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:code-yeongyu/oh-my-openagent --skill agent-browser97
Quality
96%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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, uses natural trigger terms users would actually say, includes an explicit 'Use when...' clause with comprehensive triggers, and carves out a distinct niche around browser automation that won't conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'browser interactions', 'web testing', 'form filling', 'screenshots', 'data extraction', 'navigate websites', 'interact with web pages'. 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 with explicit 'Use when...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'websites', 'web pages', 'fill forms', 'screenshots', 'test web applications', 'extract information'. Good coverage of common variations and natural language terms. | 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
92%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, highly actionable skill document that provides comprehensive CLI reference for browser automation. The content is lean, assumes Claude's competence, and provides executable examples throughout. The only weakness is the monolithic structure - advanced features like cloud providers, iOS simulator, and native mode could be split into separate reference files for better progressive disclosure.
Suggestions
Consider splitting advanced topics (Cloud providers, iOS Simulator, Native Mode, CDP Mode) into separate reference files like CLOUD.md, MOBILE.md, etc., with brief pointers from the main skill
Add a 'Common issues' or 'Troubleshooting' section for error recovery guidance (e.g., what to do when elements aren't found, timeouts occur)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is highly efficient with no unnecessary explanations. It assumes Claude knows what browsers, URLs, and web interactions are, jumping straight to executable commands and examples. | 3 / 3 |
Actionability | Every section provides copy-paste ready commands with concrete examples. The form submission and authentication examples are fully executable workflows with specific commands and expected outputs. | 3 / 3 |
Workflow Clarity | The core workflow section clearly sequences the steps (navigate → snapshot → interact → re-snapshot). Multi-step examples like form submission and authentication include validation checkpoints (wait for networkidle, check result with snapshot). | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but this is a monolithic 400+ line file that could benefit from splitting advanced topics (cloud providers, iOS simulator, native mode) into separate reference files. The structure is good but everything is inline. | 2 / 3 |
Total | 11 / 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.