A page you have just written has no tests yet. assay serves the page locally, opens it in a real Chromium browser through Playwright, finds every control on it, uses all of them, and reports where the page contradicts itself. There is no LLM API key requirement. Browser behavior can vary with application state, timing, browser version and network dependencies; repeated results are evidence only for the tested environment.
Use this skill after you create or change a web page, to run assay on that page and report the one line it prints. The skill reports the result and does not change code because of it unless you ask.
Install assay from PyPI. The package is named assay-ui and the command it installs is assay.
pip install assay-ui
It needs Python 3.10 or newer. On the first run assay downloads the Chromium build Playwright uses.
Point assay at the page itself and ask for the one-line summary.
assay <the page you changed> --one-line
Point it at a file such as todo.html or dist/index.html. A folder also works and opens the index.html inside it. The page is often a folder or two above the file you edited, so a change to a script or stylesheet still means running assay on the page that loads it. assay needs no LLM API key; initial browser installation and page dependencies may use the network. A small page takes seconds, and a busy one can take a minute or more.
Put assay's output, word for word, as the last thing in your reply. It is already one line, or one line and a short list. Do not summarize it, reformat it, add to it, or write your own version.
A clean run looks like this, with assay's own numbers and wording.
assay: checked todo/todo.html, 8 checks, nothing flagged.
A run that flagged something looks like this, followed by a short list.
assay: checked notes/index.html, 12 checks, 4 flagged:
Report the line whether it flagged anything or not. Without it, the reader cannot tell a clean page from a check that never ran.
If the command did not run, say so in your own words, name the page, and quote what the shell actually printed. Never describe a check that did not happen as one that passed, and never guess at a cause.
Report what assay found and stop. Do not edit code in response to a finding in the same reply. If the user then asks you to fix it, fix it.
User: I added a to-do list at todo/todo.html. Does it work?
assay todo/todo.html --one-line
assay: checked todo/todo.html, 8 checks, nothing flagged.
Report that line as the last thing in the reply, and do not change the page.
assay notes/ --one-line
assay: checked notes/index.html, 12 checks, 4 flagged:
- draw on canvas twice, then press Undo twice: it reacted one press late
Report the whole line and its short list, say that a finding is a place to look rather than a confirmed bug, and wait for the user to ask before changing anything.
assay dist/index.html --one-line
assay: error: dist/index.html does not exist
Say that assay did not run, name the page, and quote the message. Do not report a check that never happened as one that passed.
dist/index.html, not at a source template.npm install for you, because installing dependencies executes their setup scripts.--report to save an HTML report.Solution: Build the project first and point assay at the built page, such as dist/index.html.
Solution: Paste assay's line verbatim as the last thing in the reply, with its own numbers and wording.
Solution: Report the finding and stop. Change code only when the user asks.
Solution: Run assay on the page that loads the changed script or stylesheet, which is often a folder or two above the file you edited.
@mock-hunter audits a live page for mock data, hardcoded values, and broken endpoints, for when you need to know whether the values on screen are real.@accesslint-diff diffs a page's accessibility violations against a baseline, for when you care about accessibility rather than whether the controls work.pip install assay-ui installs.Use a reviewed pinned assay/browser installation. Serving a page on loopback does not sandbox its scripts: controls may send mail, charge accounts or mutate remote backends. Run against authorized test accounts with isolated data and controlled network access. Report which controls actually ran and any untested browser states rather than claiming every possible path was exercised.