JPeetz/agent-skills / skills/frontend/ui-verification
ui-verification
VerifiedUse this skill when asked to verify UI in the browser, reproduce a UI finding, re-measure after a fix, or try to break a feature with browser probes.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 2.5 KB |
| LICENSE | other | 1.1 KB |
| SKILL.md | skill md | 24.3 KB |
| evals/evals.json | config | 3.2 KB |
| references/exploratory-test.md | markdown | 4.8 KB |
| references/visual-review.md | markdown | 5.2 KB |
evals/evals.json
View on GitHub{
"skill": "ui-verification",
"version": "0.1.0",
"cases": [
{
"id": "e1",
"description": "Should trigger: verify a fix in the browser",
"input": "The empty state fix just landed. Verify it in the browser.",
"shouldTrigger": true,
"expect": "Runs the identical failure-injection probe as the original run, keeps the before artifact, records clearedBy, and reports applied / applied-unverified / regression"
},
{
"id": "e2",
"description": "Should trigger: reproduce a handed-over finding",
"input": "Static audit says our icon buttons are under 44px. Can you reproduce that?",
"shouldTrigger": true,
"expect": "Runs target-size on the resolved routes, reports bounding box in px with viewport width, checks pseudo-element hit-area expansion before failing"
},
{
"id": "e3",
"description": "Should trigger: exploratory pass on a finished feature",
"input": "The checkout flow passes its acceptance checks. Try to break it.",
"shouldTrigger": true,
"expect": "Loads references/exploratory-test.md, drives the feature like a fresh user in a test environment, files findings under explore: with reproduction steps"
},
{
"id": "e4",
"description": "Should trigger: theme and locale captures",
"input": "Capture the settings page in light and dark, LTR and RTL.",
"shouldTrigger": true,
"expect": "Drives the app's own theme toggle, asserts the theme attribute landed, runs the theme-locale-matrix probe, re-runs axe per theme, then visual review of matched captures"
},
{
"id": "e5",
"description": "Should trigger: before/after screenshot review",
"input": "Here are before and after screenshots of the pricing page - did anything regress?",
"shouldTrigger": true,
"expect": "Follows references/visual-review.md: matched viewport and theme, aligned crops, flags suspicious duplicates and unintended spacing shifts, separates visual observations from measurements"
},
{
"id": "e6",
"description": "Should trigger: performance attribution",
"input": "Our LCP is bad on the dashboard. What element is causing it?",
"shouldTrigger": true,
"expect": "Runs web-vitals against a production build with cold cache, attributes LCP to a specific element, records throttling conditions, issues no budget verdict"
},
{
"id": "n1",
"description": "Should NOT trigger: UI implementation work",
"input": "Restyle the pricing cards to use a bigger type scale.",
"shouldTrigger": false,
"expect": "Building UI, not verifying it"
},
{
"id": "n2",
"description": "Should NOT trigger: static source review",
"input": "Read components/Button.tsx and tell me if the ARIA usage is wrong.",
"shouldTrigger": false,
"expect": "Source-only review; no browser session is needed"
},
{
"id": "n3",
"description": "Should NOT trigger: durable test suite authoring",
"input": "Add Playwright tests for the signup form to CI.",
"shouldTrigger": false,
"expect": "Durable regression suite, not a one-off verification probe"
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |