CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

playwright-skill

Write and run scoped Playwright browser automation, responsive checks, screenshots and login-flow tests with a local Node executor.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/aasb-aas-accessibility-inclusive-ux/skills/playwright-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 highly actionable skill with concrete commands, complete code examples, and a clearly sequenced workflow. Its main problems are redundancy — an entire safety paragraph and a How It Works section duplicated verbatim, plus tips repeating earlier rules — and unverifiable external references.

Suggestions

Remove the verbatim-duplicated "Scope and data boundaries" paragraph and the second "How It Works" section, consolidating each into a single location.

Trim the Tips section and generic "When to Use" boilerplate, which restate rules already given in CRITICAL WORKFLOW without adding new information.

Make every code example follow the skill's own rules (parameterize URLs in the broken-links and error-handling examples; show imports in the inline example) and ensure API_REFERENCE.md and lib/helpers.js actually ship alongside SKILL.md.

DimensionReasoningScore

Conciseness

The "Scope and data boundaries" paragraph appears verbatim twice, "How It Works" is duplicated, the Tips section restates the CRITICAL WORKFLOW rules, and "When to Use" is contentless boilerplate — several padded/duplicated sections, though it avoids explaining concepts Claude already knows.

2 / 5

Actionability

Provides copy-paste-ready bash commands, a parameterized execution pattern, and seven complete JavaScript examples covering common cases; minor gaps remain since two examples hardcode localhost:3000 (contradicting the skill's own parameterization rule) and the inline example omits imports.

4 / 5

Workflow Clarity

The CRITICAL WORKFLOW and Execution Pattern give a clear ordered sequence with explicit decision points (one/multiple/no servers), first-time setup, and a troubleshooting section; verification exists in code (waitForURL, waitForSelector) but the workflow itself lacks an explicit validate-then-proceed checkpoint.

4 / 5

Progressive Disclosure

Advanced material is offloaded via a well-signaled, one-level-deep reference ("see [API_REFERENCE.md](API_REFERENCE.md)" with a contents list, plus lib/helpers.js), but the referenced files are not present in the bundle to verify, and the ~470-line body still inlines content (seven full examples, duplicated sections) that could be split out.

4 / 5

Total

14

/

20

Passed

Description

66%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 specific, third-person description with strong domain keywords and several concrete actions. Its main weakness is the complete absence of "when to use" trigger guidance, which caps completeness and limits discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to automate, test, or screenshot web pages with Playwright, check responsive layouts, or verify login flows."

Include common synonyms users say for this domain — "e2e/end-to-end tests", "browser testing", "UI testing" — to broaden trigger coverage.

Mention form-filling and link-checking capabilities in the description so it reflects the skill's actual coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — "browser automation, responsive checks, screenshots and login-flow tests" with "a local Node executor" — but omits body-covered capabilities like form filling, link checking, and custom headers, so coverage has minor gaps rather than being comprehensive.

4 / 5

Completeness

The "what" is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3; it is not score 2 because the "what" is specific rather than vague.

3 / 5

Trigger Term Quality

Includes natural terms users would say — "Playwright", "browser automation", "screenshots", "login-flow", "responsive checks" — but misses common variations like "e2e", "end-to-end tests", "UI testing", or "web testing".

4 / 5

Distinctiveness Conflict Risk

"Playwright" plus "local Node executor" carves a clear niche, but the broader phrasing (browser automation, screenshots, login tests) creates minor overlap risk with closely related browser-testing skills, matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 1 possibly missing (API_REFERENCE.md)

Warning

Total

14

/

16

Passed

Repository

sickn33/agentic-awesome-skills

Path

plugins/aasb-aas-accessibility-inclusive-ux/skills/playwright-skill/SKILL.md

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.