ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/h3y6e/dotfiles 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 h3y6e/dotfiles/dot_agents/skills/build-iterated-agentic-loop .claude/skills/build-iterated-agentic-loop $ npx degit h3y6e/dotfiles/dot_agents/skills/compressing-knowledge .claude/skills/compressing-knowledge $ npx degit h3y6e/dotfiles/dot_agents/skills/creating-issues .claude/skills/creating-issues $ npx degit h3y6e/dotfiles/dot_agents/skills/design-control-loop .claude/skills/design-control-loop $ npx degit h3y6e/dotfiles/dot_agents/skills/fuck .claude/skills/fuck $ npx degit h3y6e/dotfiles/dot_agents/skills/git-shipping .claude/skills/git-shipping $ npx degit h3y6e/dotfiles/dot_agents/skills/improve-claude-md .claude/skills/improve-claude-md $ npx degit h3y6e/dotfiles/dot_agents/skills/modern-web-guidance .claude/skills/modern-web-guidance $ npx degit h3y6e/dotfiles/dot_agents/skills/no-comments .claude/skills/no-comments $ npx degit h3y6e/dotfiles/dot_agents/skills/receiving-code-review .claude/skills/receiving-code-review $ npx degit h3y6e/dotfiles/dot_agents/skills/show-me .claude/skills/show-me $ npx degit h3y6e/dotfiles/dot_agents/skills/test-driven-development .claude/skills/test-driven-development $ npx degit h3y6e/dotfiles/dot_agents/skills/tracking-tasks .claude/skills/tracking-tasks $ npx degit h3y6e/dotfiles/dot_agents/skills/visual-pr .claude/skills/visual-pr $ npx degit h3y6e/dotfiles/dot_agents/skills/writing-japanese .claude/skills/writing-japanese
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 (15)
Similar rigs
0oAstro/dots
chezmoi dotfiles: zsh, git, mise modules, agent harnesses; one command per machine
Skill Collector 3.6k tok ·
zhangliang0115/ai-plugin
AI agent skills + MCP hub for DeepSeek Harness (dsh) & Claude Code — one console fronts every MCP server with ~4 meta tools, zero-config hybrid search, cross-agent skill installs. MIT.
Pragmatist 487 tok ·
raiki61/claude-plugins
Two Claude Code loops that keep reviewing and researching until they reach a fixed point: the implementer and the grader are held in separate contexts, and the machine may only ever declare failure, never convergence. Japanese only for now.
Orchestrator 1.2k tok ·
RichardBray/dotfiles
My personal configuration files and settings
Skill Collector 671 tok ·