agent-browser
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
99
100%
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 a well-crafted skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms covering both technical and natural language, explicit 'Use for' and 'Triggers' sections, and a clearly defined niche in browser automation that distinguishes it from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Navigate web pages, interact with elements using @e refs, take screenshots, record video' plus detailed capabilities like 'web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution'. | 3 / 3 |
Completeness | Clearly answers both what ('Browser automation for AI agents via inference.sh' with detailed capabilities) and when ('Use for: web automation, data extraction, testing, agent browsing, research' plus explicit 'Triggers:' section). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video' covers both technical and casual user language. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche with distinct triggers around browser automation, Playwright, and web interaction. The specific mention of '@e refs' and 'inference.sh' further distinguishes it from generic web or document skills. | 3 / 3 |
Total | 12 / 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 exemplary skill document that efficiently teaches browser automation without wasting tokens on concepts Claude already knows. It provides complete, executable examples with clear workflow patterns and appropriate validation checkpoints around ref invalidation. The progressive disclosure is well-executed with a scannable overview and clearly signaled deep-dive references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence with Playwright and browser automation concepts. No unnecessary explanations of what browsers or automation are—jumps straight to actionable commands and patterns. | 3 / 3 |
Actionability | Provides fully executable bash commands throughout with complete JSON input structures. Examples are copy-paste ready with proper session handling, and the interact actions table gives precise field requirements. | 3 / 3 |
Workflow Clarity | Clear 4-step workflow pattern (Open → Interact → Re-snapshot → Close) with explicit validation checkpoint about ref invalidation after navigation. The 'Important' callout about re-snapshotting serves as a critical feedback loop for error prevention. | 3 / 3 |
Progressive Disclosure | Excellent structure with quick start, core workflow overview, then tables for reference. Deep-dive documentation and templates are clearly signaled with one-level-deep links to specific reference files and templates. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- inference-sh/skills
- Commit
9a723cd
- 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.