scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-10-08 03:07:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
1506 commits 6 branches 7 tags 44 MiB
Commit graph

8 commits

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
2c5a793128
feat(engineering): apply karpathy-coder + Matt Pocock to fullstack/frontend/backend 
Audit findings:
- senior-fullstack / senior-frontend / senior-backend SKILL.md files were
  generic role catalogs with no opinionated workflow, no customization
  surface, and no cross-agent invocation contract.
- A 4-person SaaS startup and a 200-engineer enterprise read identical
  recommendations.
- Other agents/skills had no typed surface to orchestrate fullstack /
  frontend / backend lenses.

Per-skill additions (21 new files: 7 x 3 skills):
- scripts/<role>_decision_engine.py - stdlib-only deterministic profile
  picker. Refuses to recommend without Karpathy-#1 core assumptions.
  Surfaces kill criteria. Names human approver chain (never auto-approves).
- profiles/*.json x 4 per skill (12 total) - JSON customization surface.
  Users copy one to <your-org>.json to override defaults.
- references/forcing_questions.md - 7 Matt Pocock forcing questions per
  skill (21 total) with recommended answer + canon citation + kill criterion.
- references/composition_map.md - explicit routing into POWERFUL-tier
  specialists (api-design-reviewer, database-designer, slo-architect,
  performance-profiler, a11y-audit, epic-design, apple-hig-expert, etc.).

Three orchestrator agents (context: fork):
- agents/engineering/cs-fullstack-engineer.md
- agents/engineering/cs-frontend-engineer.md
- agents/engineering/cs-backend-engineer.md
Invokable by other agents via Agent(subagent_type="cs-<role>-engineer", ...).

Four slash commands:
- /cs:fullstack-review, /cs:frontend-review, /cs:backend-review
- /cs:engineer-grill - cross-role 21-question forcing-question runner

Augmented SKILL.md files (additive only - Karpathy #3 surgical):
Each gained 5 new sections: Assumptions & Verifiable Success Criteria
(Karpathy #1+#4), Customization profiles, Composition map, Forcing-question
library, Invocation from other agents and skills.

Verification:
- 12/12 profile JSON files parse cleanly
- 3/3 decision engines pass --help and --sample, exit 0
- 3/3 cs-* agents have valid YAML + context: fork
- 3/3 agent paths resolve from agents/engineering/
- 3/3 commands reference the correct cs-* agent
- 69/69 plugin.json files pass check_plugin_json.py
- Existing SKILL.md content unchanged (additive edits only)

Versions: engineering-team plugin 2.2.3 -> 2.8.1; marketplace entry 2.8.1.

https://claude.ai/code/session_01UyWs4rKccdxUWFcWi6Y8Ly
 2026-05-20 07:24:21 +00:00
Reza Rezvani
e2fff2f8f2 docs: sync counts and regenerate pages for product team expansion 
Update all documentation to reflect 177 skills, 254 tools, 357 references,
16 agents, and 17 commands. Add 4 new skill pages, 1 agent page, and
2 command pages to MkDocs site. Sync Codex (156) and Gemini (218) indexes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 15:15:39 +01:00
Reza Rezvani
2d5f846c58 docs: sync counts across CLAUDE.md, README, and agents guide 
- CLAUDE.md: Marketing 42→43, pages 206→210+, date updated
- README.md: Python tools 245→250
- agents/CLAUDE.md: agent count 6→15, skill count 42→173, full agent table

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 12:54:54 +01:00
Reza Rezvani
4e9f1d934d feat(engineering): add google-workspace-cli skill with 5 Python tools 
New skill for Google Workspace administration via the gws CLI:
- SKILL.md with 4 workflows (Gmail, Drive/Sheets, Calendar, Security Audit)
- 5 stdlib-only Python scripts (doctor, auth setup, recipe runner, audit, analyzer)
- 3 reference docs, 2 asset files, 43 built-in recipes, 10 persona bundles
- cs-workspace-admin agent, /google-workspace slash command
- Standalone marketplace plugin entry with .claude-plugin/plugin.json
- Cross-platform sync (Codex CLI, Gemini CLI), MkDocs docs pages
- All documentation updated (173 skills, 250 tools, 15 agents, 15 commands)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 09:59:40 +01:00
Leo
418de87449 docs: add ClawHub publishing constraints to CLAUDE.md, agents/CLAUDE.md, GEMINI.md 
- cs- prefix for slug conflicts only (ClawHub registry, not repo)
- No paid/commercial service dependencies
- Rate limit: 5 new skills/hour
- plugin.json schema enforcement
- Version must match repo release
 2026-03-10 19:27:16 +01:00
Reza Rezvani
fc565cac54 docs(agents): add production agents table to CLAUDE.md 
Day 5: Documentation Updates - Added catalog of 5 completed agents

## Agents Cataloged
- cs-content-creator (327 lines) - Marketing domain
- cs-demand-gen-specialist (289 lines) - Marketing domain
- cs-ceo-advisor (360 lines) - C-Level domain
- cs-cto-advisor (412 lines) - C-Level domain
- cs-product-manager (407 lines) - Product domain

Total: 1,795 lines of agent documentation
Template: agent-template.md (318 lines)

Sprint: sprint-11-05-2025 (Day 5)
Issue: #15
 2025-11-05 14:47:38 +01:00
Reza Rezvani
706da0250c docs(claude): refactor CLAUDE.md into modular documentation structure 
- Refactor main CLAUDE.md from 491 to 164 lines (66% reduction)
- Create 9 domain-specific CLAUDE.md files for focused guidance:
  * agents/CLAUDE.md (347 lines) - Agent development guide
  * marketing-skill/CLAUDE.md (253 lines) - Marketing tools
  * product-team/CLAUDE.md (268 lines) - Product management tools
  * engineering-team/CLAUDE.md (291 lines) - Engineering tools
  * standards/CLAUDE.md (176 lines) - Standards usage
  * c-level-advisor/CLAUDE.md (143 lines) - Strategic advisory
  * project-management/CLAUDE.md (139 lines) - Atlassian integration
  * ra-qm-team/CLAUDE.md (153 lines) - RA/QM compliance
  * templates/CLAUDE.md (77 lines) - Template system
- Add navigation map in main CLAUDE.md for easy domain access
- Create PROGRESS.md for real-time sprint tracking
- Implement auto-documentation system for sprint progress

Benefits:
- Main CLAUDE.md now concise and navigable
- Domain-specific guidance easier to find
- No duplicate content across files
- Better organization for 42 skills across 6 domains

Total: 2,011 lines across 10 organized files vs 491 lines in 1 monolithic file

Sprint: sprint-11-05-2025
Issue: Part of documentation refactoring milestone
 2025-11-05 12:44:03 +01:00