mfmezger/ai_agent_dotfiles
Dotfiles for Coding Agent Configs with Skills etc. For Claude Code, Codex, Pi, OpenCode and Gemini Cli
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit mfmezger/ai_agent_dotfiles/claude/.claude ./rig-ai_agent_dotfiles # 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 mfmezger/ai_agent_dotfiles/shared/skills/agent-registry .claude/skills/agent-registry $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/building-pydantic-ai-agents .claude/skills/building-pydantic-ai-agents $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/commit .claude/skills/commit $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/confluence-datacenter .claude/skills/confluence-datacenter $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/convert-to-markdown .claude/skills/convert-to-markdown $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/doc-coauthoring .claude/skills/doc-coauthoring $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/docx .claude/skills/docx $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/fastapi .claude/skills/fastapi $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/generate-image .claude/skills/generate-image $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/github-pr-feedback .claude/skills/github-pr-feedback $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/github-pr .claude/skills/github-pr $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/go-engineering .claude/skills/go-engineering $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/google-workspace-convert .claude/skills/google-workspace-convert $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/html-reporting .claude/skills/html-reporting $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/jira-datacenter .claude/skills/jira-datacenter $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/karpathy-guidelines .claude/skills/karpathy-guidelines $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/mcp-builder .claude/skills/mcp-builder $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/pptx .claude/skills/pptx $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/python-stack .claude/skills/python-stack $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/rust-engineering .claude/skills/rust-engineering $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/skill-creator .claude/skills/skill-creator $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/tidy-first .claude/skills/tidy-first $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/typescript-engineering .claude/skills/typescript-engineering $ npx degit mfmezger/ai_agent_dotfiles/shared/skills/xlsx .claude/skills/xlsx
$ curl -fsSL --create-dirs -o .claude/agents/code-roaster.md https://raw.githubusercontent.com/mfmezger/ai_agent_dotfiles/main/claude/.claude/agents/code-roaster.md $ curl -fsSL --create-dirs -o .claude/agents/detective.md https://raw.githubusercontent.com/mfmezger/ai_agent_dotfiles/main/claude/.claude/agents/detective.md $ curl -fsSL --create-dirs -o .claude/agents/refactorer.md https://raw.githubusercontent.com/mfmezger/ai_agent_dotfiles/main/claude/.claude/agents/refactorer.md $ curl -fsSL --create-dirs -o .claude/agents/vault-organizer.md https://raw.githubusercontent.com/mfmezger/ai_agent_dotfiles/main/claude/.claude/agents/vault-organizer.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 (24)
agent-registrybuilding-pydantic-ai-agentscommitconfluence-datacenterconvert-to-markdowndoc-coauthoringdocxfastapigenerate-imagegithub-pr-feedbackgithub-prgo-engineeringgoogle-workspace-converthtml-reportingjira-datacenterkarpathy-guidelinesmcp-builderpptxpython-stackrust-engineeringskill-creatortidy-firsttypescript-engineeringxlsx
Subagents (4)
| code-roaster model: haiku | Use this agent when you want a comprehensive, no-holds-barred critique of your entire codebase. This agent should be invoked when:\n\n<example>\nContext: User has just finished a major refactoring and |
| detective model: haiku | Identify code smells, best practices violations, and test smells across Python, Go, and Rust codebases with language-specific guidance and recommendations. |
| refactorer model: haiku | Analyze code for SOLID + DRY + KISS principle violations and create detailed, actionable refactoring plans without executing changes. |
| vault-organizer model: sonnet | Use this agent when the user needs to manage, organize, or clean up their documentation and notes vault. Examples include:\n\n<example>\nContext: User has been working on a project and has accumulated |
Plugins (6)
context7@claude-plugins-officialsuperpowers@superpowers-marketplaceclaude-hud@claude-hudgopls-lsp@claude-plugins-officialcode-review@claude-plugins-officialralph-loop@claude-plugins-official
Permissions
deny (0)
—
ask (0)
—
allow (5)
Bash(go build:*)
Read
Glob
Grep
Bash(find:*)
Similar rigs
LeastBit/Claude_skills_zh-CN
Anthropics/skills中文学习版本 来自：https://github.com/anthropics/skills
Skill Collector 608 tok ·
anthropics/skills
Public repository for Agent Skills
Skill Collector 1.3k tok ·
AYESHAKHAN101/personal-ai-employee
Personal AI Employee – Bronze Tier autonomous AI system that monitors files, extracts tasks, and executes workflows using Claude Code skills.
Skill Collector 5.8k tok ·
OpenCoworkAI/open-cowork
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.
Pragmatist 382 tok ·