playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/playwright-cli/SKILL.md

The canonical home for this skill is playwright-cli in microsoft/playwright-cli

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 a well-structured, highly actionable CLI reference that keeps the core command set inline and offloads specialized topics to real, clearly linked reference files. Its main gap is the absence of explicit validation/error-recovery checkpoints around the destructive session and storage commands.

Suggestions

Add a short validation/checklist note near destructive commands (delete-data, kill-all, cookie-clear, localstorage-clear, sessionstorage-clear) so workflows explicitly verify state before/after.

Tighten the 'Open parameters' section or move the less-common attach/cdp variants into a reference file to reduce inline length.

Consider folding the four short Example sections into a single 'Common workflows' block to reduce repetition while preserving the copy-paste sequences.

Dimension	Reasoning	Score
Conciseness	The body is a lean CLI command reference with terse inline comments and no padding about what browsers or snapshots are, matching 'efficient; minor instances of over-explanation'; not a 5 because the Open parameters and repeated Example sections could be tightened slightly.	4 / 5
Actionability	Nearly every line is an executable copy-paste command (e.g. 'playwright-cli fill e5 "user@example.com" --submit', 'playwright-cli --raw snapshot > before.yml') and the Examples cover common cases, matching 'fully executable; copy-paste ready'.	5 / 5
Workflow Clarity	Quick start and the Example sections give clear sequences (open -> snapshot -> interact -> snapshot -> close) with the snapshot-after-action pattern acting as an implicit verification checkpoint, matching 'clear sequence with most checkpoints present'; not a 5 because explicit validation/error-recovery loops are not called out for destructive commands like delete-data, kill-all, or cookie-clear.	4 / 5
Progressive Disclosure	The 'Specific tasks' section lists nine one-level-deep references, each with a brief label and link (e.g. 'Running and Debugging Playwright tests [references/playwright-tests.md]'), and all referenced files exist in ./references/, matching 'clear overview with well-signaled one-level-deep references; easy navigation'.	5 / 5
	Total	18 / 20 Passed

Description

70%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 specific and clearly niched around Playwright browser automation with good natural trigger terms, but it omits any explicit 'Use when' trigger guidance, which caps its completeness. Adding a usage trigger clause would lift it from good to excellent.

Suggestions

Append an explicit trigger clause, e.g. 'Use when automating browser interactions, running or debugging Playwright/end-to-end tests, or mocking network requests in a browser.'

Add natural synonyms users say, such as 'end-to-end (e2e) tests', 'browser automation', and 'web scraping', to broaden trigger coverage.

Optionally enumerate a couple more concrete capabilities (e.g. request mocking, tracing, screenshots) to raise specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Automate browser interactions, test web pages and work with Playwright tests' — three named actions (automate, test, work with) tied to a concrete domain, matching the 'lists several specific actions; minor gaps' anchor; not a 5 because coverage is not comprehensive (no mention of mocking, tracing, screenshots specifics).	4 / 5
Completeness	It clearly states what ('Automate browser interactions, test web pages and work with Playwright tests') but provides no 'Use when...' clause or equivalent trigger guidance, so per the judging guideline completeness is capped at 3; not a 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	Natural phrases like 'browser interactions', 'test web pages', and 'Playwright tests' are things users would actually say, fitting 'good keyword coverage; a few natural terms missing'; not a 5 because synonyms like 'end-to-end/e2e tests', 'browser automation', or file extensions are absent.	4 / 5
Distinctiveness Conflict Risk	Naming the specific tool 'Playwright' and the narrow niche of browser test automation gives a clear niche with distinct triggers and minimal conflict risk, matching the anchor exactly; a 4 would require notable overlap with a closely related skill, which is not present.	5 / 5
	Total	16 / 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: coleam00/Archon
Path: .claude/skills/playwright-cli/SKILL.md
Commit: e237584

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.