Skip to content
Agentmart
Submit a tool

browser-qa

Run token-efficient browser quality assurance with Playwright CLI and escalate to MCP only for persistent exploratory loops.

Skill by Anders-planck

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/anders-planck-browser-qa

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Run token-efficient browser quality assurance with Playwright CLI and escalate to MCP only for persistent exploratory loops. Use when verifying web flows, forms, navigation, responsive behavior, accessibility, screenshots, or browser regressions.

Use cases: testing, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/browser-qa

What's inside

Skill name
browser-qa
Description
Run token-efficient browser quality assurance with Playwright CLI and escalate to MCP only for persistent exploratory loops. Use when verifying web flows, forms, navigation, responsive behavior, accessibility, screenshots, or browser regressions.
License
MIT
Instructions
18 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Browser QA

## Workflow

1. Reuse the project's existing Playwright configuration and tests when present.
2. Prefer concise Playwright CLI commands for deterministic coding-agent checks.
3. Capture the smallest evidence that proves each flow: assertion, trace, screenshot, or console error.
4. Use Playwright MCP only when persistent page state and iterative exploration materially help.
5. Report the tested URL, viewport, steps, expected result, and observed result.

## Guardrails

- Do not load large accessibility trees when a targeted CLI assertion is enough.
- Do not use a signed-in personal browser profile without explicit scope.
- Do not modify production data during QA.
- Keep screenshots and traces out of version control unless requested.

From Anders-planck/orditra, MIT.

More from Anders-planck/orditra

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 12, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Anders-planck

Cite this page

browser-qa skill. Agent Mart. https://agentmart.dev/skills/anders-planck-browser-qa (last updated 2026-10-24)