agent-browser

Browser automation for testing and verification. Use when you need to interact with web UIs, verify visual changes, fill forms, or capture screenshots.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%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.

An excellent, token-efficient CLI skill body: concrete executable commands, a clearly sequenced core workflow with a snapshot-first checkpoint, and well-organized sections requiring no external references. No meaningful weaknesses to address.

Dimension	Reasoning	Score
Conciseness	The body is a lean, command-oriented reference with almost no prose padding and no explanation of concepts Claude already knows; inline flag comments like '# -i = interactive elements only' earn their tokens, matching the anchor-3 'every token earns its place'.	3 / 3
Actionability	It is packed with concrete, executable, copy-paste-ready commands (open, snapshot, click, fill, screenshot) with real flags and arguments, matching the anchor-3 'fully executable; copy-paste ready'.	3 / 3
Workflow Clarity	The Core Workflow gives a clear numbered sequence (open -> snapshot -> interact -> screenshot) and the 'Always snapshot first' tip acts as an explicit checkpoint; browser automation is not a destructive/batch operation, so the missing-validation cap does not apply, reaching anchor-3.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed for this self-contained CLI reference; content is split into well-organized, clearly labeled sections (When to Use, Core Workflow, Common Patterns, Sessions, Debugging, Tips) giving easy navigation, satisfying the anchor-3 'clear overview with easy navigation'.	3 / 3
	Total	12 / 12 Passed

Description

90%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.

A strong, concise description that clearly states capability and explicit triggers with good natural keyword coverage. Its only weakness is second-person voice ('you need to'), which the rubric penalizes on specificity.

Suggestions

Rewrite in third person to avoid the voice penalty, e.g. 'Browser automation for testing and verification. Use when interacting with web UIs, verifying visual changes, filling forms, or capturing screenshots.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('interact with web UIs, verify visual changes, fill forms, or capture screenshots'), which is anchor-3 material, but the second-person phrasing 'Use when you need to' triggers the rubric's voice penalty reducing specificity by one.	2 / 3
Completeness	Explicitly answers both what ('Browser automation for testing and verification') and when ('Use when you need to...'), satisfying the anchor-3 requirement for an explicit trigger clause.	3 / 3
Trigger Term Quality	Natural trigger terms a user would actually say are well covered: 'web UIs, verify visual changes, fill forms, capture screenshots', matching the anchor-3 example of good coverage.	3 / 3
Distinctiveness Conflict Risk	Browser automation is a clear niche with distinct, specific triggers unlikely to collide with other skills, matching the anchor-3 'clear niche with distinct triggers'.	3 / 3
	Total	11 / 12 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: emdash-cms/emdash
Path: skills/agent-browser/SKILL.md
Commit: 53dbf22

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.