agent-browser

Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.

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

92%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-structured CLI reference that leads with a quick-start, groups commands logically, and pairs them with worked examples. Its standout is the explicit bounded-wait guidance with recovery steps, demonstrating strong workflow discipline for a tool prone to hanging.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command tables with inline comments and no padding of concepts Claude already knows, though the bounded-wait section and several per-command comment restatements add a little that could be trimmed.	4 / 5
Actionability	Every command is concrete, copy-paste ready, and the worked form-submission and data-extraction examples cover common end-to-end cases with real refs and values.	5 / 5
Workflow Clarity	A clear numbered core workflow is followed by an explicit bounded-wait pattern with wall-clock timeout AND max-attempts, plus timeout-recovery guidance (snapshot/screenshot, report, move on) — strong validation and feedback-loop discipline.	5 / 5
Progressive Disclosure	No bundle files exist, so the single well-organized SKILL.md with clear section headers fits the under-50-lines/simple-skill exception loosely; structure is clean and navigable with no nested references.	5 / 5
	Total	19 / 20 Passed

Description

85%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, third-person description that pairs a comprehensive action list with an explicit proactive usage trigger. It is concise, concrete, and clearly answers both what and when, with only minor synonym coverage and overlap-risk gaps.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages' — giving comprehensive coverage of the browser tool's capabilities.	5 / 5
Completeness	Explicitly answers both what it does (the action list) and when to use it via the 'Use whenever a browser would be useful, not just when the user explicitly asks' clause with concrete trigger framing.	5 / 5
Trigger Term Quality	Natural user-facing terms like 'browse the web', 'research topics', 'read articles', 'fill forms', and 'take screenshots' are present, but it lacks synonym breadth and explicit file/extension-style variants for completeness.	4 / 5
Distinctiveness Conflict Risk	The browser-automation niche is fairly distinct and the proactive trigger narrows it, but the broad framing ('any task', 'whenever a browser would be useful') keeps some overlap risk with general web/research skills.	4 / 5
	Total	18 / 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: nanocoai/nanoclaw
Path: container/skills/agent-browser/SKILL.md
Commit: ad8837c

Reviewed: 4 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.