aipm-agent-spec
100 / 100 · Low risk
Fine to try.
Writes an Agent Spec with the goal and done-state, allowed tools and permissions, stop conditions and a spend budget per session, the approval points carried over from the human-in-the-loop design, and the list of actions the agent must never take alone. Use for "run aipm-agent-spec", "agent spec", "write the limits for our agent", "agent permissions", "where should the agent stop", "agent guardrails", "excessive agency", "spend cap for the agent", part of the Claude for AI Product Managers Pac…
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'aipm-agent-spec' ] || [ -L ~/.agents/skills/'aipm-agent-spec' ]; then echo 'A skill folder named aipm-agent-spec already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/polar-bear-org/claude-skills' "$d" && git -C "$d" checkout --quiet '95f01806ca43f6ee788d0579743e35853b695930' -- 'packs/ai-product-managers-pack/skills/aipm-agent-spec' && mkdir -p ~/.agents/skills && cp -R "$d"/'packs/ai-product-managers-pack/skills/aipm-agent-spec' ~/.agents/skills/'aipm-agent-spec' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'aipm-agent-spec' ~/.claude/skills/'aipm-agent-spec' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/polar-bear-org/claude-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 95f0180 | 100 |