guillempuche/ai-standards
Open-source AI coding skills for Claude Code, Cursor, Copilot, and AI agents
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit guillempuche/ai-standards/.claude ./rig-ai-standards # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit guillempuche/ai-standards/.claude/skills/commit .claude/skills/commit $ npx degit guillempuche/ai-standards/.claude/skills/release .claude/skills/release $ npx degit guillempuche/ai-standards/skills/effect-lookup .claude/skills/effect-lookup $ npx degit guillempuche/ai-standards/skills/issue .claude/skills/issue $ npx degit guillempuche/ai-standards/skills/powersync .claude/skills/powersync $ npx degit guillempuche/ai-standards/skills/pr .claude/skills/pr $ npx degit guillempuche/ai-standards/skills/tamagui .claude/skills/tamagui $ npx degit guillempuche/ai-standards/skills/test-bdd .claude/skills/test-bdd $ npx degit guillempuche/ai-standards/skills/unikraft .claude/skills/unikraft
$ curl -fsSL --create-dirs -o .claude/agents/a11y-accessibility-reviewer.md https://raw.githubusercontent.com/guillempuche/ai-standards/main/agents/a11y-accessibility-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/readability-improver.md https://raw.githubusercontent.com/guillempuche/ai-standards/main/agents/readability-improver.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (9)
Subagents (2)
| a11y-accessibility-reviewer model: opus | Review React and React Native UI code for accessibility (WCAG 2.1/2.2, WAI-ARIA, VoiceOver, TalkBack), fix Critical and Major issues local to the reviewed code, and report the rest. Use after writing |
| readability-improver model: opus | Use this agent to improve code readability through renaming, comments, and whitespace. Use after writing complex logic or when code would benefit from clarification. The agent is selective — it skips |
Similar rigs
Stackbilt-dev/charter
Context compiler for AI coding agents. Modular .ai/ rules, deterministic routing, and generated configs for Claude, Codex, Cursor, and Gemini.
Pragmatist 341 tok · · Q13
sollawen/microNeo
The terminal editor that can discuss with OpenCode and Pi
Minimalist 1.7k tok · · Q0
chanmuzi/git-claw
Claude Code skill for consistent git commit, PR, and review conventions
Skill Collector 7.6k tok · · Q0
ramarlina/agx
agx: Run AI coding agents as a persistent team with objectives, memory, and coordinated work. The same agents built this tool — 167+ merged PRs, 93% clean.
Minimalist 167 tok · · Q0