playwright-skill

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing. Do NOT use for quick page debugging or network inspection (use chrome-devtools instead).

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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.

Highly actionable with clear sequencing and validation around server detection, and good use of a separate API_REFERENCE.md for advanced content. The main weakness is conciseness: repeated script scaffolding and guidance restated across sections inflate the token budget without adding new information.

Suggestions

Consolidate the repeated browser-launch scaffolding (chromium.launch + newPage + close) into a single reusable template or helper snippet instead of restating it in every Common Patterns example.

Reduce duplication between the Tips section and the inline CRITICAL WORKFLOW guidance (e.g., detect-servers-first, headless:false, parameterize URLs) which appear nearly verbatim in both places.

Since no references/assets bundle exists, either create the referenced API_REFERENCE.md file referenced under Advanced Usage, or drop the deep-link to avoid pointing at a missing resource.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste-ready code, but the body is long and repeats similar script scaffolding across many examples (multiple near-identical browser-launch blocks), and re-explains wait-strategy and headless guidance in several places, so it could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready scripts and exact commands for the common cases (page test, login, form, broken links, responsive, screenshot with error handling), each runnable via a concrete run.js invocation.	5 / 5
Workflow Clarity	Presents a clearly numbered critical workflow with explicit ordering (detect servers first, write to /tmp, execute) and error-recovery branching for the detection step; setup and troubleshooting sections add feedback loops.	5 / 5
Progressive Disclosure	Well-organized with section headers and a one-level-deep pointer to API_REFERENCE.md for advanced material, but no references/ or assets/ bundle files exist alongside the skill, so the navigation structure is only partially realized against the actual bundle.	4 / 5
	Total	17 / 20 Passed

Description

88%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, specific description that concretely enumerates actions, gives explicit use-when triggers, and disambiguates from adjacent skills. Minor gap in covering a few synonymous trigger terms keeps it just shy of perfect on keyword breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links) plus automation capabilities, giving comprehensive coverage of browser-automation actions.	5 / 5
Completeness	Clearly answers 'what' (browser automation via Playwright) and 'when' with an explicit 'Use when...' trigger clause plus a 'Do NOT use for...' boundary, satisfying both halves with concrete triggers.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'test websites', 'automate browser interactions', 'validate web functionality', 'browser-based testing'; slightly misses common synonyms like 'scrape' or 'crawl' but covers the core natural vocabulary.	4 / 5
Distinctiveness Conflict Risk	Anchored to a distinct niche (Playwright browser automation) with explicit conflict avoidance against chrome-devtools, leaving minimal risk of triggering for the wrong skill.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(web-automation)/playwright-skill/SKILL.md
Commit: fc886b7

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.