rome: Skill for Claude Code

UX Audit

Evaluate UI code against a curated set of verifiable UX rules and emit findings a coding agent can directly act on. This is a linter for UX semantics, not an aesthetic critique: the goal is high-precision, evidence-backed findings, not a wall of vague suggestions.

Design philosophy (read this — it shapes every judgment call)

1. Precision over recall. A false positive costs more than a miss: the consuming coding agent will "fix" a non-problem and degrade the design. When in doubt, don't flag.
2. No evidence, no finding. Every finding must cite the exact file, line range, and quoted code snippet that demonstrates the violation. If you cannot point at the code, the finding does not exist.
3. Exceptions are where precision lives. Each rule in references/rules.md has an enumerated exceptions list. Before flagging, check the exceptions. A candidate that matches an exception is a pass, not a "borderline flag."
4. Severity is trust calibration. block findings are mechanical and near-certain — the agent should fix all of them. warn findings involve judgment — the agent should consider them and may reasonably decline with a reason. Never promote a judgment call to block.
5. Feedback must be constructive and specific. Every finding includes a concrete suggested fix expressed in terms of the actual code, not a restatement of the rule.

Workflow

Step 1 — Scope the audit

Identify the unit of analysis: the view. A view is a screen, page, route, dialog, drawer, or self-contained form — the thing a user perceives at one time. Enumerate the views in scope:

• If given a whole repo/directory: find view-level components (pages, routes, dialogs, modals). List them and confirm scope with the user if there are more than ~10.
• If given a single component/file: that component and its rendered children are the view.
• If given a screenshot or design description alongside code, the code is the source of truth for findings; the image is context.