agentsclimarketplace

Workbench browser proofshot qa

Skill Fearvox/multica-ultimate-workbench/skills/workbench-browser-proofshot-qa

Public multi-agent workbench skill pack for SDD, review gates, context discipline, VM lanes, Sanity context, and autonomous agent coordination.

Install
npx -y skills add Fearvox/multica-ultimate-workbench --skill workbench-browser-proofshot-qa

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 23 stars23 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Browser verification, proof screenshots, traces, console and network checks, and reproducible UI evidence for Workbench QA.

SKILL.md

1.3 KB, as published. Nobody here has run it

Workbench Browser Proofshot QA

Use this skill for browser-based verification, Playwright checks, proof screenshots, local web app dogfooding, and reproducible UI evidence.

Browser Verification Loop

  1. Start or identify the real app URL.
  2. Record browser, viewport, account/auth state, and build/commit when available.
  3. Exercise the user workflow, not only page load.
  4. Capture screenshots or trace artifacts for states that matter.
  5. Check console errors, failed network requests, obvious layout breakage, and final persisted state.
  6. Report exact repro steps and evidence paths.

Boundaries

  • Do not edit code during report-only QA unless explicitly assigned.
  • Do not treat a static screenshot as proof that a workflow works.
  • Do not rely on cached authenticated state without saying so.
  • Do not include private data in screenshots or copied logs.

Output Contract

Return:

  • BROWSER_VERDICT: PASS / FLAG / BLOCK.
  • RUN: URL, viewport, browser/tool, commit/build if known.
  • STEPS: concise repro or verification path.
  • EVIDENCE: screenshot/trace/log paths.
  • FINDINGS: ordered by severity.
  • FOLLOW-UP: smallest fix or re-test needed.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.