a set
  instead of substring-matching error text, so a prefix-style id can no
  longer suppress another session's never-scored error
- redact_secrets(): broader patterns no longer stack markers on top of an
  already-redacted value
- session files read through the MAX_FILE_BYTES cap instead of slurped whole
- README deviations 21-22 recorded; count trued to 22 in CLAUDE.md and
  authoring-notes; prefix-id regression + single-marker redaction verified

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017yFdbrdBnFL8Gw7DLrdg19

2026-08-24 20:03:06 +00:00

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

2 commits