agentleFS
Sign inStart free
MesteriisMesteriis/Engineering-Bible-AI/skills/ui-qa/SKILL.md

ui-qa

Skill0 starsChanged 4 months agoMITView on GitHub

Routes UI validation to native mobile, browser, accessibility or responsive QA.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for validation, debugging, and review of UI work.

    line 8
  2. Very specific:

    If evidence research is needed, select ui-research.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

UI QA Router

Use this skill for validation, debugging, and review of UI work.

Original author providers must be exposed by the current-session catalog. Read their complete skills and prerequisites; retain reviewed upstream and native plugin ownership. Bible's local QA policies define the requested evidence and scope separately. Missing native skills, tools or connections remain unresolved dependencies; report official setup and pending exposure instead of assuming availability.

Routing

  • Requested UX critique, technical UI audit, final polish or error/edge-case hardening -> impeccable.impeccable, selecting its corresponding original critique, audit, polish or harden reference. Use Operate mode for app UI.
  • Native Android/iOS app behavior on a device or emulator -> mobile-qa
  • Visual fidelity, screenshot comparison, UI regression -> playwright-visual-qa
  • Desktop/tablet/mobile web layout verification -> responsive-breakpoint-check
  • Keyboard, focus, semantics, contrast, or ARIA review -> accessibility-ui-review
  • Rendered frontend testing / debugging -> build-web-apps:frontend-testing-debugging
  • React / Next.js perf review -> build-web-apps:react-best-practices
  • Engineering review for UI changes -> superpowers.requesting-code-review, with rendered QA evidence when the requested review depends on visual behavior.

Rule

For business apps, choose relevant evidence from ui-business-apps: task completion and state behavior as well as the rendered screen. A static visual review does not prove working filters, permissions, save behavior or chart data. Report checks that ran and the precise unresolved interaction or runtime gap. If evidence research is needed, select ui-research; if implementation is requested, select ui-build. Reuse an established route on follow-up turns.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free