agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Quality

92%

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

85%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 strong, action-oriented skill body with executable examples, a clear sequenced workflow, and built-in validation (re-snapshot/diff). The main weakness is progressive disclosure: the 'Ready-to-Use Templates' table references a templates/ directory that is not present in the bundle.

Suggestions

Either add the templates/ directory with form-automation.sh, authenticated-session.sh, and capture-workflow.sh, or remove the 'Ready-to-Use Templates' section to avoid dangling references.

Tighten overlap between 'Essential Commands' and 'Common Patterns' (e.g., form/auth/session commands appear twice) to reduce redundancy and token cost.

Consider moving the verbose 'JavaScript Evaluation' rules-of-thumb explanation into references/ since commands.md can absorb it, keeping the body to the --stdin/-b pattern and a single example.

Dimension	Reasoning	Score
Conciseness	Mostly lean and command-dense with minimal conceptual padding, but the 'Essential Commands' and 'Common Patterns' sections overlap (form/auth/session patterns repeat commands) and a few explanatory paragraphs ('Why this matters', rules of thumb) could be trimmed further.	4 / 5
Actionability	Fully executable copy-paste-ready bash commands throughout, with concrete examples covering the common cases (navigate, snapshot, fill, click, wait, screenshot, eval) plus annotated output examples showing real refs.	5 / 5
Workflow Clarity	Core Workflow is explicitly sequenced (Navigate -> Snapshot -> Interact -> Re-snapshot) with a validation/checkpoint pattern (re-snapshot after navigation, diff snapshot to verify changes) and the 'Ref Lifecycle' section codifies when to re-validate.	5 / 5
Progressive Disclosure	Good use of a one-level-deep references table pointing to real files in references/, but the body also advertises a templates/ directory (3 .sh templates referenced) that does not exist in the bundle, leaving those links dangling.	3 / 5
	Total	17 / 20 Passed

Description

100%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.

An exemplary description: concise, third-person, lists concrete actions, and provides an explicit 'Use when' clause with natural trigger phrases a user would actually say. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ('navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps') with comprehensive coverage of browser automation tasks.	5 / 5
Completeness	Explicitly answers both 'what' (browser automation CLI for AI agents with enumerated actions) and 'when' ('Use when the user needs to interact with websites' plus a dedicated 'Triggers include' clause).	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say ('open a website', 'fill out a form', 'click a button', 'take a screenshot', 'scrape data from a page', 'login to a site', 'automate browser actions').	5 / 5
Distinctiveness Conflict Risk	Clearly scoped to browser automation via a specific CLI tool (agent-browser) with distinct web-interaction triggers, minimal overlap risk with unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: Jamie-BitFlight/claude_skills
Path: .agents/skills/agent-browser/SKILL.md
Commit: 4e1e73b

Reviewed: ~14 hours 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.