agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/playwright-browser-validation/SKILL.md

playwright-browser-validation

Skill2 starsChanged 32 days agoMITView on GitHub

Runs Playwright or browser checks, captures screenshots, and records UI evidence

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If configured, run the project's e2e script and save output under .agent/evidence/test-results/.

    line 21
  2. Distinctive:

    If not configured, prefer the lightest addition approved by the plan (or manual browser verification with screenshots).

    line 22
  3. Distinctive:

    Do not claim e2e coverage without running checks or capturing evidence.

    line 33
  4. Very specific:

    Do not commit large binary evidence into git unless the project already does so.

    line 34
  5. Distinctive:

    Do not enable production crawling or authenticated production URLs without Captain approval.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Playwright / Browser Validation

Use this Skill when

Validating UI changes end-to-end, capturing screenshots, or checking browser-visible behavior after a React (or other web UI) change.

Inputs

  • Running or startable local app (dev server or preview)
  • Acceptance criteria from the approved plan
  • Existing Playwright/e2e config if present

Procedure

  1. Detect whether Playwright (or another e2e runner) is already configured.
  2. If configured, run the project's e2e script and save output under .agent/evidence/test-results/.
  3. If not configured, prefer the lightest addition approved by the plan (or manual browser verification with screenshots).
  4. Capture before/after or success-state screenshots under .agent/evidence/screenshots/.
  5. Spot-check keyboard focus and visible error/success states for forms.
  6. Record commands, results, and evidence paths in the validation report.

Output

Browser validation report with evidence paths for the First Mate and PR package.

Prohibited actions

  • Do not claim e2e coverage without running checks or capturing evidence.
  • Do not commit large binary evidence into git unless the project already does so; prefer .agent/evidence/ (often gitignored for private paths).
  • Do not enable production crawling or authenticated production URLs without Captain approval.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free