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.
Install with Tessl CLI
npx tessl i github:tibelf/ai_project_init --skill agent-browser100
Does it follow best practices?
Validation for skill structure
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 natural trigger terms users would actually say, explicitly answers both what and when, and carves out a distinct niche around browser automation. The description is comprehensive without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, automating any browser task'. Uses third person voice correctly. | 3 / 3 |
Completeness | Clearly answers both what ('Browser automation CLI for AI agents' with specific capabilities) AND when ('Use when the user needs to...' with explicit trigger phrases). Has a comprehensive 'Triggers include' clause with multiple 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 automation with distinct triggers like 'open a website', 'browser actions', 'scrape data from a page'. Unlikely to conflict with non-browser skills due to specific web/browser terminology throughout. | 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 file that maximizes token efficiency while providing comprehensive, actionable guidance. The core workflow pattern is immediately clear, common patterns cover real-world use cases with executable examples, and the progressive disclosure to reference docs and templates is well-organized. The explicit 'Ref Lifecycle' section addresses a critical gotcha that could otherwise cause failures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what browsers or automation are. Every section delivers actionable content immediately with minimal prose. | 3 / 3 |
Actionability | Fully executable commands throughout with copy-paste ready examples. The core workflow, common patterns, and all command examples are concrete and immediately usable. | 3 / 3 |
Workflow Clarity | Clear 4-step core workflow (Navigate → Snapshot → Interact → Re-snapshot) with explicit validation pattern. The 'Ref Lifecycle' section explicitly addresses when to re-snapshot, providing the critical feedback loop for DOM changes. | 3 / 3 |
Progressive Disclosure | Excellent structure with quick-start content inline, then clear tables pointing to deep-dive documentation and ready-to-use templates. References are one level deep and well-signaled with descriptive 'When to Use' guidance. | 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.
- 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.