firefrost-gaming/claude-skills-reference
3
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
502 Commits 1 Branch 0 Tags
164749cb73d032ae69a85f775cff181dfd4bca87
Commit Graph

8 Commits

Author SHA1 Message Date
Reza Rezvani
7911cf957a feat(autoresearch-agent): fix critical bugs, package as plugin with 5 slash commands 
**Bug fixes (run_experiment.py):**
- Fix broken revert logic: was saving HEAD as pre_commit (no-op revert),
  now uses git reset --hard HEAD~1 for correct rollback
- Remove broken --loop mode (agent IS the loop, script handles one iteration)
- Fix shell injection: all git commands use subprocess list form
- Replace shell tail with Python file read

**Bug fixes (other scripts):**
- setup_experiment.py: fix shell injection in git branch creation,
  remove dead --skip-baseline flag, fix evaluator docstring parsing
- log_results.py: fix 6 falsy-zero bugs (baseline=0 treated as None),
  add domain_filter to CSV/markdown export, move import time to top
- evaluators: add FileNotFoundError handling, fix output format mismatch
  in llm_judge_copy, add peak_kb on macOS, add ValueError handling

**Plugin packaging (NEW):**
- plugin.json, settings.json, CLAUDE.md for plugin registry
- 5 slash commands: /ar:setup, /ar:run, /ar:loop, /ar:status, /ar:resume
- /ar:loop supports user-selected intervals (10m, 1h, daily, weekly, monthly)
- experiment-runner agent for autonomous loop iterations
- Registered in marketplace.json as plugin #20

**SKILL.md rewrite:**
- Replace ambiguous "Loop Protocol" with clear "Agent Protocol"
- Add results.tsv format spec, strategy escalation, self-improvement
- Replace "NEVER STOP" with resumable stopping logic

**Docs & sync:**
- Codex (157 skills), Gemini (229 items), convert.sh all pick up the skill
- 6 new MkDocs pages, mkdocs.yml nav updated
- Counts updated: 17 agents, 22 slash commands

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-13 14:38:59 +01:00
Reza Rezvani
aeab2174d2 fix(docs): convert backtick relative paths to clickable GitHub links 
Extend rewrite_relative_links() to also handle `../../path/to/file`
backtick code references, converting them to clickable links showing
parent/filename for context (e.g., product-analytics/SKILL.md).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 15:27:32 +01:00
Reza Rezvani
d10d324d50 fix(docs): rewrite broken relative links in agent and command pages 
Add rewrite_relative_links() to generate-docs.py that converts ../../
relative paths to absolute GitHub URLs. Sibling agent links (e.g.,
cs-foo.md → cs-bar.md) are preserved as local doc links. Regenerated
all agent pages with fixed references.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 15:25:31 +01:00
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
670930c69d feat(docs): implement unified design system across all generated pages 
- Add CSS components: .page-meta badges, .domain-header, .install-banner
- Fix invisible tab navigation (explicit color for light/dark modes)
- Rewrite generate-docs.py with design system templates
- Domain indexes: centered headers with icons, install banners, grid cards
- Skill pages: pill badges (domain, skill ID, source), install commands
- Agent/command pages: type badges with domain icons
- Regenerate all 210 pages (180 skills + 15 agents + 15 commands)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 12:32:49 +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
Reza Rezvani
cb3fa6b7ea feat: integrate saas-metrics-coach, add finance commands, remove seek-and-analyze-video 
- Integrate saas-metrics-coach into cs-financial-analyst agent with SaaS health
  and unit economics workflows
- Add /financial-health and /saas-health slash commands
- Add /update-docs repo command for post-creation sync pipeline
- Remove seek-and-analyze-video skill (requires paid external API)
- Update all documentation (CLAUDE.md, README.md, docs site, marketplace)
- Sync Codex CLI (150 skills), Gemini CLI (207 items), fix count consistency
- Regenerate 206 MkDocs pages, fix docs/index.md meta 170→171,
  getting-started.md finance bundle 1→2

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-10 14:29:41 +01:00
Reza Rezvani
979a1cefc7 docs: add 14 agent pages, 12 command pages, update getting-started and index 
- Extended generate-docs.py to auto-generate agent and command documentation pages
- Added extract_subtitle() for meaningful command descriptions in index
- Added Agents nav section (14 entries) and Commands nav section (12 entries) to mkdocs.yml
- Updated docs/index.md: 170 skills, 237 tools, 14 agents, 12 commands, Gemini CLI
- Updated docs/getting-started.md: Gemini CLI tab, 237 tools, fixed brand_voice path, new FAQs
- Regenerated all 203 docs pages (177 skills + 14 agents + 12 commands)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-10 09:54:53 +01:00