技能列表

>

|

>-

>

Transform blog posts, articles, and long-form content into multiple formats—videos, podcasts, social media posts, and summaries. Use when the user needs content automation, multi-channel distribution, or quick content recycling."

Generate optimized 30/60/90-day content calendars by analyzing brand voice, industry trends, and engagement data. Use when the user needs content strategy planning, editorial calendars, or campaign scheduling for solopreneurs and agencies."

聚合国内最新AI相关政策，覆盖国家级（国务院、工信部、科技部、网信办等）和广东省及广州的政策动态，提供简报式解读。

Conduct structured AI paper surveys using alphaXiv MCP tools. Reads user research interests from a keywords file, searches recent papers across multiple dimensions, classifies by innovation tier, runs impact analysis, and outputs a Markdown report. Use when the user asks to survey recent papers, do a literature review, find what's new in a research area, or track progress in AI subfields.

>

>

Use when building AI-powered features with the Claude API or Anthropic SDK — structured outputs, tool calling, streaming, multi-provider routing, multi-agent orchestration, LLM evaluation, prompt engineering, agent memory, RAG pipelines, and production deployment. Covers single-agent, multi-agent, and agentic loop patterns for Next.js, Python, and TypeScript stacks.

WIME AI 电商创作平台 OpenAPI。提供两个核心能力：1）抠图 — 上传本地图片（或 URL）自动抠图，返回透明背景图 URL；2）商拍图 — 自动抠图后生成多张 AI 商拍图。触发场景：用户提到抠图、商拍图、商品图、WIME、电商图片处理时激活。