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.

4.09x

Quality

89%

Does it follow best practices?

Impact

86%

4.09x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Quality

Content

86%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 content is highly actionable and well-structured with a clear workflow and a proper one-level reference split. The main improvements are removing a duplicated install block and making post-interaction validation checkpoints more explicit.

Suggestions

Remove the duplicated 'npm install -g @playwright/cli@latest' block (it appears in both the prerequisite check and the quick-start alternative) and consolidate the snapshot guidance into one section to tighten conciseness.

Add an explicit validation checkpoint after interactions (e.g., 'after click/fill, snapshot to confirm the expected element changed') so the workflow has a clear per-step verify step rather than only a failure-triggered re-snapshot.

Consider surfacing 'Playwright' as a trigger word in the description and adding common synonyms (e.g., 'scrape', 'click') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean imperative prose with executable blocks and no background padding, but the global-install block is duplicated (prerequisite and quick-start sections) and the snapshot rule is restated three times, fitting the score-4 'minor instances that could be trimmed' anchor rather than score 5.	4 / 5
Actionability	Commands are fully executable and copy-paste ready ('command -v npx', 'export PWCLI=...', '"$PWCLI" open ...'), and form-fill, trace, and multi-tab examples cover the common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	A numbered 5-step core workflow and a re-snapshot-on-failure feedback loop are present, but there is no explicit per-step success-verification checkpoint or checklist, placing it at score 4 ('most checkpoints present; minor validation gaps') rather than score 5.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview that offloads detail to two clearly signaled, one-level-deep references (references/cli.md and references/workflows.md, both verified present), matching the score-5 'well-signaled one-level-deep references' anchor.	5 / 5
	Total	18 / 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.

The description is strong: it leads with an explicit 'Use when' trigger, lists six concrete capabilities, and occupies a distinct niche. Its only notable gap is trigger-term breadth — it lacks the Playwright brand word and synonym/extension coverage that would push it to a perfect score.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete actions ('navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging'), matching the comprehensive-coverage anchor rather than the score-4 'minor gaps' anchor.	5 / 5
Completeness	It opens with an explicit 'Use when the task requires...' trigger clause and states a concrete 'what' (terminal browser automation via playwright-cli or the wrapper), matching the score-5 anchor that requires both an explicit when and concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms like 'automating a real browser', 'form filling', and 'screenshots' give good coverage, but the Playwright brand word is not surfaced as a user trigger and no synonyms or file extensions are included, so it falls short of the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Terminal automation of a real browser via a specific CLI is a clear niche with minimal overlap risk, fitting the score-5 'clear niche with distinct triggers' anchor rather than the score-4 'minor overlap risk' anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/playwright/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.