Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mostafa-drz/claude-skillsnpx agentmods add skills/mostafa-drz/claude-skills/ux-interviewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mostafa-drz/claude-skills/ux-interview)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/ux-interview"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/ux-interview/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/ux-interview"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/ux-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00147 | $0.04442 |
| Opus 5.5 | $0.00059 | $0.01777 |
| Sonnet 5.5 | $0.00029 | $0.00888 |
| Haiku 4.5 | $0.00015 | $0.00444 |
Grade A, and why
ux-interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 takenviewport:1440x900— also accepts a list (e.g.375x812,1440x900) to test responsiveconfirm-plan:always(always / never) — confirm the test plan before opening the browserauto-open-report:true
Also load ~/.claude/skills/ux-interview/feedback-journal.md if present — surface the latest 5 Signal: lines to bias defaults (e.g. if the user repeatedly downgraded "minor copy issues", raise the severity floor pre-selection).
Context
On startup, use Bash to detect: today's date+time (date +%Y-%m-%d-%H%M), the current working directory (pwd), and whether the configured output-root exists. Do NOT call any browser tool yet — that happens in Step 4.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +3 lines e691a06e5c24
- 1mo ago First seen · 368 lines · 147 tokens per session scan A f2df50ef9abe
ux-interview is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed yesterday), licensed MIT. It adds 147 tokens to every session and 4,442 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
architecture-drawer
Use when asked to draw system architecture diagrams, generate technical architecture SVGs, or export architecture diagrams to editable PowerPoint presentations. Supports multi-layer diagrams with automatic layout validation and scoring (16-dimension evaluator catches collisions, overlaps, dangles, crossings, palette…
style-guide-builder
Build a reusable visual style guide from reference images.
agency-brand-scoping
Five brand direction variations for pitch discovery.
dev-screenshot-beautifier
Polish raw screenshots into LP-ready heroes.
information-architecture
Map the user journey first, then derive the screen inventory, navigation and hierarchy from it, flagging any screen that serves no journey step. Writes the four-part markdown plus an HTML diagram of the step-to-screen mapping. Use after the brief is settled and before tokens or UI.
design-tokens
Establish color, typography, spacing, radius and motion as named role-based tokens. Use before building any interface.