dev-browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Quality

91%

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

82%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 skill body with executable examples and a clear workflow loop. Minor conciseness redundancies and an inlined API reference keep it just short of top marks.

Suggestions

De-duplicate the `cd "$CODEX_HOME/skills/dev-browser"` preamble — state the working-directory requirement once and reference it, rather than repeating it in Setup, Writing Scripts, and Error Recovery.

Tighten the "No TypeScript in Browser Context" section to a single short example plus a one-line rule, instead of full correct and wrong code blocks.

Move the bulk of the Client API / ARIA snapshot reference into a separate references file (e.g. references/api.md) and link to it, keeping only a minimal quick-start example inline to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable examples and no padding of basic concepts, but the repeated `cd "$CODEX_HOME/skills/dev-browser"` preamble and the dual correct/wrong TypeScript block are minor instances that could be trimmed. Not a 5 because those redundancies keep it from being fully lean.	4 / 5
Actionability	Provides copy-paste-ready executable heredocs with real imports, concrete Client API method signatures, and examples covering navigation, screenshots, ARIA snapshots, and error recovery.	5 / 5
Workflow Clarity	The Workflow Loop (write → run → evaluate → decide → repeat) plus "Wait for the Ready message" and an Error Recovery section give a clear sequence with feedback loops. Not a 5 because explicit validation checkpoints before risky actions (form submission, auth) are only implicit.	4 / 5
Progressive Disclosure	Clear sectioned overview with a well-signaled one-level-deep reference to references/scraping.md (verified present). Not a 5 because the Client API and ARIA reference are inlined rather than split into a separate reference file, a minor organization gap.	4 / 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.

A strong, third-person description that clearly states both what the skill does and when to use it, with comprehensive concrete actions and natural trigger phrases. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows" — matching the comprehensive-coverage anchor; not a 4 because coverage is broad rather than having minor gaps.	5 / 5
Completeness	Explicitly states what ("Browser automation with persistent page state") and when ("Use when users ask to navigate websites... Trigger phrases include...") with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Includes natural user phrases — "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into" — giving comprehensive coverage of terms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Browser automation with persistent page state is a clear niche with distinct triggers ("go to [url]", "scrape", "take a screenshot") and minimal overlap risk with other skills.	5 / 5
	Total	20 / 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: marchatton/agent-skills
Path: .agents/skills/00-utilities/dev-browser/SKILL.md
Commit: a0eadb2

Reviewed: 5 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.