scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-10-07 02:58:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
979 commits 6 branches 7 tags 44 MiB
Commit graph

8 commits

Author SHA1 Message Date
Claude
5954dfcce1
cleanup(engineering): address remaining 7 polish items from PR #718 bot review 
Bundle of low-medium-severity follow-ups that were deferred when PR #720
landed the 3 blocking bugs. None of these silently break correctness —
they're discoverability, consistency, and convention gaps.

Bugs / code-quality:

1. fullstack_decision_engine.py: asymmetric cadence matching
   `inputs.cadence in target or target in inputs.cadence` produced
   asymmetric results — "per-pr" matched "per-pr-with-gates" but not
   vice versa. Profile cadences are intentional alternatives joined
   by "-or-" (e.g. "weekly-or-on-demand" → {weekly, on-demand}); now
   parsed explicitly with "-with-..." modifier suffixes stripped.

   Verified:
     cadence=per-pr → matches per-pr, per-pr-with-gates, daily-or-per-pr
     cadence=daily  → matches daily-or-per-pr (only)
     cadence=on-demand → matches weekly-or-on-demand

2. fullstack_decision_engine.py: rename weight_total/weight_matched
   to w_total/w_matched. Backend and frontend engines already use the
   short form; this aligns the three files as a family.

3. sync-gemini-skills.py: 3-way name collision in dedup logic
   The naive `if name in seen_names: name = parent-name` handled one
   collision but not two. Three "status" skills under "skills" parent
   dirs produced two entries both named "skills-status". Now suffixes
   with -2, -3, ... so each entry has a unique index name. Eliminates
   the duplicate-name ambiguity surfaced when checking PR #713.

Discoverability:

4. senior-fullstack/SKILL.md: surface fullstack_decision_engine.py in
   the labeled "Tools" section at the top. Previously only mentioned
   inline in the body (5 references buried in the Stack Decision Matrix
   section); not findable when scanning the SKILL.md.

Conventions / v2.8.0 compliance:

5. commands/cs-{fullstack,backend,frontend}-review.md: add explicit
   "## Forcing-question library" section header per the v2.8.0
   convention. Each lists the 7 questions inline with a pointer to
   the canonical reference file.

6. agents/engineering/cs-{fullstack,backend,frontend}-engineer.md:
   alphabetize the specialist list in the description field (annotated
   that workflow body order remains dependency-driven). Makes the
   three agent descriptions consistent as a family.

7. agents/engineering/cs-{backend,frontend}-engineer.md: promote the
   "Cross-agent invocation" content out of Workflow 3 into a dedicated
   "## When invoked as fork target" section with an explicit question-
   skip table per parent agent (cs-fullstack-engineer, cs-cto-advisor,
   cs-vpe-advisor, cs-ciso-advisor for backend; cs-fullstack-engineer,
   cs-content-creator, cs-product-manager for frontend). Closes the
   cross-agent contract gap the bot flagged.

Not changed:

- CLAUDE.md plugin-schema section (already corrected in #715; bot's
  "stale text" claim was incorrect — it was reading the cumulative diff)
- Workflow body specialist order (intentional dependency order; would
  break the SLO-first → API → DB → migration → observability sequence)

Verification:
- All 3 decision engines: --sample → exit 0
- Cadence matching: 3 test cases pass cleanly
- check_plugin_json.py --all → 0 FAIL, 0 WARN, 69 OK
- sync-gemini-skills.py → 392 unique names (was 391 unique / 1 dupe)
 2026-05-21 13:47:08 +00:00
claude[bot]
59e5e48cc9 fix(agents): remove hardcoded model from engineering agents to inherit user settings 
Remove 'model: sonnet' from cs-fullstack-engineer, cs-frontend-engineer,
and cs-backend-engineer YAML frontmatter so each agent inherits the model
configured in the user's Claude Code settings instead of being locked to sonnet.

Co-authored-by: Alireza Rezvani <alirezarezvani@users.noreply.github.com>
 2026-05-21 04:59:09 +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
9c2facebf4 fix(karpathy-coder): pass 8-phase plugin audit + wire repo integration 
Auto-fixes from plugin-audit pipeline:

Phase 2 (70.4 → 75.0 GOOD):
- Added README.md with quick start, tool descriptions, enforcement levels

Phase 3 (51.7 → 63.5, above 60):
- Added expected_outputs/ with 4 JSON fixtures (one per tool)
- Completeness 66.7 → 85.0

Phase 6 (marketplace + agent + command):
- Added karpathy-coder to .claude-plugin/marketplace.json (category: development)
- Mirrored cs-karpathy-reviewer to agents/engineering/
- Mirrored /karpathy-check to commands/
- mkdocs.yml: added skill + command nav entries

Phase 7 (ecosystem sync):
- Ran sync-codex-skills.py + sync-gemini-skills.py
- karpathy-coder now in both indexes

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-12 13:34:55 +02:00
Reza Rezvani
b6ca45ddec feat(engineering): add llm-wiki plugin — second brain for Claude Code + Obsidian 
Implements Karpathy's LLM Wiki pattern as a production-grade plugin. The LLM
incrementally ingests sources into a persistent, interlinked Obsidian vault —
updating entity/concept/source pages, flagging contradictions, maintaining an
index and append-only log. Knowledge compounds instead of being re-derived by
RAG on every query.

Plugin contents (engineering/llm-wiki/):
- SKILL.md with `context: fork` frontmatter for skill chaining
- 3 sub-agents: wiki-ingestor, wiki-librarian, wiki-linter
- 5 slash commands: /wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log
- 8 Python tools (stdlib only): init_vault, ingest_source, update_index,
  append_log, wiki_search (BM25), lint_wiki, graph_analyzer, export_marp
- 8 reference docs: schema, page-formats, ingest/query/lint workflows,
  obsidian-setup, cross-tool-setup, memex-principles
- Vault templates: CLAUDE.md, AGENTS.md, .cursorrules, index.md, log.md,
  5 page templates (entity, concept, source, comparison, synthesis)
- Worked example vault on "LLM interpretability"
- .claude-plugin/plugin.json manifest

Cross-tool compatibility: the scripts are pure Python stdlib. Only the schema
loader changes per tool (CLAUDE.md for Claude Code, AGENTS.md for Codex CLI /
Cursor / Antigravity / OpenCode / Gemini CLI, .cursorrules for legacy Cursor).
init_vault.py --tool all installs all three.

Repo-level registration:
- Commands mirrored to top-level commands/ for repo-wide discovery
- Agents mirrored to agents/engineering/ as cs-wiki-{ingestor,librarian,linter}
- .claude-plugin/marketplace.json: new llm-wiki entry + version bump to v2.3.0
- CLAUDE.md updated: 234 skills, 313 Python tools, 432 refs, 28 agents, 27 commands

Also saved (deferred): craighewitt-mattpocock reimplementation plan at
documentation/implementation/ — 4-pod proposal for building better versions
of selected skills from thecraighewitt-skills and mattpocock-skills
collections. Not executed; awaiting user confirmation on scope.

End-to-end smoke test passed: init_vault → ingest → update_index → append_log
→ wiki_search → lint → graph_analyzer → export_marp all run against a fresh
vault with real pages, wikilinks, and frontmatter.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-11 01:14:11 +02:00
Reza Rezvani
ce1d7925cc feat(engineering): integrate focused-fix skill — docs, command, agent, marketplace 
- Normalize SKILL.md frontmatter to repo standard (remove non-standard
  license, metadata.* fields; inline description)
- Generate docs page (docs/skills/engineering/focused-fix.md)
- Add to mkdocs.yml nav (skills + commands)
- Create /focused-fix slash command (commands/ + .claude/commands/)
- Add to cs-senior-engineer agent (skill integration + new workflow #4)
- Update marketplace.json and plugin.json descriptions (30 → 31 skills)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 13:59:30 +01:00
Alireza Rezvani
a68ae3a05e
Dev (#305) 
* chore: update gitignore for audit reports and playwright cache

* fix: add YAML frontmatter (name + description) to all SKILL.md files

- Added frontmatter to 34 skills that were missing it entirely (0% Tessl score)
- Fixed name field format to kebab-case across all 169 skills
- Resolves #284

* chore: sync codex skills symlinks [automated]

* fix: optimize 14 low-scoring skills via Tessl review (#290)

Tessl optimization: 14 skills improved from ≤69% to 85%+. Closes #285, #286.

* chore: sync codex skills symlinks [automated]

* fix: optimize 18 skills via Tessl review + compliance fix (closes #287) (#291)

Phase 1: 18 skills optimized via Tessl (avg 77% → 95%). Closes #287.

* feat: add scripts and references to 4 prompt-only skills + Tessl optimization (#292)

Phase 2: 3 new scripts + 2 reference files for prompt-only skills. Tessl 45-55% → 94-100%.

* feat: add 6 agents + 5 slash commands for full coverage (v2.7.0) (#293)

Phase 3: 6 new agents (all 9 categories covered) + 5 slash commands.

* fix: Phase 5 verification fixes + docs update (#294)

Phase 5 verification fixes

* chore: sync codex skills symlinks [automated]

* fix: marketplace audit — all 11 plugins validated by Claude Code (#295)

Marketplace audit: all 11 plugins validated + installed + tested in Claude Code

* fix: restore 7 removed plugins + revert playwright-pro name to pw

Reverts two overly aggressive audit changes:
- Restored content-creator, demand-gen, fullstack-engineer, aws-architect,
  product-manager, scrum-master, skill-security-auditor to marketplace
- Reverted playwright-pro plugin.json name back to 'pw' (intentional short name)

* refactor: split 21 over-500-line skills into SKILL.md + references (#296)

* chore: sync codex skills symlinks [automated]

* docs: update all documentation with accurate counts and regenerated skill pages

- Update skill count to 170, Python tools to 213, references to 314 across all docs
- Regenerate all 170 skill doc pages from latest SKILL.md sources
- Update CLAUDE.md with v2.1.1 highlights, accurate architecture tree, and roadmap
- Update README.md badges and overview table
- Update marketplace.json metadata description and version
- Update mkdocs.yml, index.md, getting-started.md with correct numbers

* fix: add root-level SKILL.md and .codex/instructions.md to all domains (#301)

Root cause: CLI tools (ai-agent-skills, agent-skills-cli) look for SKILL.md
at the specified install path. 7 of 9 domain directories were missing this
file, causing "Skill not found" errors for bundle installs like:
  npx ai-agent-skills install alirezarezvani/claude-skills/engineering-team

Fix:
- Add root-level SKILL.md with YAML frontmatter to 7 domains
- Add .codex/instructions.md to 8 domains (for Codex CLI discovery)
- Update INSTALLATION.md with accurate skill counts (53→170)
- Add troubleshooting entry for "Skill not found" error

All 9 domains now have: SKILL.md + .codex/instructions.md + plugin.json

Closes #301

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add Gemini CLI + OpenClaw support, fix Codex missing 25 skills

Gemini CLI:
- Add GEMINI.md with activation instructions
- Add scripts/gemini-install.sh setup script
- Add scripts/sync-gemini-skills.py (194 skills indexed)
- Add .gemini/skills/ with symlinks for all skills, agents, commands
- Remove phantom medium-content-pro entries from sync script
- Add top-level folder filter to prevent gitignored dirs from leaking

Codex CLI:
- Fix sync-codex-skills.py missing "engineering" domain (25 POWERFUL skills)
- Regenerate .codex/skills-index.json: 124 → 149 skills
- Add 25 new symlinks in .codex/skills/

OpenClaw:
- Add OpenClaw installation section to INSTALLATION.md
- Add ClawHub install + manual install + YAML frontmatter docs

Documentation:
- Update INSTALLATION.md with all 4 platforms + accurate counts
- Update README.md: "three platforms" → "four platforms" + Gemini quick start
- Update CLAUDE.md with Gemini CLI support in v2.1.1 highlights
- Update SKILL-AUTHORING-STANDARD.md + SKILL_PIPELINE.md with Gemini steps
- Add OpenClaw + Gemini to installation locations reference table

Marketplace: all 18 plugins validated — sources exist, SKILL.md present

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(product,pm): world-class product & PM skills audit — 6 scripts, 5 agents, 7 commands, 23 references/assets

Phase 1 — Agent & Command Foundation:
- Rewrite cs-project-manager agent (55→515 lines, 4 workflows, 6 skill integrations)
- Expand cs-product-manager agent (408→684 lines, orchestrates all 8 product skills)
- Add 7 slash commands: /rice, /okr, /persona, /user-story, /sprint-health, /project-health, /retro

Phase 2 — Script Gap Closure (2,779 lines):
- jira-expert: jql_query_builder.py (22 patterns), workflow_validator.py
- confluence-expert: space_structure_generator.py, content_audit_analyzer.py
- atlassian-admin: permission_audit_tool.py
- atlassian-templates: template_scaffolder.py (Confluence XHTML generation)

Phase 3 — Reference & Asset Enrichment:
- 9 product references (competitive-teardown, landing-page-generator, saas-scaffolder)
- 6 PM references (confluence-expert, atlassian-admin, atlassian-templates)
- 7 product assets (templates for PRD, RICE, sprint, stories, OKR, research, design system)
- 1 PM asset (permission_scheme_template.json)

Phase 4 — New Agents:
- cs-agile-product-owner, cs-product-strategist, cs-ux-researcher

Phase 5 — Integration & Polish:
- Related Skills cross-references in 8 SKILL.md files
- Updated product-team/CLAUDE.md (5→8 skills, 6→9 tools, 4 agents, 5 commands)
- Updated project-management/CLAUDE.md (0→12 scripts, 3 commands)
- Regenerated docs site (177 pages), updated homepage and getting-started

Quality audit: 31 files reviewed, 29 PASS, 2 fixed (copy-frameworks.md, governance-framework.md)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: audit and repair all plugins, agents, and commands

- Fix 12 command files: correct CLI arg syntax, script paths, and usage docs
- Fix 3 agents with broken script/reference paths (cs-content-creator,
  cs-demand-gen-specialist, cs-financial-analyst)
- Add complete YAML frontmatter to 5 agents (cs-growth-strategist,
  cs-engineering-lead, cs-senior-engineer, cs-financial-analyst,
  cs-quality-regulatory)
- Fix cs-ceo-advisor related agent path
- Update marketplace.json metadata counts (224 tools, 341 refs, 14 agents,
  12 commands)

Verified: all 19 scripts pass --help, all 14 agent paths resolve, mkdocs
builds clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: repair 25 Python scripts failing --help across all domains

- Fix Python 3.10+ syntax (float | None → Optional[float]) in 2 scripts
- Add argparse CLI handling to 9 marketing scripts using raw sys.argv
- Fix 10 scripts crashing at module level (wrap in __main__, add argparse)
- Make yaml/prefect/mcp imports conditional with stdlib fallbacks (4 scripts)
- Fix f-string backslash syntax in project_bootstrapper.py
- Fix -h flag conflict in pr_analyzer.py
- Fix tech-debt.md description (score → prioritize)

All 237 scripts now pass python3 --help verification.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(product-team): close 3 verified gaps in product skills

- Fix competitive-teardown/SKILL.md: replace broken references
  DATA_COLLECTION.md → references/data-collection-guide.md and
  TEMPLATES.md → references/analysis-templates.md (workflow was broken
  at steps 2 and 4)

- Upgrade landing_page_scaffolder.py: add TSX + Tailwind output format
  (--format tsx) matching SKILL.md promise of Next.js/React components.
  4 design styles (dark-saas, clean-minimal, bold-startup, enterprise).
  TSX is now default; HTML preserved via --format html

- Rewrite README.md: fix stale counts (was 5 skills/15+ tools, now
  accurately shows 8 skills/9 tools), remove 7 ghost scripts that
  never existed (sprint_planner.py, velocity_tracker.py, etc.)

- Fix tech-debt.md description (score → prioritize)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* release: v2.1.2 — landing page TSX output, brand voice integration, docs update

- Landing page generator defaults to Next.js TSX + Tailwind CSS (4 design styles)
- Brand voice analyzer integrated into landing page generation workflow
- CHANGELOG, CLAUDE.md, README.md updated for v2.1.2
- All 13 plugin.json + marketplace.json bumped to 2.1.2
- Gemini/Codex skill indexes re-synced
- Backward compatible: --format html preserved, no breaking changes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: alirezarezvani <5697919+alirezarezvani@users.noreply.github.com>
Co-authored-by: Leo <leo@openclaw.ai>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-10 09:48:49 +01:00
Alireza Rezvani
8902ba79d7
release: v2.1.1 — skill optimization, agents, commands, reference splits (#297) 2026-03-09 15:54:25 +01:00