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.
86
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
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 skill description that clearly communicates what the skill does and when to use it. It uses third person voice, lists concrete actions, and includes an explicit 'Use when...' clause with natural trigger terms. The only minor weakness is potential overlap with other skills that handle forms or data extraction outside of a browser context.
| 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 language. | 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). It could benefit from mentioning the specific tool (e.g., Playwright, Puppeteer) to further distinguish it. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured and highly actionable CLI reference for browser automation. Its main strength is comprehensive, concrete command documentation with good progressive disclosure to reference files and templates. Its weaknesses are that the inline content is quite long (much of the command reference could live in a separate file) and it lacks explicit error handling/validation workflows for what is inherently a fragile automation domain.
Suggestions
Move the exhaustive command listings (mouse control, cookies/storage, network, frames, dialogs, browser settings) to a separate reference file and keep only the most commonly used commands inline to improve conciseness.
Add validation/error recovery guidance to the core workflow — e.g., 'If snapshot returns no interactive elements, wait for page load: `agent-browser wait --load networkidle`' or 'Re-snapshot after any click that triggers navigation to get fresh refs.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is largely a comprehensive CLI reference, which is useful, but it's quite long (~250+ lines) and includes many commands that could be in a separate reference file. Some sections like cookies, storage, network, mouse control, and frames could be offloaded to reference docs rather than listed inline. However, it avoids explaining basic concepts and stays focused on commands. | 2 / 3 |
Actionability | Every command is concrete, copy-paste ready, and uses real syntax with actual flags and arguments. The examples at the end show complete workflows with realistic inputs and expected outputs (e.g., snapshot output showing 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 complete flow. However, there are no explicit validation checkpoints or error recovery steps — e.g., what to do if a snapshot returns no interactive elements, or if a click doesn't navigate as expected. For browser automation (which can be fragile), feedback loops for error handling would be valuable. | 2 / 3 |
Progressive Disclosure | Excellent structure with a quick start, core workflow overview, organized command sections, and a clear deep-dive documentation table pointing to one-level-deep reference files. Templates are also well-signaled with descriptions and usage examples. Navigation is easy and references are clearly labeled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%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
05d40bb
- Reviewed
Table of Contents
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.