visual-qa

visual-qa is an open-source frontend skill for Codex, published by code-yeongyu. Its author describes it as: “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 brows…”. The project has 68k stars on GitHub and ships custom license terms, so review them before reuse. Add it to your setup with `git clone https://github.com/code-yeongyu/oh-my-openagent ~/.claude/skills/visual-qa`.

What visual-qa does

Verify a rendered UI against intent using objective script evidence plus two parallel read-only oracle passes, then synthesize one good/bad verdict. The script numbers focus the reviewers. They are not the verdict.

Installation

Add visual-qa to your agent with:

git clone https://github.com/code-yeongyu/oh-my-openagent ~/.claude/skills/visual-qa

Always review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.

What's inside

The SKILL.md for visual-qa is organised into these sections:

• Purpose and when to use
• Step 1 - Detect the surface
• Step 2 - Capture objective reference evidence
• Reference packet hygiene
• Coverage - capture every page, not a sample
• Evidence must be fresh
• Capture hygiene - validate before dispatching reviewers
• Web
• TUI
• Motion and interaction capture
• Step 3 - Dispatch two read-only QA subagents in parallel
• Pass A - Design-system and functional integrity (deeper, strict)

When to use it

Reach for visual-qa when you want frontend help from Codex without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.

Strengths

• Ships in code-yeongyu/oh-my-openagent, an established project with 67,593 GitHub stars
• Declares compatibility with Codex
• Actively maintained (recent commits)

Things to check

• No license declared — confirm terms with the author before reuse

Topics

Frequently asked questions

What does visual-qa do?

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.

How do I install visual-qa?

Run git clone https://github.com/code-yeongyu/oh-my-openagent ~/.claude/skills/visual-qa in your agent, then reload your skills. Review the source at https://github.com/code-yeongyu/oh-my-openagent before installing.

Is visual-qa free to use?

visual-qa is publicly available on GitHub, but code-yeongyu has not declared a standard open-source license (Other). Confirm the terms with the author before reusing it.

Which agents does visual-qa work with?

visual-qa declares compatibility with Codex. Agent Skills use a portable SKILL.md format, so other compatible clients can usually load it too.

Where does visual-qa come from?

visual-qa ships inside code-yeongyu/oh-my-openagent, a repository that contains 46 catalogued skills in total. The repository's 67,593 GitHub stars apply to that whole collection, not to this skill on its own.