SKILLEMALL.ai
GitHub ↗ RU Sign in

BB cross-browser-testing

Design analytics-driven browser test matrices and execute cross-browser tests. Covers BrowserStack/Sauce Labs configuration, Playwright browser channels, common cross-browser CSS/JS divergences, a known-issues documentation log, and progressive enhancement validation. Use when: "cross-browser," "browser matrix," "BrowserStack," "Safari issues," "browser compatibility," "Edge," "works in Chrome but not Safari." Not for: pixel-level baseline strategy and threshold tuning — use visual-testing; device-farm testing of native/hybrid apps — use mobile-testing. Related: visual-testing, playwright-automation, ci-cd-integration, mobile-testing.

Not recommendedcritical or high security findings
petrkindlmann/qa-skills Agent Skills author: petrkindlmann MIT 4 files body ≈ 4 282 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Design analytics-driven browser test matrices and execute cross-browser tests.

As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions

IntegrationPlaywrightData and analyticstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
78/100
safety, quality, tests
Safety 60%
64
Quality 40%
98
Run on models
none yet
Process rating
B
68/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • 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 · 2

  • high Exfiltration intent-browser-credential-store references/common-browser-issues.md:7
    Accesses a browser credential / cookie store
    Third-party cookies in an embedded context behave differently per engine: Chrome's CHIPS keys a `Partitioned` cookie to the top-level site, Safari's ITP blocks most third-party state, and Firefox's St
  • high Exfiltration intent-browser-credential-store SKILL.md:142
    Accesses a browser credential / cookie store
    - **Partitioned cookies / partitioned storage:** Chrome's CHIPS (`Partitioned` attribute), Safari's ITP, and Firefox's State Partitioning each behave differently for embedded third-party contexts. Tes

Files scanned: 4. 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 68/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 70Execution cost. Instruction body is 4282 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 36 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

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

  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +5Description quotes 6 example trigger phrases
  • +4Description says when NOT to use the skill
  • +3Description length 642: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 98.