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

83%

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

82%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.

A highly actionable, well-organized CLI reference with copy-paste commands and a clear core workflow. The main gaps are minor redundancy in the intro/options table and the absence of explicit validation feedback loops and external reference splitting.

Suggestions

Remove or condense the opening sentence that repeats the frontmatter description, and prune option flags already demonstrated inline from the Useful Options table to tighten conciseness.

Add an explicit validation feedback loop for form/interaction workflows (e.g., snapshot after clicking Save to confirm the expected state, and re-snapshot and retry if it differs).

Consider moving the full option reference and detailed Common Patterns into a separate reference file linked from the body, leaving SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean with tight code blocks and no concept over-explanation, but the opening line partially repeats the frontmatter description and the "Useful Options" table re-covers flags already shown in the workflow, so it is not quite the every-token-earns-its-place 5 anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (open, snapshot, click, fill, screenshot) plus worked common-case examples like Form Verification and Find by Role/Label, matching the top anchor.	5 / 5
Workflow Clarity	A clear numbered Core Workflow (open → snapshot → interact → screenshot) with a Debugging section for error recovery and the image-size check as a validation step, but lacks explicit validate→fix→retry feedback loops so it stays below the 5 anchor.	4 / 5
Progressive Disclosure	Well-organized into clear sections (When to Use, Core Workflow, Common Patterns, Sessions, Options, Debugging, Tips) with no nested references, but at ~140 lines with no external file split it exceeds the simple-skill <50-line exception and has minor organization gaps versus the ideally-split 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

83%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.

A strong, well-structured description that clearly states both capability and trigger conditions with concrete actions. It is comprehensive on completeness but leaves a little synonym coverage and distinctiveness on the table.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("interact with web UIs, verify visual changes, fill forms, or capture screenshots") with only minor coverage gaps; "interact with web UIs" is somewhat generic compared to the others, keeping it just below the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both what ("Browser automation for testing and verification") and when ("Use when you need to interact with web UIs, verify visual changes, fill forms, or capture screenshots") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("web UIs", "visual changes", "fill forms", "screenshots", "browser automation") but misses common synonyms like "web pages", "frontend", or "clicks", so it falls short of the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	"Browser automation" is a clear niche with distinct triggers, but broad terms like "fill forms" and "testing and verification" create minor overlap risk with generic frontend-testing or screenshot skills rather than the minimal-conflict 5 anchor.	4 / 5
	Total	17 / 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: emdash-cms/emdash
Path: skills/agent-browser/SKILL.md
Commit: 1717d31

Reviewed: 2 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.