lynx

Run a UI experience audit on a single screen by ID using the lynx ui-experience-audit skill. Captures screenshot, accessibility snapshot, and design-token evidence for that screen only.

Run a full UI experience audit on the current project using the lynx full-ui-experience-audit skill. Captures screenshots, accessibility snapshots, and design-token evidence under e2e-evidence/<run-id>/.

Generate a human-readable Markdown report from the most recent lynx audit run. Reads e2e-evidence/<run-id>/verdict.md and per-screen evidence, then prints a structured summary to the session.

Report the verdict from the most recent lynx audit run. Reads e2e-evidence/<run-id>/verdict.md and prints a summary. Returns a clear "no prior run" message if no audit has been executed yet.

Writes structured PASS/FAIL verdicts for lynx audit runs based on evidence review

End-to-end app audit + auto-remediation loop combining the per-screen UX rigor of `ui-experience-audit` with the app-wide breadth of `full-functional-audit`. Keeps cycling — discover, audit, validate, fix in parallel, re-audit — until the codebase converges below a user-chosen defect threshold and survives a clean confirmation pass. Detects platform (iOS, web, full-stack) and routes tooling: `agent-browser` for every web interaction (never Playwright), `xcrun simctl` + `ios-validation-runner` patterns for iOS, real curl + DB checks for backends. Use whenever the request is "audit and fix the whole app", "find and fix every issue", "run the full audit until it passes", "complete UI/UX + functional sweep", "release-readiness pass with auto-fix", "production-readiness loop", "audit and remediate", "make the app pass", or "loop until clean". Supports solo-agent or parallel team-of-subagents execution — ask the user which at the start.

Deep end-to-end audit of any UI screen — visual defects, interactive element verification, content quality, and UX heuristics — in one protocol. Goes far beyond a screenshot checklist: inventories every action item (button, link, field, gesture), verifies each is discoverable / reachable / functional, audits prose / code-block / diagram / data-viz rendering, and evaluates the experience against Nielsen's 10 heuristics plus affordance theory. Use whenever reviewing a UI screenshot, simulator capture, browser screenshot, or live page on iOS, web, or cross-platform. Trigger even when the user just says "review this screen", "audit this page", "is this UI good", "QA this view", or attaches a UI screenshot. Configurable depth: identify-and-delegate (light, screenshot-only) or drive-interaction (heavy, when tap / click tools available). Complements `visual-inspection`, `functional-validation`, and `full-functional-audit`.

5 hooks across 2 events