CtrlK
BlogDocsLog inGet started
Tessl Logo

playwright-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, extract information from web pages, mock network requests, manage browser sessions, or generate test code.

67

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body is highly actionable with concrete executable commands and useful golden rules, but it repeats some content and lacks validation checkpoints. Its main weakness is progressive disclosure: the Guide Index references nine bundle files that are not present in the skill bundle.

Suggestions

Add explicit validation/verification checkpoints to risky workflows — e.g. after state-load, verify login was skipped; after route mocking, confirm the intercepted request returned the expected response.

Provide the nine referenced Guide Index .md files (core-commands.md, test-generation.md, screenshots-and-media.md, tracing-and-debugging.md, request-mocking.md, running-custom-code.md, storage-and-auth.md, session-management.md, device-emulation.md, advanced-workflows.md), or remove links to files that do not exist.

Tighten overlap between the Quick Start examples and the Command Reference to reduce redundancy and save context tokens.

DimensionReasoningScore

Conciseness

Mostly efficient with tight command blocks, but the full command reference repeats commands already shown in Quick Start and could be tightened; no over-explanation of concepts Claude knows.

2 / 3

Actionability

Commands are concrete, executable, and copy-paste ready (e.g. 'playwright-cli fill e5 "search query"', 'state-save auth.json'), with real argument examples rather than pseudocode.

3 / 3

Workflow Clarity

Golden Rules sequence core actions (snapshot first, fill vs click, trace before debugging) but there are no explicit validation checkpoints or error-recovery feedback loops for risky/batch operations like route mocking or state deletion.

2 / 3

Progressive Disclosure

The Guide Index links to nine .md files (core-commands.md, test-generation.md, etc.) but none of these bundle files exist in the skill directory, so the signaled references point to missing material.

1 / 3

Total

8

/

12

Passed

Description

100%

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

The description is specific, complete, and uses natural trigger terms with an explicit 'Use when' clause. It is well scoped to browser automation with low conflict risk, though it leans slightly long.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'web testing, form filling, screenshots, and data extraction', plus 'mock network requests', 'manage browser sessions', 'generate test code' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicit 'what' (automates browser interactions for testing/forms/screenshots/extraction) and explicit 'when' via the 'Use when the user needs to...' clause, satisfying both halves.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered — 'navigate websites', 'fill forms', 'take screenshots', 'test web applications', 'extract information' — the terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Scoped to playwright-cli browser automation with distinct triggers unlikely to overlap with non-browser skills, occupying a clear niche.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 10 missing

Warning

Total

15

/

16

Passed

Repository
zebbern/claude-code-guide
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.