chaohong-ai/ai-auto-work
Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development review using → test AI large language models. Capable of autonomously handling medium to large-scale
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit chaohong-ai/ai-auto-work/.claude ./rig-ai-auto-work # 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 chaohong-ai/ai-auto-work/.claude/skills/skill-creator .claude/skills/skill-creator $ npx degit chaohong-ai/ai-auto-work/.claude/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max
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 (2)
Slash commands (22)
/auto-work/bug/analyze/bug/fix-review/bug/fix/bug/report/fast-auto-work/feature/develop-review/feature/develop/feature/developing.auto/feature/developing/feature/plan-creator.auto/feature/plan-creator/feature/plan-review/feature/plan/git/commit/git/push/manual-work/research/do/research/loop/research/review/restart-server/start-platform
Permissions
deny (0)
—
ask (0)
—
allow (36)
Bash(go build:*)
Bash(go test:*)
Bash(go vet:*)
Bash(go run:*)
Bash(git:*)
Bash(bash:*)
Bash(mkdir:*)
Bash(touch:*)
Bash(cp:*)
Bash(rm:*)
Bash(mv:*)
Bash(cat:*)
Bash(find:*)
Bash(ls:*)
Bash(head:*)
Bash(tail:*)
Bash(grep:*)
Bash(sed:*)
Bash(awk:*)
Bash(wc:*)
Bash(sort:*)
Bash(uniq:*)
Bash(tr:*)
Bash(echo:*)
Bash(date:*)
Bash(python3:*)
Bash(npm:*)
Bash(npx:*)
Bash(node:*)
Bash(curl:*)
Bash(xargs:*)
Bash(true:*)
Bash(false:*)
Bash(test:*)
Bash(source:*)
Bash(export:*)
Similar rigs
PleasePrompto/ductor
Control Claude Code, Codex CLI and Gemini CLI from Telegram. Live streaming, persistent memory, cron jobs, webhooks, Docker sandboxing.
Minimalist 1.9k tok ·
Abdullah-967/my-claudec0de-setup-2026
Transform Claude Code into a professional autonomous agent. This setup includes structured context handoffs, a features.json tracking system, and built-in workflows for synchronization and semantic commits.
Pragmatist 750 tok ·
Arter2507/pilo-masterkit
The Ultimate AI Agent Scaffolding, Standardized Ruleset Orchestrator & UI/UX Engine. Initialize context-rich workspaces with 71+ premium reference designs, offline UI/UX Pro Max skill, dynamic PROJECT_MAP, and bilingual (VI/EN) support.
Minimalist 86 tok ·
dukcode/claude-dotfiles
Personal configuration files for Claude Code — skills, hooks, and settings.claude-config
Minimalist 155 tok ·