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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clear core workflow and good reference structure, but it is somewhat verbose and references template files that are absent from the bundle, weakening navigation reliability.

Suggestions

Tighten the body: consolidate the duplicated command listings across 'Essential Commands' and 'Common Patterns', and trim the engine/timeout commentary to keep the overview lean.

Remove or actually provide the referenced templates/ files (form-automation.sh, authenticated-session.sh, capture-workflow.sh) so navigation links resolve to real bundle content.

Move the dense flag reference tables (e.g. download-path, diff variants) into references/commands.md, leaving the SKILL.md body as a concise overview.

Dimension	Reasoning	Score
Conciseness	Largely efficient and code-dense, but the body is long with repeated inline command listings and commentary (e.g. engine/timeout sections) that pads the overview beyond the lean ideal.	2 / 3
Actionability	Commands are concrete, executable, and copy-paste ready throughout — e.g. 'agent-browser open <url>', 'agent-browser snapshot -i', with real flags and example values.	3 / 3
Workflow Clarity	The core workflow is explicitly sequenced (Navigate, Snapshot, Interact, Re-snapshot) with validation checkpoints like re-snapshotting after navigation and auth-safety gating before entering credentials.	3 / 3
Progressive Disclosure	The body lists real one-level-deep references (commands.md, snapshot-refs.md, etc.), but also advertises templates/form-automation.sh and other templates/ files that do not exist in the bundle, breaking the navigation promises.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 concrete, third-person, and answers both what the skill does and when to use it, with natural trigger phrases. It is a strong, well-scoped trigger description.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps' — and a programmatic interaction purpose, all explicit.	3 / 3
Completeness	Explicitly answers what ('Browser automation CLI for AI agents...') and when ('Use when the user needs to interact with websites... Triggers include...'), satisfying both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	Quotes natural phrasings a user would say ('open a website', 'fill out a form', 'take a screenshot', 'scrape data from a page', 'login to a site') with good variation coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped to a browser automation CLI with distinct triggers; the domain and use cases are specific enough to avoid conflicting with unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (542 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: ZHangZHengEric/Sage
Path: app/skills/agent-browser/SKILL.md
Commit: ce79d60

Reviewed: about 18 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.