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

92%

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

85%

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

A well-structured, code-first skill: executable commands, a clear snapshot-driven workflow with an error-recovery loop, and real one-level references. The only weakness is minor verbosity in the prerequisite install steps and the skill-path environment explanation.

Suggestions

Tighten the prerequisite section: the verbatim Node install block and comments could be reduced to a one-line npx check plus a brief "install Node.js if missing" pointer, keeping the global-install detail only where it is first introduced.

Trim the skill-path environment explanation ("production default: app userData/SKILLs, macOS usually ~/Library/...") to the essential export lines, since the fallback default is already encoded in the export itself.

Consider consolidating the two mentions of the optional global install ("npm install -g @playwright/mcp@latest") into a single place to avoid repeating the same guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and code-first without explaining concepts Claude already knows, but the verbatim prerequisite install block and the skill-path environment paragraph ("production default: app userData/SKILLs, macOS usually ~/Library/...") carry detail that could be tightened, matching the score-2 anchor of efficient-but-trimmable.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout ("$PWCLI open", "snapshot", "fill e1", "tracing-start") with multiple complete worked examples, and explicitly explains the placeholder ref convention so examples are unambiguous.	3 / 3
Workflow Clarity	The 5-step core workflow is clearly sequenced, the "When to snapshot again" section gives explicit re-checkpoint triggers, and the stale-ref rule ("When a command fails due to a missing ref, snapshot again") is a concrete error-recovery feedback loop.	3 / 3
Progressive Disclosure	SKILL.md stays an overview and signals one-level-deep references ("CLI command reference: references/cli.md", "Practical workflows and troubleshooting: references/workflows.md") that exist as real files, with content appropriately split and easy to navigate.	3 / 3
	Total	11 / 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 strong: it opens with an explicit "Use when" trigger, enumerates concrete browser-automation actions, and carves out a distinct CLI-based niche. It reads like the rubric's good examples with no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging" — matching the score-3 anchor that enumerates specific capabilities rather than vague language.	3 / 3
Completeness	Explicitly answers both what (browser automation via playwright-cli/wrapper with named actions) and when ("Use when the task requires automating a real browser from the terminal"), satisfying the explicit-trigger requirement that would otherwise cap at 2.	3 / 3
Trigger Term Quality	Uses natural terms a user would actually say ("automating a real browser", "form filling", "screenshots", "data extraction", "UI-flow debugging") with good coverage of common variations, not technical jargon.	3 / 3
Distinctiveness Conflict Risk	The "from the terminal via playwright-cli" niche with snapshot/ref/trace actions is a clear, distinct trigger unlikely to fire for unrelated skills; it does not stop at the generic level of the score-2 anchor.	3 / 3
	Total	12 / 12 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: 2921c1e

Reviewed: about 11 hours 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.