uxr-ai-feature-study
100 / 100 · Low risk
Fine to try.
Plans a user study of an AI feature with users' current mental model and expectations before first use, tasks on their own real inputs, planned wrong-answer scenarios with what users do next, trust and correction checks and a Wizard of Oz option. Use for "run uxr-ai-feature-study", "test the AI feature with users", "what happens when the AI is wrong", "Wizard of Oz test", "user trust in AI output", "mental model of the AI feature", "AI feature research plan", part of the UX Research with Claude…
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/'uxr-ai-feature-study' ] || [ -L ~/.agents/skills/'uxr-ai-feature-study' ]; then echo 'A skill folder named uxr-ai-feature-study 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 "$d" checkout --quiet '95f01806ca43f6ee788d0579743e35853b695930' -- 'packs/ux-research-pack/skills/uxr-ai-feature-study' && mkdir -p ~/.agents/skills && cp -R "$d"/'packs/ux-research-pack/skills/uxr-ai-feature-study' ~/.agents/skills/'uxr-ai-feature-study' && 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/'uxr-ai-feature-study' ~/.claude/skills/'uxr-ai-feature-study' (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 |