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.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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.

The body is a highly actionable, token-efficient command reference with sensible golden rules and a well-organized guide index. Its one serious defect is that the entire referenced bundle is missing: all 10 linked guides are absent from the skill directory, leaving dead links and duplicated inline reference material.

Suggestions

Ship the 10 referenced guide 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 the Guide Index if they will not exist.

Move the bulk of the inline Command Reference into core-commands.md (and storage-and-auth.md for the cookie/storage commands), keeping only the most common commands in SKILL.md to eliminate duplication with the linked guides.

Add explicit verification steps to key workflows, e.g. re-run snapshot after fill/click to confirm the page state changed, or check console/network output before declaring a debugging step complete.

Dimension	Reasoning	Score
Conciseness	The body is a dense, one-line-per-command cheat sheet with no explanations of concepts Claude already knows — efficient but not perfectly lean. Minor duplication (snapshot/fill/click appear in both Quick Start and Command Reference, and Golden Rules restate command facts) keeps it at anchor 4 rather than 5.	4 / 5
Actionability	Every entry is an executable, copy-paste-ready command ("playwright-cli open https://playwright.dev", "playwright-cli fill e5 \"search query\"", "playwright-cli screenshot --filename=checkout-step3.png"), and the Quick Start covers the common case end-to-end. Fully concrete with no pseudocode — anchor 5.	5 / 5
Workflow Clarity	Quick Start gives a clear sequence (open → snapshot → interact → screenshot → close) and Golden Rules encode checkpoints ("Always snapshot first — never guess ref numbers", "tracing-start before the failing step, not after"). It stays at 4 rather than 5 because there are no explicit verify-after-action or error-recovery steps, though the operations are interactive rather than destructive batch jobs.	4 / 5
Progressive Disclosure	The Guide Index is well organized and clearly signaled, but the bundle contains none of the 10 linked guide files (core-commands.md, test-generation.md, storage-and-auth.md, etc.) — every reference is dead, so navigation cannot resolve. Additionally, ~130 lines of inline command reference duplicate what the linked core-commands.md should hold. Structure exists and signaling is clear (above 2), but broken references and inlined reference content keep it below 4.	3 / 5
	Total	16 / 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.

An exemplary description: third-person, concrete about both capabilities and trigger situations, tool-anchored, and free of fluff. The only weakness is a few missing natural synonyms (e.g., "scrape", "automate the browser", "log in") that would broaden trigger matching.

Dimension	Reasoning	Score
Specificity	"Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli" plus the enumerated actions (navigate, interact, fill forms, mock network requests, manage browser sessions, generate test code) lists multiple concrete actions with comprehensive coverage, in third-person voice. It matches the anchor-5 example and has no coverage gaps that would drop it to 4.	5 / 5
Completeness	Both parts are explicit: a clear what ("Automates browser interactions for web testing, form filling, screenshots, and data extraction") and a concrete when ("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"), matching the anchor-5 example exactly.	5 / 5
Trigger Term Quality	Strong natural phrases users would say — "navigate websites", "fill forms", "take screenshots", "test web applications", "extract information from web pages" — but common synonyms such as "scrape", "automate the browser", or "log in" are absent, placing it at anchor 4 ("good keyword coverage; a few natural terms missing") rather than 5.	4 / 5
Distinctiveness Conflict Risk	It names the specific tool ("using playwright-cli") and a clear browser-automation niche with distinct triggers, so conflict with other skills is minimal. It is not below 5 because the tool name anchors it more precisely than the anchor-4 case of overlapping file-type skills.	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: 10 missing	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/playwright/playwright-cli/SKILL.md
Commit: a2e6ee3

Reviewed: 2 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.