checking-a-page — Claude Code skill for web page checks
The checking-a-page Claude Code skill opens a web page in a browser and tests its controls. It runs after changes to a page’s HTML, JavaScript, or CSS.
MIT ★ 110 updated 2026-11-05
npx skills add awss1i/assay --skill checking-a-page -a claude-codeWhat checking-a-page does
The skill opens a finished page in a browser, operates its controls, and prints the results. Run it after the last edit, once for each page that changed. It checks one page and does not crawl to others.
Run assay <the page you changed> --one-line on the built page, such as dist/index.html, or on a folder containing index.html. The skill does not build the project or install its dependencies. On its first run, assay downloads Chromium if it is not installed. No API key or configuration is needed.
Pass along the output unchanged, and do not edit code in response to findings in the same reply. The check reports what controls do; it cannot tell whether their behavior matches the page’s intended purpose.
What it helps with
- test controls on a built web page
- spot controls that produce unexpected results when used
- check a page after changes to its JavaScript or CSS
- get a browser check report for one page
Example prompts for the agent
- Check the finished page at
dist/index.htmlafter the latest edits. - Run the page check on
todo.htmland return its output unchanged. - Check
index.htmlin this folder after the CSS edits.
How to install checking-a-page
1Skills CLI (Vercel)
npx skills add awss1i/assay --skill checking-a-page -a claude-code2Manually: put the files in place
~/.claude/skills/checking-a-page/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/checking-a-page/
1Skills CLI (Vercel)
npx skills add awss1i/assay --skill checking-a-page -a codex2Manually: put the files in place
.agents/skills/checking-a-page/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add awss1i/assay --skill checking-a-page -a cursor2Manually: put the files in place
.cursor/skills/checking-a-page/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install awss1i/assay plugins/assay/skills/checking-a-page2Manually: put the files in place
.github/skills/checking-a-page/SKILL.md1Skills CLI (Vercel)
npx skills add awss1i/assay --skill checking-a-page -a gemini-cli2Platform CLI
gemini skills install https://github.com/awss1i/assay --path plugins/assay/skills/checking-a-pageManually: put the files in place
.devin/skills/checking-a-page/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add awss1i/assay --skill checking-a-page -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about checking-a-page
How do I install checking-a-page in Claude Code?
Run npx skills add awss1i/assay --skill checking-a-page -a claude-code. The skill file is placed at ~/.claude/skills/checking-a-page/SKILL.md.
What does checking-a-page do?
It opens a built web page in a browser, operates its controls, and prints what happened. Each run checks a single page.
What does checking-a-page need to run?
It needs the assay command and a built page or a folder containing index.html. On the first run, assay downloads Chromium if needed. No API key or configuration is required.
Source text
SKILL.md · MIT
--- name: checking-a-page description: Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads. --- # Checking a page A page you have just written has no tests yet. `assay` opens it in a real browser, finds every control on it, uses all of them, and reports what it did and what happened. ## When to run it **When the work is done**, not while you are still making changes. Run it once at the end, after the last edit, on each page you changed. That includes changes to the JavaScript or CSS a page loads, not only the HTML. The page is often a folder or two above the file you changed. ## Run exactly this ```bash assay <the page you changed> --one-line ``` Point it at the page itself, such as `todo.html` or `dist/index.html`. A folder works too and opens the `index.html` inside it. It needs no key or configuration. The first run downloads Chromium if it isn't installed yet. A small page takes seconds, and a busy one can take a minute or more. ## Then print what it printed Put its output, **verbatim**, as the last thing in your reply. It is already one line, or one line and a short list. Do not summarise it, reformat it, add to it, or write your own version. It looks like this, and the numbers and wording are assay's own: ``` assay: checked <page>, <n> checks, nothing flagged. ``` Print it whether it flagged anything or not. If you print nothing, the reader can't tell a clean page from a check that never ran. **If the command did not run, say so instead, in your own words**, naming the page and quoting what the shell actually said. Never describe a check that did not happen as one that passed, and never guess at a cause. If the shell printed an error, quote it. If you didn't see one, say only that it did not run. ## Do not act on what it found **Report it and stop.** Do not edit code in response to a finding in the same reply. assay doesn't know what the page is for. It presses what the page offers and reports what followed, so a finding is a place to look, not a confirmed bug. A control can correctly do nothing in the state it was pressed in, and a value can be limited on purpose. Changing working code because of a finding nobody has checked is the mistake to avoid, which is why you report instead of fixing. If the person you are working with asks you to fix it, then fix it. ## What it will not do - **It will not build your project.** Point it at built output. Given a source tree, it says so and names the command to run. It won't run `npm install` for you, because installing dependencies executes their setup scripts. - **It checks one page.** It doesn't crawl, so run it on each page. - **It can't check intent.** A control that runs but does the wrong thing usually isn't caught.
© awss1i · MIT · awss1i/assay