agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Quality

78%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./config/claude/skills/agent-browser/SKILL.md

Quality

Discovery

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description that clearly communicates what the skill does and when to use it, with good trigger term coverage. The 'Use when...' clause is well-constructed with multiple natural trigger scenarios. The only minor weakness is potential overlap with other skills that handle forms or data extraction in non-browser contexts.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'browser interactions', 'web testing', 'form filling', 'screenshots', and 'data extraction'. These are clear, actionable capabilities.	3 / 3
Completeness	Clearly answers both 'what' (automates browser interactions for web testing, form filling, screenshots, data extraction) and 'when' (explicit 'Use when...' clause listing six trigger scenarios).	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'navigate websites', 'interact with web pages', 'fill forms', 'take screenshots', 'test web applications', 'extract information from web pages'. These cover a good range of natural user phrasings.	3 / 3
Distinctiveness Conflict Risk	While browser automation is a fairly distinct niche, terms like 'data extraction' and 'form filling' could overlap with non-browser skills (e.g., PDF form filling, API-based scraping). Adding mention of specific tools (e.g., Playwright, Puppeteer) or file types would sharpen distinctiveness.	2 / 3
	Total	11 / 12 Passed

Implementation

64%

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

This is a comprehensive and highly actionable CLI reference for browser automation with concrete, executable commands and good examples. Its main weaknesses are the monolithic length (most command categories could be in reference files) and the lack of explicit error handling/validation checkpoints in workflows, which is important for fragile browser automation tasks. The progressive disclosure structure is partially implemented with reference links but undermined by the extensive inline content.

Suggestions

Move detailed command categories (mouse control, network, cookies/storage, frames, dialogs, browser settings) into reference files and keep only the most common commands in SKILL.md to improve conciseness and progressive disclosure.

Add explicit validation/error recovery steps to the core workflow and examples — e.g., 'If snapshot returns no interactive elements, wait for page load: `agent-browser wait --load networkidle`' or 'If click fails, re-snapshot to get fresh refs.'

Dimension	Reasoning	Score
Conciseness	The skill is largely a comprehensive command reference, which is useful but quite long (~250+ lines). Most content earns its place as a CLI reference, but some sections like the video recording explanation and certain comments could be tightened. It avoids explaining concepts Claude already knows, but the sheer volume of commands listed inline rather than in reference files hurts token efficiency.	2 / 3
Actionability	Every command is concrete, copy-paste ready, and uses real syntax with specific flags and arguments. The examples section shows complete workflows with realistic inputs and expected outputs (e.g., form submission with snapshot refs). No pseudocode or vague instructions.	3 / 3
Workflow Clarity	The core workflow section provides a clear 4-step sequence, and the form submission example demonstrates a good flow. However, there are no explicit validation checkpoints or error recovery steps — e.g., what to do if a snapshot returns no interactive elements, if a click fails, or if navigation times out. For browser automation (which can be fragile), missing feedback loops cap this at 2.	2 / 3
Progressive Disclosure	The skill references detailed documentation in references/ and templates/ directories with a clear table of links, which is good structure. However, the main SKILL.md itself is very long with extensive inline command references that could be split into reference files. The bulk of the content (all command categories) is presented monolithically rather than keeping the SKILL.md as a concise overview. Note: no bundle files were provided, so referenced files cannot be verified.	2 / 3
	Total	9 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: freekmurze/dotfiles
Commit: 3974caa

Reviewed: 19 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.