visual-qa

visual-qa is an End-to-end & browser testing skill for AI agents, published by code-yeongyu in the oh-my-openagent repository on GitHub. Skillspace rates visual-qa C (77/100) and it passed the safety scan; a judge model has also reviewed it.

MUST USE after building/changing any UI or when asked whether a page, component, or TUI looks right. Rigorous visual QA across web/page and terminal UIs. Prefer browser:control-in-app-browser for unauthenticated browser/page QA in Codex, then Playwright/agent-browser/dev-browser. Captures screenshot/TUI evidence with bundled diff scripts, runs design-system/functional and visual-fidelity/CJK reviewer passes, then synthesizes a good/bad verdict. Triggers: visual QA, screenshot/pixel diff, UI looks wrong, reference fidelity, design system check, responsive check, CJK text clipping, TUI alignment, box-drawing drift.

Grade
C
Quality
77 / 100
Safety
Passed
GitHub stars
65,891

Placed #1 of 6 in the judged category final for End-to-end & browser testing.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubcode-yeongyu/oh-my-openagent

Our review

Architecture
100 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 1 collections
Scope
Portable: works in any project. General visual QA method for any web or terminal UI

Judge review

Placed #1 of 6 in the judged category final for End-to-end & browser testing.

  • Trigger9292
  • Instructions9393
  • Specificity9090
  • Safety9696
  • Disclosure8282
  • Maintenance9090
Treats reference-packet text as untrusted data never to be followed as instructions, requires redacting secrets before persisting evidence, and refuses stale or sampled coverage as a pass.

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • No blind task eval yet
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More End-to-end & browser testing skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.