agent-browser
Browser automation CLI for AI agents. Use for website interaction, form automation, screenshots, scraping, and web app verification. Prefer snapshot refs (@e1, @e2) for deterministic actions.
87
83%
Does it follow best practices?
Impact
90%
3.10xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
67%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 description effectively communicates specific browser automation capabilities and establishes a clear niche. However, it lacks an explicit 'Use when...' clause and could benefit from more natural user-facing trigger terms like 'click', 'navigate', or 'open website' that users would actually say when needing this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to navigate websites, click elements, fill out web forms, take screenshots, or scrape web content.'
Include more natural trigger terms users would say: 'click', 'navigate', 'browse', 'open URL', 'web page', 'login to site'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'website interaction, form automation, screenshots, scraping, and web app verification'. Also includes technical guidance about snapshot refs for deterministic actions. | 3 / 3 |
Completeness | Clearly answers 'what' with specific capabilities, but lacks an explicit 'Use when...' clause. The 'when' is only implied through the capability list rather than explicitly stated with trigger guidance. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'browser automation', 'screenshots', 'scraping', 'form automation', but missing common user variations like 'click', 'navigate', 'web page', 'URL', 'browse', or 'open website'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche as 'Browser automation CLI for AI agents' with distinct triggers around web interaction, screenshots, and scraping. The mention of 'snapshot refs (@e1, @e2)' adds unique technical specificity unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that demonstrates best practices across all dimensions. It provides a clear, actionable workflow with executable examples, appropriate safety considerations, and well-organized progressive disclosure to reference materials. The troubleshooting section adds practical value without bloating the core content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence with CLI tools and browser automation concepts. No unnecessary explanations of what browsers or automation are; every section provides actionable information. | 3 / 3 |
Actionability | Provides fully executable bash commands throughout, with concrete examples for the core workflow, command chaining, verification patterns, and troubleshooting. Commands are copy-paste ready with real flags and arguments. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced (open -> wait -> snapshot -> interact -> re-snapshot) with explicit validation through snapshots after DOM changes. The verification patterns section shows proper baseline -> action -> verify feedback loops. | 3 / 3 |
Progressive Disclosure | Well-structured overview with clear references to deep-dive docs (commands, snapshot-refs, session-management, authentication) and ready templates. References are one level deep and clearly signaled in the References section. | 3 / 3 |
Total | 12 / 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
- supercent-io/skills-template
- Commit
c033769
- 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.