CtrlK
BlogDocsLog inGet started
Tessl Logo

playwright

Look at Kiln's UI in a real browser, and run its end-to-end tests. Use when checking UI you are changing, taking a screenshot of the app, driving the app with playwright-cli, starting the dev sandbox with playwright_server.sh, running or debugging `npm run tests:e2e`, or working with the seeded fixture project that gives the app's screens data to render.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable body that sequences the setup workflow and offloads detail to five well-signaled reference files, with only minor conciseness and checkpoint-explicitness gaps.

DimensionReasoningScore

Conciseness

Lean and operational with no padding about what Playwright or a browser is, but a few phrases ('This is what you want when building UI.', 'whatever URL you ask for') and the chatty section titles could be trimmed, so it sits just below the lean-every-token-earns-its-place anchor.

4 / 5

Actionability

Fully executable, copy-paste-ready commands with real URLs and arguments — `playwright_server.sh start`, `playwright-cli localstorage-set ...`, `playwright-cli run-code "async page => ..."`, `playwright-cli screenshot --filename=/tmp/ui.png` — covering the common cases.

5 / 5

Workflow Clarity

The UI-setup flow is explicitly sequenced ('Run all three, in that order' with the redirect rationale) and the 'three rules' section supplies validation/error guidance (settle page before screenshot, test $? , treat 402/429 as budget-exhausted), but a couple of checkpoints are implicit rather than framed as explicit validate-then-proceed steps.

4 / 5

Progressive Disclosure

The body is an overview and ends with a Reference table mapping each of five real bundle files to a 'When' condition, giving well-signaled one-level-deep navigation with no nesting — all five referenced files exist under references/.

5 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that names specific tools and actions and pairs them with an explicit 'Use when' trigger clause, all in third-person imperative voice with no padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Look at Kiln's UI in a real browser', 'run its end-to-end tests', 'taking a screenshot', 'driving the app with playwright-cli', 'starting the dev sandbox with playwright_server.sh', 'running or debugging `npm run tests:e2e`' — covering the skill comprehensively.

5 / 5

Completeness

Explicitly answers both 'what' (look at UI in a browser, run e2e tests) and 'when' via a 'Use when ...' clause enumerating concrete trigger situations, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Natural trigger phrases a user would say are present and varied — 'checking UI you are changing', 'taking a screenshot', 'end-to-end tests', 'npm run tests:e2e', 'playwright-cli' — including synonyms and the concrete command surface.

5 / 5

Distinctiveness Conflict Risk

A clear niche tied to Kiln plus specific tooling (playwright-cli, playwright_server.sh, tests:e2e, seeded fixture) gives it distinct triggers with minimal overlap risk against generic browser skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Kiln-AI/Kiln
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.