ux-audit
Audit a page / surface against the Designing Interfaces pattern language + the ux skill checklists, then land findings. Three layers — static (code), visual (screenshots), dynamic (automated user journey + perf). Use to run a repeatable, standards-based UX review of one screen.
Profile →npx skills add lobehub/lobehub --skill ux-audit --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# UX Audit A repeatable, standards-based UX review of **one surface at a time**. The benchmark is two things together: 1. **Jenifer Tidwell, _Designing Interfaces_** — the pattern language for what a good interface is _made of_. See [`references/pattern-catalog.md`](references/pattern-catalog.md). 2. **The [`ux`](../ux/SKILL.md) skill** — LobeHub's execution checklists for how a flow should _behave_. The audit answers: **which patterns does the surface use** (and how well), and **where is the experience weak** (each gap tied to a checklist item). Recurring gaps feed back as new `ux` checklist items; the audit itself becomes a worked-example reference. Do **one surface per run** — a full-app sweep is too much for a single pass. Re-run per page as the product grows; that's the "continuous" part. ## Three layers — pick by what you need to catch An audit is not one activity. A finding is only trustworthy from a layer that can actually _see_ it. Each layer has its own procedure file; run the ones the surface needs. | Layer | File | What it does | Catches | Cost | | -------------- | --------------------------------------------------- | ----------------------------------------------------
- Three layers — pick by what you need to catch
- Coverage matrix — which layer can conclude what
- Tiering — don't run all three every time
- Ground rule: evidence, not vibes
- Ground rule: benchmark the surface class, not just our own artifact
- Ground rule: report the good, not only the gaps
- Severity rubric (shared)
- Output (shared)
- Land the findings (shared)
- Related skills
What does the ux-audit skill do?
Audit a page / surface against the Designing Interfaces pattern language + the ux skill checklists, then land findings. Three layers — static (code), visual (screenshots), dynamic (automated user journey + perf). Use to run a repeatable, standards-based UX review of one screen.
How do I install it?
Run `npx skills add lobehub/lobehub --skill ux-audit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From lobehub/lobehub, a repository with 81,252 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.