CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/playwright-testing

Use whenever the task is to write, fix or speed up Playwright tests, even one quick test or a flaky one: role-based locators, web-first assertions instead of waitForTimeout, page objects, config and browser projects, traces, sharding and CI. Has the anti-pattern table for flaky Playwright tests.

1.00x
Quality

94%

Does it follow best practices?

Impact

100%

1.00x

Average score across 10 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

92%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.

An excellent, well-structured skill body: nine clearly sequenced steps with executable code and commands throughout, an explicit failure-debugging feedback loop, an anti-pattern checklist, and clean progressive disclosure into two real, appropriately scoped reference files. The only improvement area is trimming Claude-known explanatory content (the Playwright-overview blockquotes and the trace-viewer feature list).

DimensionReasoningScore

Conciseness

The body is dominated by lean, runnable commands and code, but the Overview blockquotes ("Playwright Test is an end-to-end test framework for modern web apps...") and the trace-viewer feature list restate facts Claude already knows, and the repeated "Per [pw-intro][pwi]" attributions are trimmable — minor over-explanation per anchor 4 rather than the pervasive padding of anchor 3.

4 / 5

Actionability

Every step ships copy-paste-ready material: the scaffold command, a complete spec, a full Page Object class, a complete defineConfig, CLI invocations, and CI/sharding YAML; the only non-literal fragment is the test-results/<...>/trace.zip path placeholder, which reflects a genuinely variable path rather than missing detail.

5 / 5

Workflow Clarity

Steps 1-9 form an explicit scaffold→author→configure→run→debug→scale→CI sequence with an error-recovery feedback loop ("When a test fails, the trace contains everything needed to debug" plus show-trace command), retry configuration, and an anti-pattern checklist — matching anchor 5's feedback loops and checklists; anchor 4 would imply missing checkpoints.

5 / 5

Progressive Disclosure

Both referenced files (references/browser-matrix.md, 199 lines; references/mobile-emulation.md, 180 lines) exist as real one-level-deep references, clearly signaled inline and in a References section, with the cross-browser matrix and mobile-emulation detail appropriately split out of the concise overview — matching anchor 5's well-signaled navigation.

5 / 5

Total

19

/

20

Passed

Description

92%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 description: it states concrete capabilities, includes an explicit and natural 'Use whenever' trigger clause covering even edge cases like a single flaky test, and is tightly scoped to Playwright. The only gap is the absence of common synonyms (E2E, end-to-end, browser testing) that users might say without naming Playwright.

DimensionReasoningScore

Specificity

Concrete verbs ("write, fix or speed up") are followed by a comprehensive list of specific capabilities ("role-based locators, web-first assertions instead of waitForTimeout, page objects, config and browser projects, traces, sharding and CI"), matching the comprehensive-coverage anchor rather than anchor 4's 'minor gaps'.

5 / 5

Completeness

The explicit trigger clause "Use whenever the task is to write, fix or speed up Playwright tests, even one quick test or a flaky one" answers 'when' with concrete trigger phrases, and the technique list clearly answers 'what' — matching anchor 5; anchor 4 would require the 'when' to be less explicit.

5 / 5

Trigger Term Quality

Natural phrases users would say ("write", "fix", "speed up", "even one quick test or a flaky one") are well covered, but common synonyms such as "E2E", "end-to-end", or "browser tests" are missing, so it falls short of anchor 5's comprehensive synonym coverage without being merely partial.

4 / 5

Distinctiveness Conflict Risk

The description is anchored to a single named tool (Playwright) with distinct triggers ("flaky one", "waitForTimeout", "traces, sharding"), giving it a clear niche with minimal conflict risk against generic testing skills.

5 / 5

Total

19

/

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.

Reviewed

On this page