pm-discovery
100 / 100 · Low risk
Fine to try.
Plan or critique a product discovery process — figuring out what to build before building it. Establishes which risk you're de-risking and how much certainty the decision needs, applies the always-true core (continuous not phased, outcomes over output, problem before solution, ask about past behavior, match evidence to risk, generate solutions from validated problems, research ethically) and gates the context-dependent decisions (problem vs. solution research, qual vs. quant, lightweight vs. de…
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/'pm-discovery' ] || [ -L ~/.agents/skills/'pm-discovery' ]; then echo 'A skill folder named pm-discovery already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Uxcel-Lab/product-skills' "$d" && git -C "$d" checkout --quiet '5007cd0241ccaa51ae2e4681f9618912dc10e239' -- 'pm/processes/discovery' && mkdir -p ~/.agents/skills && cp -R "$d"/'pm/processes/discovery' ~/.agents/skills/'pm-discovery' && 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/'pm-discovery' ~/.claude/skills/'pm-discovery' (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/Uxcel-Lab/product-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 5007cd0 | 100 |