agentleFS
Sign inStart free
robinbrilrobinbril/claude-code-harness/skills/render-proof/SKILL.md

render-proof

Skill3 starsChanged 23 days agoMITView on GitHub

Render a web page or local HTML file headless to PNG with Playwright, full page or one element, at a chosen width, and read the expected fact off the image. Use to prove a UI change visually before calling it done, at 1440, 768 and 390 wide, or when another skill asks for a render proof.

  • Installs packages

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the expected fact first: a number, a label, a position.

    line 12
  2. Distinctive:

    Never render pages with client, candidate or other personal data for a model outside your own Claude seat.

    line 31

≈ “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

Render proof

A DOM read proves nothing about layout. A real render does. This skill renders a URL or a local file headless and saves a PNG you read back.

Steps

  1. Write the expected fact first: a number, a label, a position. "Looks right" is not a fact.

  2. Render with the script in this skill's folder:

    node <deze-skill-map>/scripts/shoot.js <url|bestand> <out.png> [selector] [breedte]
    • Full page: leave out selector or pass "".
    • One element sharp: pass a CSS selector, for example "#hero".
    • Width: default 1280. For a UI change render 1440, 768 and 390.
  3. Read each PNG and check the expected fact. A mismatch is a code fix, not a note.

Requirement

Playwright with Chromium. In the project: npm i -D playwright and npx playwright install chromium. The script also finds a Playwright install in your home folder (~/node_modules).

Limits

  • Logged-in pages, hover or drag state: use the user's own browser, not this headless render.
  • Never render pages with client, candidate or other personal data for a model outside your own Claude seat.

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