agent-browser

CLI-based browser automation with persistent page state using ref-based element interaction. Use when users ask to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Quality

83%

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

78%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-sectioned command reference with executable examples and clear core workflow checkpoints. Its main weakness is progressive disclosure: the large inlined command catalog would benefit from being split into a separate reference file, and the Quick Start/Core Workflow redundancy could be trimmed.

Suggestions

Move the bulk per-command reference (Navigation, Interactions, Get Information, Browser Settings, Cookies, Network, etc.) into a separate references/REFERENCE.md and keep SKILL.md as a concise overview pointing to it, improving progressive disclosure.

Remove the redundancy between the Quick Start, Core Workflow, and Commands sections so each command appears in one canonical place.

Add an explicit error-recovery note to the Core Workflow (e.g. 'if a ref is stale or not found, re-snapshot before retrying') to lift workflow clarity toward anchor 5.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and every line is actionable command syntax, but the Quick Start/Core Workflow sections restate commands shown later and the ~265-line catalog is longer than necessary, fitting anchor 4 rather than 5.	4 / 5
Actionability	Commands are fully executable and copy-paste ready throughout, and worked examples (form submission, authentication with saved state) cover the common cases, matching anchor 5.	5 / 5
Workflow Clarity	The Core Workflow gives a clear 4-step sequence with a re-snapshot checkpoint, and examples include validation via 'wait --load networkidle' and re-snapshotting results, but there is no explicit error-recovery branching, placing it at anchor 4.	4 / 5
Progressive Disclosure	No bundle files exist and the entire command catalog is inlined in one ~265-line file; section headers give some structure, but bulk reference content that belongs in a separate REFERENCE.md is inlined and no external references are signaled, fitting anchor 3 (the under-50-line simple-skill exception does not apply).	3 / 5
	Total	16 / 20 Passed

Description

88%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 description that clearly states what the skill does and when to use it with concrete, natural trigger phrases and a distinct CLI-browser-automation niche. Minor gaps in trigger-term synonym breadth and slight overlap risk with generic web skills keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information' — giving comprehensive coverage of user-facing browser-automation capabilities, matching the anchor-5 example.	5 / 5
Completeness	Explicitly answers both 'what' ('CLI-based browser automation with persistent page state using ref-based element interaction') and 'when' ('Use when users ask to navigate websites…') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Natural user phrases like 'navigate websites', 'fill forms', 'take screenshots', and 'test web applications' give good keyword coverage, but a few common synonyms (e.g. 'scrape', 'log in') are missing, so it sits at anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The 'CLI-based browser automation with ref-based element interaction' niche is mostly distinct, but the trigger terms (navigate/fill/screenshot) carry minor overlap risk with general web-fetch skills, placing it at anchor 4 rather than 5.	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: ArabelaTso/Skills-4-SE
Path: skills/agent-browser/SKILL.md
Commit: 4f38503

Reviewed: 22 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.