playwright-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

4.42x

Quality

93%

Does it follow best practices?

Impact

84%

4.42x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

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

Quality

Content

87%Weight 40%Scale 1-3

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 lean, highly actionable command reference with good progressive disclosure through verified reference files. Its main weakness is workflow clarity: example workflows rely on implicit snapshot verification and omit explicit validation/feedback steps for destructive operations.

Suggestions

Add explicit validation checkpoints to example workflows — e.g., after fill/click, snapshot and confirm the expected element state before proceeding.

For destructive/batch commands (delete-data, kill-all, cookie-clear, localstorage-clear), add a brief verify-then-confirm step or warning so Claude checks state before irreversible actions.

Add one short error-recovery feedback loop (e.g., if a click fails or a ref is stale, re-snapshot and retry) to demonstrate the validate-fix-retry pattern.

Dimension	Reasoning	Score
Conciseness	The body is a lean command catalog with minimal prose and no explanations of concepts Claude already knows; nearly every token is an executable command or a brief, useful comment, matching the lean/efficient anchor.	3 / 3
Actionability	Almost entirely concrete, executable commands with real flags, plus complete copy-paste example workflows (form submission, multi-tab, debugging), matching the fully-executable anchor rather than the pseudocode anchor 2.	3 / 3
Workflow Clarity	Examples show clear sequences with snapshot-based verification, but there are no explicit validation checkpoints or error-recovery feedback loops, and destructive operations (delete-data, kill-all, cookie-clear) lack verification steps — capping clarity at 2 per the destructive-ops guideline.	2 / 3
Progressive Disclosure	The "Specific tasks" section provides seven well-signaled one-level-deep markdown links, all pointing to real verified files in references/, with the main body acting as a clear overview — matching the clear-overview anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, uses natural trigger terms, answers both what and when explicitly, and occupies a distinct browser-automation niche. It is a strong, well-formed skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "web testing, form filling, screenshots, and data extraction" and "navigate websites... fill forms, take screenshots, test web applications" — matching the anchor for several specific concrete actions, not the partial anchor 2.	3 / 3
Completeness	Explicitly states both what it does ("Automates browser interactions...") and when to use it via an explicit "Use when the user needs to..." clause, satisfying the what-AND-when anchor.	3 / 3
Trigger Term Quality	Uses natural user phrasing ("fill forms", "take screenshots", "navigate websites", "test web applications") that a user would actually say, giving good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Targets a clear browser-automation niche with web-specific triggers unlikely to fire for unrelated skills; written in third person with no voice penalty.	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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: coleam00/Archon
Path: .claude/skills/playwright-cli/SKILL.md
Commit: ace0a41

Reviewed: 8 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.