visual-qa

A skill for checking whether a changed user interface looks and behaves as intended. It captures repeatable screenshots or other visual evidence across declared pages, screen sizes, themes, and states, then reviews and repairs problems.

In plain words
What is it for?
Use it after UI changes to capture screenshots, inspect responsive layouts and themes, verify interactions and accessibility constraints, and decide whether the visual work passes review.
Why use it?
It replaces informal visual checking with evidence that can be reviewed and compared. It also catches missing, outdated, or inconsistent UI states before the work is marked complete.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/moasq/agentic-ship/visual-qa
Any agent
npx skills add moasq/agentic-ship --skill visual-qa
Clone the repo
git clone --depth 1 https://github.com/moasq/agentic-ship

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.01163
Opus 5 $0.00026 $0.00581
Sonnet 5 $0.00010 $0.00233
Haiku 4.5 $0.00005 $0.00116

Measured 2d ago against content hash f6c8259d9de9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/visual-qa/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual QA

Downstream contract: paths like src/ and convex/ refer to the product workspace that adopts Agentic Ship, not this tool repo.

Turn a visual direction into reviewable evidence. Automated checks prove coverage and basic browser integrity; the reviewer proves that the rendered product expresses the declared direction without generic generated-page residue.

Authority and required inputs

Read the Component rules, Styling rules, and UI-quality rules in AGENTS.md. They are authoritative. Use this skill as the post-implementation procedure, and use testing for the gate order and repair loop.

Before capture, require this frontend handoff:

  • a valid UI plan;
  • changed surface ids and source summary;
  • declared routes, deterministic states, themes, viewports, and interactions;
  • accessibility constraints, anti-goals, reference decisions, and the signature element;
  • confirmation that captures use only public or synthetic content.

If the plan is absent or invalid, return to visual-direction. Do not reverse-engineer intent from the finished screenshot.

Load references/review-policy.md when capturing, accepting, diagnosing stale evidence, or integrating the completion gate. Load the operational anti-slop rubric for the subjective rendered review.

Procedure

1. Reproduce the declared scope

Run the plan check first:

pnpm ui:plan check

Start the application in a separate terminal with deterministic local fixtures:

pnpm dev

Do not capture production, authenticated personal state, changing vendor data, secrets, or real customer content. A polished production screenshot is not worth creating an unreviewable data artifact.

2. Generate the evidence matrix

Capture from the local server:

pnpm ui:review capture --base-url http://localhost:3000

Read the full file on GitHub · 150 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 150 lines · 52 tokens per session scan A f6c8259d9de9

Subscribe to this mod's changes

visual-qa is a skill published in the GitHub repository moasq/agentic-ship (10 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 1,163 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens