AC browser-qa
Run automated post-deploy UI verification with a browser automation MCP (claude-in-chrome, Playwright, or Puppeteer): console-error and Core Web Vitals smoke checks, form and auth-flow interaction tests, screenshot visual regression across three breakpoints, and axe-core accessibility audits ending in a SHIP / DO-NOT-SHIP verdict. Use when testing a deployed feature on staging or preview, before shipping frontend changes, reviewing a frontend PR, or checking responsive layout and accessibility.
The skill runs browser automation before deploy: checks console errors, Core Web Vitals, form and auth interactions, visual regression across three breakpoints, and accessibility via axe-core. Returns SHIP or DO-NOT-SHIP verdict.
The file contains 872 tokens of instructions without scripts. Quality score 87/100, safety maxed out. No critical findings. Works across all major platforms from Claude to OpenClaw. Process score of 59 hints at documentation gaps or sparse run examples, but the described functionality is complete.
Install if you test frontend changes before production and want to automate checks in one go. Without scripts you'll need to wire up the browser driver manually, but the instructions are there.
Run automated post-deploy UI verification with a browser automation MCP (claude-in-chrome, Playwright, or Puppeteer): console-error and Core Web Vitals smoke…
As a process C 59/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 59/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 872 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 499: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 8 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.