web-browser

Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.

Quality

85%

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

86%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 well-structured, highly actionable CLI reference with executable commands throughout and clean one-level-deep script references. The only weakness is minor repetition of profile/headless guidance that slightly dents token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is a lean command reference that assumes competence and mostly avoids concept padding, but profile/headless behavior is restated across the Start and Stop sections and could be tightened, keeping it just below the lean anchor 5.	4 / 5
Actionability	Every section gives copy-paste-ready executable bash commands with concrete arguments covering the common cases (navigate, eval, screenshot, emulate), matching the fully-executable anchor.	5 / 5
Workflow Clarity	The 'Quick Mobile Debug Flow' and the 'switch to a visible browser' steps provide clear sequences, and no destructive/batch operations require validation; minor checkpoint and error-recovery detail is missing, so it sits below anchor 5.	4 / 5
Progressive Disclosure	SKILL.md is an overview pointing to one-level-deep, real script files (all referenced ./scripts/*.js exist), well sectioned with no nested references, matching the clear-overview anchor.	5 / 5
	Total	18 / 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, third-person description that concretely lists capabilities and gives an explicit use-when trigger. Its main weakness is trigger breadth — a single 'when' phrase and a few missing natural synonyms keep it just short of top marks.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — 'navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity' — giving comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Both 'what' (the enumerated actions) and 'when' ('Use when an agent needs a real browser') are explicit, but the single trigger phrase could be expanded with more concrete scenarios to reach the clearly-comprehensive anchor 5.	4 / 5
Trigger Term Quality	Natural terms like 'web pages', 'real browser', 'screenshots', and 'headless Chrome' are present, but common synonyms users might say ('browse', 'scrape', 'open a page', 'Playwright/Selenium') are missing, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The Chrome/Chromium + CDP + headless niche is specific and distinct, with triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.	5 / 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: mitsuhiko/agent-stuff
Path: skills/web-browser/SKILL.md
Commit: 122e299

Reviewed: 3 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.