stella/ai-shared
Shared AI prompts, skills, and sync tooling for stella repositories
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 stella/ai-shared/skills ./rig-ai-shared/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 stella/ai-shared/skills/finish-pr .claude/skills/finish-pr $ npx degit stella/ai-shared/skills/open-pr .claude/skills/open-pr $ npx degit stella/ai-shared/skills/plan .claude/skills/plan $ npx degit stella/ai-shared/skills/product-think .claude/skills/product-think $ npx degit stella/ai-shared/skills/rabbit-round .claude/skills/rabbit-round $ npx degit stella/ai-shared/skills/regression-hunt .claude/skills/regression-hunt $ npx degit stella/ai-shared/skills/security-audit .claude/skills/security-audit $ npx degit stella/ai-shared/skills/update-deps .claude/skills/update-deps
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 (8)
Similar rigs
asafofer/perch
Where you left off, in the notch. A macOS app for people running Claude Code, Codex, OpenCode and pi sessions at once.
Pragmatist 10.5k tok · · Q37
moruku36/multi-ai-workflow
Multi-agent workflow architecture, Alibaba/MiMo and Cloudflare-guided source reviews, and an inactive central review hub.
Minimalist 835 tok · · Q0
MairwunNx/ctxray
🩻 X-ray for agent harnesses. See exactly what your Claude Code, Codex, Cursor & co. loaded — and test it in CI.
Minimalist 1.5k tok · · Q5
ArcadeAI/arcade-mcp
MCP Server Framework and Tool Development library for building custom capabilities into agents.
Pragmatist 4.8k tok · · Q5