agentleFS
Sign inStart free
PyModelPyModel/designer-skill/.claude/skills/designer-skill-mcp-render-checks/SKILL.md

designer-skill-mcp-render-checks

Skill52 starsChanged 3 days agoMITView on GitHub

Use when editing verify_rendered or its Playwright checks.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Keep the query and hash of file URLs.

    line 15
  2. Very specific:

    No browser driver means NOT_RUN with the reason.

    line 16

≈ “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

designer-skill-mcp: rendered checks

A rendered check judges where the page ends up. A page that fails to load is a finding (page-load FAIL), not a tool error.

  • The browser runs in a child process (assets/engine/node/rendered-worker.mjs), forked by src/rendered.ts with credential environment variables removed. Keep project code out of the server process.
  • One scope rule, assets/engine/node/local-url.mjs, covers the input URL and every main-frame navigation. Do not write a second copy.
  • Playwright's page.route does not see redirect hops. Confine navigation with route.fetch({ maxRedirects: 0 }), refuse a non-local Location, then route.fulfill. A redirect to another host must be refused before that host is contacted; the test asserts zero requests reached it.
  • Subresources and iframes are not confined. Keep that limit stated in docs/HARDENING.md.
  • Keep the query and hash of file URLs; #/settings is a different state.
  • No browser driver means NOT_RUN with the reason. Never PASS. Playwright and axe-core load from the project only; the package has no fallback.
  • The whole check has one deadline (renderedPolicy.deadlineMs); the deadline and a client cancel both kill the child.
  • In the worker use process.on('message'), not once: once lets the process exit before the check runs.
  • Tests live in the verify_rendered block of test/audit-fixes.test.ts; scripts/smoke-tarball.mjs calls the tool from the packed tarball.

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