ryanliu30/claude-setup
A personal Claude Code setup script.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/ryanliu30/claude-setup 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 ryanliu30/claude-setup/home/skills/build-fix .claude/skills/build-fix $ npx degit ryanliu30/claude-setup/home/skills/check .claude/skills/check $ npx degit ryanliu30/claude-setup/home/skills/commit .claude/skills/commit $ npx degit ryanliu30/claude-setup/home/skills/cpp-coding-standards .claude/skills/cpp-coding-standards $ npx degit ryanliu30/claude-setup/home/skills/cpp-review .claude/skills/cpp-review $ npx degit ryanliu30/claude-setup/home/skills/cpp-testing .claude/skills/cpp-testing $ npx degit ryanliu30/claude-setup/home/skills/domain-modeling .claude/skills/domain-modeling $ npx degit ryanliu30/claude-setup/home/skills/grilling .claude/skills/grilling $ npx degit ryanliu30/claude-setup/home/skills/improve-codebase-architecture .claude/skills/improve-codebase-architecture $ npx degit ryanliu30/claude-setup/home/skills/ml-review .claude/skills/ml-review $ npx degit ryanliu30/claude-setup/home/skills/ponytail-audit .claude/skills/ponytail-audit $ npx degit ryanliu30/claude-setup/home/skills/ponytail-review .claude/skills/ponytail-review $ npx degit ryanliu30/claude-setup/home/skills/ponytail .claude/skills/ponytail $ npx degit ryanliu30/claude-setup/home/skills/python-patterns .claude/skills/python-patterns $ npx degit ryanliu30/claude-setup/home/skills/python-review .claude/skills/python-review $ npx degit ryanliu30/claude-setup/home/skills/python-testing .claude/skills/python-testing $ npx degit ryanliu30/claude-setup/home/skills/tdd-workflow .claude/skills/tdd-workflow $ npx degit ryanliu30/claude-setup/home/skills/test-coverage .claude/skills/test-coverage $ npx degit ryanliu30/claude-setup/home/skills/verify-agent-implementation .claude/skills/verify-agent-implementation
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 (19)
Similar rigs
jpc4729/setup
My agent setup for Claude Code, Codex, Cursor, Grok and opencode: shared rules, six subagents, a git guard hook and 14 skills, with an installer that copies files and merges settings.
Pragmatist 9.9k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
saqie803/ponytail
Ship production-ready code with one line of AI-generated output, built for 20 agents and zero ceremony.
Pragmatist 714 tok ·
contextmux/contextmux
Turn a ticket into a reviewed pull request, under gates that stop work which drifted out of scope or weakened tests. Compiles one source of coding rules to CLAUDE.md, AGENTS.md, .cursor/rules and copilot-instructions.
Pragmatist 10.1k tok ·