ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/Karo-Bakhtiyar/ai-dev-starter-kit 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 Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/01-fullstack-patterns .claude/skills/01-fullstack-patterns $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/02-project-scaffold .claude/skills/02-project-scaffold $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/03-api-contract .claude/skills/03-api-contract $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/04-debug-strategy .claude/skills/04-debug-strategy $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/05-db-and-migrations .claude/skills/05-db-and-migrations $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/06-deploy-and-infra .claude/skills/06-deploy-and-infra $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/07-security-audit .claude/skills/07-security-audit $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/08-frontend-design .claude/skills/08-frontend-design $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/09-testing-strategy .claude/skills/09-testing-strategy $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/10-performance-checklist .claude/skills/10-performance-checklist $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/11-devlog-protocol .claude/skills/11-devlog-protocol $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/12-git-workflow .claude/skills/12-git-workflow $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/13-code-review .claude/skills/13-code-review $ npx degit Karo-Bakhtiyar/ai-dev-starter-kit/.context/skills/14-team-communication .claude/skills/14-team-communication
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 (14)
Similar rigs
pravindurgani/claude-code-multipane-iterm2
Stop your AI agent from reviewing its own code — 4-pane iTerm2 setup with role-locked Claude Code sessions. Step-by-step guide included.
Minimalist 1.0k tok ·
HartBrook/staghorn
Sync Claude Code configs and skills from GitHub — for teams, communities, or across your personal projects. Run evals to verify your guidelines actually work.
Minimalist 196 tok ·
huynhanh48/opencode-config
An enterprise-grade AI coding environment config featuring multi-agent workflow, token-efficient fallbacks, safety guardrails, and seamless model orchestration.
Minimalist 1.6k tok ·
pretend1111/claude-desktop-app
Desktop AI assistant powered by Claude API
Pragmatist 681 tok ·