← ClaudeAtlas

ux-interviewlisted

Plays the role of a real user in an interview-style usability test. Takes context about the product (URL, description, focus areas), auto-suggests a persona (overridable), then drives real Chrome via the claude-in-chrome extension to explore the product think-aloud style — narrating live reactions while flagging confusion, friction, and delight, and capturing GIFs/screenshots of the friction moments. Produces a structured UX report with severity-ranked pain points, what worked, and prioritized recommendations. Learns over time which findings the user considers signal vs noise. Use when you want a real-user-perspective audit of a web product to catch UX/UI/product issues that automated tests can't catch.
mostafa-drz/claude-skills · ★ 4 · Web & Frontend · score 76
Install: claude install-skill mostafa-drz/claude-skills
# UX Interview Play a real user in an interview-style test of a web product. Narrate think-aloud reactions live as you click, scroll, and try to accomplish realistic goals — then deliver a structured report with severity-ranked findings, delight moments, and prioritized recommendations. This skill is **not** an automated test runner (see `/ui-test` for that). It is a qualitative user-perspective audit. Findings are based on judgement, not assertions. ## Preferences _On startup, use the `Read` tool to load `~/.claude/skills/ux-interview/preferences.md`. If missing, treat as first-run (see First-time detection)._ Defaults when no preferences exist: - `output-root`: `./ux-interviews/` (cwd-relative when in a project; falls back to `~/.claude/skills/ux-interview/runs/` otherwise) - `default-depth`: `standard` (quick ≈ 5–7 min walkthrough / standard ≈ 12–18 min / deep ≈ 25 min+ with multiple flows) - `narration-style`: `expressive` (expressive — feels like a real user / neutral — observational / terse — short notes only) - `persona-mode`: `auto-suggest` (auto-suggest with override / always-ask / fixed-default) - `severity-floor`: `minor` (nitpick / minor / moderate / major — anything at-or-above is reported) - `capture-mode`: `friction-only` (friction-only / per-section / never) — when GIFs/screenshots are taken - `viewport`: `1440x900` — also accepts a list (e.g. `375x812,1440x900`) to test responsive - `confirm-plan`: `always` (always / never) — confirm the test plan before