weiyi88/cc-code
极简开发工作流系统 — 角色串行(PM→Architect→Dev→QA) + L0~L4 文件分层的状态机循环,解决 LLM 上下文污染与幻觉发散
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 weiyi88/cc-code/skills ./rig-cc-code/skills 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 weiyi88/cc-code/skills/agent-debug .claude/skills/agent-debug $ npx degit weiyi88/cc-code/skills/agent-feature .claude/skills/agent-feature $ npx degit weiyi88/cc-code/skills/agent-mvp .claude/skills/agent-mvp $ npx degit weiyi88/cc-code/skills/agent-uiux .claude/skills/agent-uiux $ npx degit weiyi88/cc-code/skills/agent-whole-qa .claude/skills/agent-whole-qa $ npx degit weiyi88/cc-code/skills/cc-code .claude/skills/cc-code $ npx degit weiyi88/cc-code/skills/check-fix .claude/skills/check-fix $ npx degit weiyi88/cc-code/skills/deploy .claude/skills/deploy $ npx degit weiyi88/cc-code/skills/init .claude/skills/init $ npx degit weiyi88/cc-code/skills/just-do-it .claude/skills/just-do-it $ npx degit weiyi88/cc-code/skills/login_auto .claude/skills/login_auto $ npx degit weiyi88/cc-code/skills/plan-debug .claude/skills/plan-debug $ npx degit weiyi88/cc-code/skills/plan-feature .claude/skills/plan-feature $ npx degit weiyi88/cc-code/skills/plan-mvp .claude/skills/plan-mvp $ npx degit weiyi88/cc-code/skills/plan-uiux .claude/skills/plan-uiux $ npx degit weiyi88/cc-code/skills/pr .claude/skills/pr $ npx degit weiyi88/cc-code/skills/project_resume .claude/skills/project_resume $ npx degit weiyi88/cc-code/skills/short .claude/skills/short $ npx degit weiyi88/cc-code/skills/version .claude/skills/version
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 (19)
Similar rigs
csakaszamok/p9m
Self-hosted Docker sandboxes for teams and AI agents: own Docker daemon per sandbox, a URL for every app, sleeps when idle. API + MCP server.
Minimalist 251 tok · · Q0
stxrmik/antigravity-plus
Claude Code-style workflow for Google Antigravity agents: memory, a safety guard, several agents on one project, checks of every edit, autonomy. macOS, Linux, Windows.
Skill Collector 8.5k tok · · Q10
hazeliscoding/axiomarium
Build, test, and debug your AI coding environment like software. My open lab of agents, skills, hooks, policies and evals, plus axm, a local CLI that inspects, validates and tests them.
Skill Collector 4.3k tok · · Q18
lfrodrigues/packt-claude-code-course-auth
—
Fort Knox 14.5k tok · · Q58