paulirish/dotfiles
paul's fish, bash, git, etc config files. good stuff.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit paulirish/dotfiles/agents ./rig-dotfiles/agents 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 paulirish/dotfiles/agents/skills/buildless-types .claude/skills/buildless-types $ npx degit paulirish/dotfiles/agents/skills/distill-page .claude/skills/distill-page $ npx degit paulirish/dotfiles/agents/skills/fetch-as-markdown .claude/skills/fetch-as-markdown $ npx degit paulirish/dotfiles/agents/skills/github-pr-comments .claude/skills/github-pr-comments $ npx degit paulirish/dotfiles/agents/skills/google-ai-search .claude/skills/google-ai-search $ npx degit paulirish/dotfiles/agents/skills/heap-snapshot-inspection .claude/skills/heap-snapshot-inspection $ npx degit paulirish/dotfiles/agents/skills/hot-reload-chrome-ext .claude/skills/hot-reload-chrome-ext $ npx degit paulirish/dotfiles/agents/skills/lexicon .claude/skills/lexicon $ npx degit paulirish/dotfiles/agents/skills/modern-css .claude/skills/modern-css $ npx degit paulirish/dotfiles/agents/skills/npm-trusted-publishing .claude/skills/npm-trusted-publishing $ npx degit paulirish/dotfiles/agents/skills/pauls-project-setup .claude/skills/pauls-project-setup $ npx degit paulirish/dotfiles/agents/skills/qmd-expert .claude/skills/qmd-expert
$ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-types/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-page/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/updating.md https://raw.githubusercontent.<redacted>-page/updating.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/paulirish/dotfiles/main/agents/skills/fetch-as-markdown/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-pr-comments/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-ai-search/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/paulirish/dotfiles/main/agents/skills/heap-snapshot-inspection/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/paulirish/dotfiles/main/agents/skills/hot-reload-chrome-ext/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-css/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/argyle-cacadia-2025-deck.md https://raw.githubusercontent.<redacted>-css/references/argyle-cacadia-2025-deck.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/paulirish/dotfiles/main/agents/skills/npm-trusted-publishing/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/paulirish/dotfiles/main/agents/skills/pauls-project-setup/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/paulirish/dotfiles/main/agents/skills/qmd-expert/SKILL.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (12)
buildless-typesdistill-pagefetch-as-markdownGitHub PR comment fetchergoogle-ai-searchheap-snapshot-inspectionHot Reloading for Chrome Extensionslexiconmodern-cssnpm-trusted-publishingpauls-project-setupqmd-expert
Subagents (14)
| buildless-types | Use when the user asks to "set up types without a build step", "use vanilla JS with types", "configure erasable syntax", or mentions "JSDoc type checking". It provides instructions for modern type saf |
| distill-page | Extract distilled page content as Markdown using Chromium's on-device ML page content annotation. |
| updating | — |
| fetch-as-markdown | Fetch a URL using Playwright and convert its content to Markdown. |
| GitHub PR comment fetcher | Easily query for open discussions and reviews on a pull request to help resolve them. |
| google-ai-search | Run a Google Search and capture the AI response/Overview. |
| heap-snapshot-inspection | Investigating memory issues and leaks in Chromium-based environments (Chrome, Node.js, Electron) using heap snapshots and the @paulirish/agents CLI. |
| Hot Reloading for Chrome Extensions | Set up hot-reloading for chrome extensions. Provides a zero-dependency solution for automatic extension refreshing during development. |
| lexicon | Define, review, and audit a project's domain vocabulary across code and documentation. Use when creating or editing a lexicon, glossary, or term list; auditing against a lexicon for drift, invented vo |
| modern-css | Specialized knowledge for writing modern high-quality CSS. Trigger this skill when starting a new CSS project/file, when the user asks about new CSS features (e.g. Masonry, View Transitions, Container |
| argyle-cacadia-2025-deck | — |
| npm-trusted-publishing | Set up or debug npm Trusted Publishing (OIDC) from GitHub Actions. Handles permissions, metadata validation, and provenance. |
| pauls-project-setup | Paul's modern stack conventions for new projects (pnpm, native node test, esbuild, buildless-types). Consult when starting a new project or repository. |
| qmd-expert | How to effectively use QMD (Quick Markdown Search) to pull in extra relevant context, run multi-query searches, extract high-scoring chunk IDs, and fetch their contents. Use this skill when asked to s |
Similar rigs
ashlrai/lexicon
Personal lexicon for voice-to-agents. Fixes the names STT gets wrong (Ashler -> Ashlr.AI) before Claude Code, Codex or any MCP agent sees your dictated prompt.
Pragmatist 5.5k tok ·
G-Eskayo/marvin
Open-source memory, routing, and skills layer for Claude Code — persistent memory, 27 skills, autonomous background agents, and a self-measuring bench
Skill Collector 3.9k tok ·
queirozlc/claude-config
Portable Claude Code config: skills, settings, hooks, install script
YOLO Cowboy 3.5k tok ·
eliranwong/biblemate-agentic-workspace
BibleMate AI + UniqueBible Data (running on Google Antigravity / Claude Code / Grok Build) - An integrated local workspace combining robust scripture databases, modular study skills, and specialized AI personas to streamline biblical resear
Orchestrator 5.8k tok ·