playwright

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

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.

A well-structured, CLI-first skill body: executable commands throughout, a clear snapshot-driven workflow with stale-ref recovery, and appropriate offloading of the command reference and troubleshooting to one-level-deep reference files. The only weakness is minor duplication of the global-install instructions.

Dimension	Reasoning	Score
Conciseness	The body is command-first and lean with almost no concept explanation Claude already knows, but there is minor redundancy: the global-install block ("npm install -g @playwright/mcp@latest / playwright-cli --help") appears in both the prerequisite section and Quick start, and the snapshot-retry advice is stated twice. This is efficient with minor trim opportunities, not the fully lean anchor.	4 / 5
Actionability	Every step is a copy-paste-ready command: the npx check ("command -v npx"), path setup ("export PWCLI=..."), and full command sequences for open/snapshot/click/fill/tab/tracing. Concrete examples cover the common cases (form fill, multi-tab, tracing), matching the fully-executable anchor.	5 / 5
Workflow Clarity	The core workflow is a clear 5-step sequence with explicit checkpoints (snapshot before referencing ids, re-snapshot after navigation/DOM changes) and an explicit error-recovery feedback loop ("When a command fails due to a missing ref, snapshot again"), plus a prerequisite validation step. This matches the anchor with explicit validation and feedback loops rather than just most checkpoints.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with a clearly signaled one-level-deep reference section ("Open only what you need" → references/cli.md and references/workflows.md, both real bundle files), with the wrapper script in scripts/ and assets present. Content is appropriately split with easy navigation, matching the clear-overview anchor.	5 / 5
	Total	19 / 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 description with an explicit "Use when..." trigger, a concrete parenthetical list of capabilities, and clear tool identification. Keyword coverage is good but misses a few natural synonyms (e.g., "scraping", "browser automation").

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging" — which comprehensively covers the terminal browser-automation domain, matching the anchor for multiple specific concrete actions. It is not a 4 because the coverage of the domain's common cases is complete rather than having notable gaps.	5 / 5
Completeness	It explicitly answers both: what it does ("automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script") and when to use it ("Use when the task requires...") with concrete trigger phrases. This matches the anchor that clearly and explicitly answers both what and when.	5 / 5
Trigger Term Quality	Good natural-term coverage: "automating a real browser", "navigation", "form filling", "screenshots", "data extraction", "UI-flow debugging", plus the tool name "playwright-cli". It is not a 5 because common user synonyms like "scraping", "browser automation", or "web page" phrasing are missing; it is above a 3 because most phrases a user would naturally say are present.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and pinned to "playwright-cli or the bundled wrapper script" from the terminal, making it mostly distinct with minor overlap risk against generic web-scraping or screenshot skills triggered by "data extraction" or "screenshots". It is not a 5 because those broad terms could pull in closely related skills; it is well above a 3 because the terminal-CLI framing is unambiguous.	4 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/playwright/SKILL.md
Commit: 791a352

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.