SKILLEMALL.ai
GitHub ↗ RU Sign in

DD playwright-core

Battle-tested Playwright patterns for writing and debugging reliable E2E, API, component, visual, accessibility, and security tests. Use when you need locator strategy, assertions, fixtures, network mocking, auth flows, trace debugging, or framework recipes for React, Next.js, Vue, and Angular. TypeScript and JavaScript.

testdino-hq/playwright-skill Agent Skills author: testdino-hq 51 files body ≈ 1 414 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Battle-tested Playwright patterns for writing and debugging reliable E2E, API, component, visual, accessibility, and security tests.

As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationPlaywrightSoftware developmenttype 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
D
74/100
safety, quality, tests
Safety 60%
70
Quality 40%
80
Run on models
none yet
Process rating
D
44/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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.

Secrets in code medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

How to improve

    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 · 22

    ✓ No critical or high findings

    Medium and low: 22
    • medium Exfiltration intent-browser-credential-store authentication.md:1375
      Accesses a browser credential / cookie store (documentation of a security skill)
      **Cause**: Some auth flows set cookies with `SameSite=Strict` or use browser-specific cookie behavior. Chromium and Firefox handle third-party cookies differently.
      security skill
    • medium Secrets in code secret-labelled-token third-party-integrations.md:490
      Labelled token / key literal (vendor format unknown — verify it is not a live credential)
      // Secret key: 6LeI…JWe
    • low Secrets in code secret-password-literal auth-flows.md:579
      Hard-coded password / key literal (may be an example)
      editor: { email: 'ed…@….com', password: 'Edit…123!' },
    • low Secrets in code secret-password-literal auth-flows.md:580
      Hard-coded password / key literal (may be an example)
      viewer: { email: 'vi…@….com', password: 'View…123!' },
    • low Secrets in code secret-password-literal auth-flows.md:941
      Hard-coded password / key literal (may be an example)
      password: 'Secu…123!',
    • low Secrets in code secret-password-literal configuration.md:537
      Hard-coded password / key literal (may be an example)
      API_KEY=stag…789
    • low Secrets in code secret-password-literal test-architecture.md:227
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      password: 's3cure!Pass',
      fixture
    • low Secrets in code secret-password-literal test-architecture.md:278
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      password: 's3cure!Pass',
      fixture
    • low Secrets in code secret-password-literal test-data-management.md:101
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      password: 'SecureP@ss123!',
      fixture
    • low Secrets in code secret-password-literal test-data-management.md:149
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      password: 'SecureP@ss123!',
      fixture
    • low Secrets in code secret-password-literal third-party-integrations.md:179
      Hard-coded password / key literal (may be an example)
      client_secret: 'pi_m…456',
    • low Secrets in code secret-high-entropy-token third-party-integrations.md:489
      High-entropy token-like string (may be an id, hash or a credential)
      // Site key: 6LeI…KhI (always passes)
    • low Secrets in code secret-high-entropy-token third-party-integrations.md:490
      High-entropy token-like string (may be an id, hash or a credential)
      // Secret key: 6LeI…JWe
    • low Secrets in code secret-password-literal when-to-mock.md:64
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      clientSecret: 'pi_m…123',
      fixture
    • low Secrets in code secret-password-literal when-to-mock.md:116
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      clientSecret: 'pi_m…123',
      fixture
    • low Secrets in code secret-password-literal when-to-mock.md:765
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      clientSecret: 'pi_m…123',
      fixture
    • low Secrets in code secret-password-literal when-to-mock.md:793
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      clientSecret: 'pi_m…123',
      fixture

    A further 5 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 51. 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 44/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 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
    • 40Consistency. Frontmatter name (playwright-core) differs from the folder (core)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 100Steps. 10 steps
    • 100Execution cost. Instruction body is 1414 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)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 322: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 10 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.