agent-browser

Use the host-side `agent-browser` CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-3

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

The body is a model of lean, actionable reference material: executable commands, clear sequencing with validation checkpoints, and tidy sections with no filler. No substantive weaknesses to address.

Dimension	Reasoning	Score
Conciseness	Lean and command-driven with terse bullets; it assumes Claude's competence and never explains concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands (open, wait, snapshot, click @e1, fill, record, screenshot --screenshot-dir) with no pseudocode gaps.	3 / 3
Workflow Clarity	The Core flow is a clear sequenced 3-command path with explicit validation checkpoints (wait --load networkidle, re-snapshot after DOM changes); no destructive/batch feedback-loop cap applies.	3 / 3
Progressive Disclosure	A compact, single-purpose, self-contained skill (no bundle files exist) with well-organized sections and no content that needs splitting out, satisfying the simple-skill allowance.	3 / 3
	Total	12 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 specific, distinctive description that clearly states the skill's capabilities, but it omits an explicit 'when to use' trigger clause, which caps completeness at 2. Adding a Use-when clause would round it out.

Suggestions

Add an explicit trigger clause such as 'Use when verification needs a real browser after booting the app from the sandbox' to the description so completeness can reach 3.

Consider including a couple of plain-language trigger variants (e.g. 'browser checks', 'page load test') alongside the technical terms to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs' — rather than naming only a domain.	3 / 3
Completeness	Clearly states what the skill does but lacks a 'Use when...' or equivalent explicit trigger clause, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Natural terms a user would say ('browser smoke tests', 'screenshots', 'snapshots', 'UI validation') are well covered, beyond just a few relevant keywords.	3 / 3
Distinctiveness Conflict Risk	The 'host-side agent-browser CLI against forwarded localhost URLs' framing carves a clear niche unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 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: superagent-ai/grok-cli
Path: .agents/skills/agent-browser/SKILL.md
Commit: fb97af8

Reviewed: ~1 month 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.