agent-browser

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.

Quality

88%

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

Quality

Content

77%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.

A highly actionable, well-organized command reference with clear workflows and copy-paste examples. Its main weakness is length and a duplicated debugging block, plus a missed opportunity to offload the exhaustive command listing into a separate reference file.

Suggestions

De-duplicate the Debugging section, which repeats 'open example.com --headed', 'console', 'errors', and 'record start' already documented earlier — keep one canonical listing.

Move the exhaustive per-category command tables into a references/REFERENCE.md and keep SKILL.md as overview + Quick start + Core workflow + one or two examples, leaving a clearly signaled one-level link to the reference.

Verify the ../../docs/e2e-testing.md and ../../docs/e2e-testing-wsl.md links resolve from the bundle, or move that setup guidance into a bundle reference file so navigation stays one level deep.

Dimension	Reasoning	Score
Conciseness	Each line is a lean command-plus-comment with no concept-explanation fluff, but the body runs ~270 lines and the Debugging section duplicates several commands (open --headed, console, errors, record start) already shown nearby, so it could be tightened.	2 / 3
Actionability	Commands are fully executable and copy-paste ready, reinforced by concrete worked examples (form submission, authentication with saved state) — matching the top anchor.	3 / 3
Workflow Clarity	The Core workflow is explicitly sequenced (navigate, snapshot, interact, re-snapshot) and examples include checkpoints like 'wait --load networkidle' followed by 'snapshot -i # Check result', providing a clear feedback loop.	3 / 3
Progressive Disclosure	No bundle files exist; the entire command reference lives inline in SKILL.md as a ~270-line monolith that could be split into a separate REFERENCE.md, and the only doc links point outside the bundle to ../../docs/* rather than real bundle references.	2 / 3
	Total	10 / 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.

A strong, third-person description that names concrete capabilities and pairs them with an explicit, natural-language 'Use when' trigger clause. It is concise, complete, and unlikely to conflict with sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'web testing, form filling, screenshots, and data extraction' — rather than vague language, matching the top anchor.	3 / 3
Completeness	Clearly answers both what it does (first sentence) and when to use it via an explicit 'Use when the user needs to...' trigger clause, satisfying the top anchor.	3 / 3
Trigger Term Quality	The 'Use when' clause covers natural terms users would actually say — 'navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages' — giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear browser-automation niche with distinct triggers unlikely to overlap with other skills; it would not fire for non-browser tasks.	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: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: coleam00/Archon
Path: .claude/skills/agent-browser/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.