agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
92
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Quality
Discovery
100%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 an excellent skill description that hits all the marks. It provides specific concrete actions, includes a comprehensive list of natural trigger phrases users would actually say, explicitly addresses both what the skill does and when to use it, and carves out a distinct niche around browser automation that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task.' | 3 / 3 |
Completeness | Clearly answers both what ('Browser automation CLI for AI agents' with specific capabilities) AND when ('Use when the user needs to...' followed by explicit 'Triggers include...' clause with concrete examples). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user phrases: 'open a website', 'fill out a form', 'click a button', 'take a screenshot', 'scrape data from a page', 'test this web app', 'login to a site', 'automate browser actions' - these are exactly what users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on browser/web automation with distinct triggers like 'browser', 'website', 'web app', 'screenshot', 'scrape' that are unlikely to conflict with non-web skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability and clear workflow guidance. The core pattern is immediately clear, and all examples are executable. The main weakness is some redundancy in authentication coverage and a few sections that could be consolidated to reduce token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (authentication is explained in multiple sections with overlapping content). Some sections like 'Viewport & Responsive Testing' repeat information already covered in 'Essential Commands'. However, it avoids explaining basic concepts Claude would know. | 2 / 3 |
Actionability | Excellent executable examples throughout with copy-paste ready bash commands. Every pattern includes concrete code, specific flags, and real command sequences. The examples are complete and immediately usable. | 3 / 3 |
Workflow Clarity | Clear core workflow pattern (Navigate -> Snapshot -> Interact -> Re-snapshot) with explicit validation steps. The 'Ref Lifecycle' section explicitly warns about invalidation and shows the correct re-snapshot pattern. Diffing section provides verification workflow. | 3 / 3 |
Progressive Disclosure | Well-structured with a clear overview, essential commands, common patterns, and a reference table pointing to deep-dive documentation. References are one level deep and clearly signaled with a table mapping topics to files. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (631 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 9 / 11 Passed | |
- Repository
- tibelf/ai_project_init
- Commit
56f4516
- 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.