claude-skills

scriptoriumadmin/claude-skills

Fork 0

mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-09-06 08:15:58 +00:00

Commit graph

Author	SHA1	Message	Date
Claude	c84e322a99	chore(registry,ci): derive counters, register 11 plugins, add CI guards - marketplace.json: 11 shipped-but-unregistered plugins added (compliance-os, snowflake-development, behuman, claude-coach, grill-with-docs, llm-cost-optimizer, prompt-governance, business-investment-advisor, video-content-strategist, compliance-team-eu-ai-act, compliance-team-iso42001) -> 77/77 registered; self-contradicting counts fixed - counters reconciled to derived ground truth across README.md, CLAUDE.md, agents/CLAUDE.md, marketplace.json (346 skills / 17 domains / 584 tools / 701 references / 93 agents / 99 commands / 77 plugins) - new guards: scripts/derive_counters.py (--check, gate G3), scripts/check_dual_publish.py (11 pairs, gate G4), scripts/smoke_scripts.py + smoke_exceptions.txt (gate G8) - meta-tooling fixes (gate G9): generate-docs.py --help no longer rewrites docs/ as a side effect; audit_skills.py --help instant; markdown-html added to hermes/vibe/gemini sync scripts and generate-docs domain maps - ci-quality-gate.yml: compileall completed 9 -> 17 domains; 4 new advisory gate steps (continue-on-error pending burn-in) Verification (all green): check_plugin_json --all 77 OK; check_paths --all 0 findings; check_dual_publish 0 drifted; smoke 586 pass / 0 fail / 11 by-design exceptions; derive_counters --check pass; compileall 17 domains rc=0. https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF	2026-06-10 14:33:19 +00:00
Claude	507f62610f	feat(scripts): add audit_skills.py — repo-wide write-a-skill validator runner Adds a small stdlib-only orchestration script that runs the skill_review_checklist_runner.py (shipped in v2.6.0) across every SKILL.md in the repo and aggregates results. Output: - Total skills audited (PASS / WARN / FAIL / ERROR counts + percentages) - Failure breakdown by rule (which of Matt's 6 checklist items fail most) - Top-10 worst offenders (skill folder + specific failing rules) Excludes auto-generated tool-specific symlinks (.gemini, .codex, .cursor, .cline, /site/, /.git/) and template fixtures (templates/, assets/sample-skill). Use case: periodic audit of skill-library hygiene. Re-run after each batch of new skills to catch drift early. Produced the punch list that informed the v2.6.1 cleanup planning (40% of repo skills miss "Use when" triggers; 88% exceed Matt's 100-line ceiling — both flagged for triage). Stdlib-only. No external dependencies. Runs in ~30s on a 298-skill repo. https://claude.ai/code/session_01VFreMf7XLBqMgjsrG4wSYe	2026-05-13 23:25:55 +00:00

Author

SHA1

Message

Date

Claude

c84e322a99

chore(registry,ci): derive counters, register 11 plugins, add CI guards

- marketplace.json: 11 shipped-but-unregistered plugins added (compliance-os,
  snowflake-development, behuman, claude-coach, grill-with-docs,
  llm-cost-optimizer, prompt-governance, business-investment-advisor,
  video-content-strategist, compliance-team-eu-ai-act, compliance-team-iso42001)
  -> 77/77 registered; self-contradicting counts fixed
- counters reconciled to derived ground truth across README.md, CLAUDE.md,
  agents/CLAUDE.md, marketplace.json (346 skills / 17 domains / 584 tools /
  701 references / 93 agents / 99 commands / 77 plugins)
- new guards: scripts/derive_counters.py (--check, gate G3),
  scripts/check_dual_publish.py (11 pairs, gate G4),
  scripts/smoke_scripts.py + smoke_exceptions.txt (gate G8)
- meta-tooling fixes (gate G9): generate-docs.py --help no longer rewrites
  docs/ as a side effect; audit_skills.py --help instant; markdown-html added
  to hermes/vibe/gemini sync scripts and generate-docs domain maps
- ci-quality-gate.yml: compileall completed 9 -> 17 domains; 4 new advisory
  gate steps (continue-on-error pending burn-in)

Verification (all green): check_plugin_json --all 77 OK; check_paths --all 0
findings; check_dual_publish 0 drifted; smoke 586 pass / 0 fail / 11 by-design
exceptions; derive_counters --check pass; compileall 17 domains rc=0.

https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF

2026-06-10 14:33:19 +00:00

Claude

507f62610f

feat(scripts): add audit_skills.py — repo-wide write-a-skill validator runner

Adds a small stdlib-only orchestration script that runs the
skill_review_checklist_runner.py (shipped in v2.6.0) across every SKILL.md
in the repo and aggregates results.

Output:
- Total skills audited (PASS / WARN / FAIL / ERROR counts + percentages)
- Failure breakdown by rule (which of Matt's 6 checklist items fail most)
- Top-10 worst offenders (skill folder + specific failing rules)

Excludes auto-generated tool-specific symlinks (.gemini, .codex, .cursor,
.cline, /site/, /.git/) and template fixtures (templates/, assets/sample-skill).

Use case: periodic audit of skill-library hygiene. Re-run after each batch
of new skills to catch drift early. Produced the punch list that informed
the v2.6.1 cleanup planning (40% of repo skills miss "Use when" triggers;
88% exceed Matt's 100-line ceiling — both flagged for triage).

Stdlib-only. No external dependencies. Runs in ~30s on a 298-skill repo.

https://claude.ai/code/session_01VFreMf7XLBqMgjsrG4wSYe

2026-05-13 23:25:55 +00:00

2 commits