查找技能

Helps build or improve reusable OpenCLI website commands in JavaScript. It uses observed page behavior, captured requests, and existing adapters to guide implementation, then checks definitions and tests real command behavior and failure handling.

中文简介正在准备中。当前显示英语简介。

• Turning repeated website tasks into OpenCLI commands
• Improving an existing website adapter
• Investigating API requests before implementation

Helps agents find and use OpenCLI commands for websites and Chrome. It guides command discovery, input checks, result interpretation, and error recovery so agents can select suitable browser tools or reusable website commands.

中文简介正在准备中。当前显示英语简介。

• Finding OpenCLI commands for a specific website
• Checking command inputs and output formats
• Diagnosing Chrome connection problems

Routes OpenCLI searches to sources suited to the topic, language, or requested website. It starts with one AI source when none is specified, adds specialist sources as needed, and reports search terms and usage counts.

中文简介正在准备中。当前显示英语简介。

• Researching a topic on a specified website
• Choosing sources for Chinese or English research
• Finding original posts, products, or job listings

Uses OpenCLI to inspect and interact with Chrome pages, including logged-in websites. Agents can fill forms, extract page data, inspect captured network requests, take screenshots, and manage Chrome tabs, groups, and windows.

中文简介正在准备中。当前显示英语简介。

• Filling forms and clicking controls on logged-in websites
• Extracting page text and taking screenshots
• Inspecting network requests for API investigation

Diagnose OpenCLI commands broken by website changes, collect execution traces, patch the adapter that connects to the site, and retry. After a verified repair, prepares a GitHub issue for submission with user approval.

中文简介正在准备中。当前显示英语简介。

• Repair commands broken by website layout changes
• Adapt to changed API responses
• Distinguish empty results from adapter failures