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.
Install with Tessl CLI
npx tessl i github:brianlovin/claude-config --skill agent-browser92
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation 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 a well-crafted skill description that follows best practices. It uses third person voice, lists specific capabilities, includes a clear 'Use when...' clause with natural trigger terms, and establishes a distinct domain (browser automation) that won't easily conflict with other skills.
| 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, and data extraction') AND when ('Use when the user needs to navigate websites, interact with web pages...') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'navigate websites', 'interact with web pages', 'fill forms', 'take screenshots', 'test web applications', 'extract information from web pages'. Good coverage of common user language. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on browser automation and web interaction. The combination of 'browser', 'web pages', 'screenshots', and 'web testing' creates a distinct domain unlikely to conflict with document processing or other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and concise command reference that respects Claude's intelligence by providing pure executable examples without unnecessary explanation. The main weaknesses are the lack of error handling/validation guidance in workflows and the monolithic structure that could benefit from splitting detailed command categories into separate reference files.
Suggestions
Add error handling guidance to the core workflow section (e.g., what to do when elements aren't found, how to retry failed interactions)
Consider splitting detailed command categories (Navigation, Interactions, Network, etc.) into a separate REFERENCE.md file, keeping only quick start and core workflow in SKILL.md
Add a troubleshooting section or validation steps for common failure scenarios (element not found, timeout, stale refs after DOM changes)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient - pure command reference with no unnecessary explanations. Every line provides actionable information without explaining what browsers or automation are. | 3 / 3 |
Actionability | Fully executable commands throughout with copy-paste ready examples. The form submission and authentication examples show complete workflows with actual commands and expected outputs. | 3 / 3 |
Workflow Clarity | Core workflow is clearly sequenced (navigate → snapshot → interact → re-snapshot), but lacks validation checkpoints for error recovery. No guidance on what to do if commands fail or elements aren't found. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections, but the document is quite long (~200 lines) and could benefit from splitting detailed command references into separate files. All content is inline rather than appropriately distributed. | 2 / 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.
- 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.