pmg-build-personas
100 / 100 · Low risk
Fine to try.
Builds three or four composite personas from real interview evidence, with goals, context, needs and frustrations each linked to its source, plus proto-personas marked untested when no research exists. Use for "run pmg-build-personas", "build personas", "user personas from interviews", "who is our user", "research-based personas", "proto-personas", "persona from our research", "everyone means a different user", part of The Complete Claude Guide for Product Managers Pack by 90n.
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/'pmg-build-personas' ] || [ -L ~/.agents/skills/'pmg-build-personas' ]; then echo 'A skill folder named pmg-build-personas 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 "$d" checkout --quiet '95f01806ca43f6ee788d0579743e35853b695930' -- 'packs/complete-claude-guide-for-product-managers-pack/skills/pmg-build-personas' && mkdir -p ~/.agents/skills && cp -R "$d"/'packs/complete-claude-guide-for-product-managers-pack/skills/pmg-build-personas' ~/.agents/skills/'pmg-build-personas' && 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/'pmg-build-personas' ~/.claude/skills/'pmg-build-personas' (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 |