Is the Visual Tester skill free?

Yes. The skill itself is free from incubrain/foundry. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Visual Tester SkillProof Score?

8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Visual Tester?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Visual Tester with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Visual Tester

Annotated-snapshot UI reviews with severity-tagged findings via agent-browser.

by incubrain · incubrain/foundry

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 2dff974

Its mandated Findings Format (CRITICAL/WARNING/INFO + @eN refs) turns a vague 'the button looks off' review into a scannable triage report — but the wrapper script (.claude/scripts/visual-review.sh) and the data-testid selector table it references live in the source repo's own project config, not inside skills/visual-tester itself, so a bare copy silently can't run until you port both by hand.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Visual Tester does

Drives the agent-browser CLI to open a page, capture an annotated screenshot, and produce a structured visual-bug report with CRITICAL/WARNING/INFO severities and @eN element references. Triggers on requests to review a UI, screenshot a page, compare layouts, or test responsive design. Built as an internal project skill for one product's landing page, so the wrapper script and data-testid selector table it depends on live outside the skill folder and don't travel with a plain copy.

How to install Visual Tester

git clone https://github.com/incubrain/foundry
cd foundry
mkdir -p ~/.claude/skills
cp -r skills/visual-tester ~/.claude/skills/visual-tester

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Visual Tester

/visual-tester Annotated-snapshot UI reviews with severity-tagged findings via agent-browser.

It also activates on plain-language prompts like these:

Take a screenshot of this page and flag any visual bugs you see
Review this UI for layout issues and rate them by severity
Compare how this page renders across a few different screen sizes

Frequently asked questions

Is the Visual Tester skill free?: Yes. The skill itself is free from incubrain/foundry. SkillProof publishes the install command and an independent test verdict at no cost.
Does Visual Tester work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. Its mandated Findings Format (CRITICAL/WARNING/INFO + @eN refs) turns a vague 'the button looks off' review into a scannable triage report — but the wrapper script (.claude/scripts/visual-review.sh) and the data-testid selector table it references live in the source repo's own project config, not inside skills/visual-tester itself, so a bare copy silently can't run until you port both by hand.
What is the Visual Tester SkillProof Score?: 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Visual Tester?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Visual Tester with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.