技能列表

Collaborative task checklist manager for AI agents with sequential, parallel, and looping execution. Features agent coordination, dependencies, deadlock prevention, and loop safety.

Plan Walmart grocery and household orders with pickup timing, substitutions, repeat restocks, and budget-aware cart decisions.

Allows users to check the status of a blockchain transaction by submitting a TxId. Queries the AOX transaction API and returns human-readable results.

Test translation quality with built-in dictionaries and comparison tools. Use when evaluating translations.

Daily morning briefing — emails, calendar, tasks, and weather in one summary. Cron or on-demand.

Find the cheapest meaningful visible price for a user-provided product name across major Chinese shopping platforms such as Taobao, Tmall, JD.com, Pinduoduo, Vipshop, and similar marketplaces. Use when the user asks where a product is cheapest, wants a quick cross-platform price check, wants the lowest current visible price, wants to compare the same product across Chinese e-commerce platforms, or asks questions like "哪个最便宜", "哪里买最便宜", "帮我比价", "全网找最低价", "哪个平台便宜", "哪里下单最划算", or "帮我找最低价".

|

Implement Chatbot Personality Set using OrbCafe UI (CustomizeAgent). Enterprise-grade React component with built-in best practices.

Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.

Build real-time voice chatbot applications with natural conversation flow and customizable personalities. Use when users want to create voice assistants, conversational AI, or interactive voice agents.

Use the local Codex CLI through mcporter and codex-mcp-server for real coding work in the current project. Use when the user asks to build features, fix bugs, refactor code, debug failures, write or update tests, review implementation options, or otherwise delegate non-trivial development work to the machine-local Codex installation.

Audio transcription and text-to-speech generation using OpenRouter API. Use when the user needs to transcribe audio files to text or generate speech/audio from text. Supports multiple audio formats for input and output, reads API key from environment, and writes generated audio to OpenClaw workspace tmp when available or an explicit output path.