Loading...
Loading...
Found 49 Skills
Use when creating new skills, commands, or agent definitions for Claude Code, including writing SKILL.md files, defining triggers, and testing skill behavior
TDD applied to documentation - create production-ready skills. Use when authoring new skills. Includes writing style guidelines for clear prose.
Identify and eliminate AI-generated traces in Chinese text to make articles more natural and human-like. AI writing feature detection based on Chinese context, including clichés, over-modification, mechanical structures, etc. Referenced the Wikipedia "Signs of AI writing" guide and localized it for Chinese context.
LaTeX academic paper assistant for English papers (IEEE, ACM, Springer, NeurIPS, ICML). Domains: Deep Learning, Time Series, Industrial Control. Triggers (use ANY module independently): - "compile", "编译", "build latex" → Compilation Module - "format check", "chktex", "格式检查" → Format Check Module - "grammar", "语法", "proofread", "润色" → Grammar Analysis Module - "long sentence", "长句", "simplify" → Long Sentence Analysis Module - "academic tone", "学术表达", "improve writing" → Expression Module - "logic", "coherence", "methodology", "argument structure", "论证" → Logical Coherence & Methodological Depth Module - "translate", "翻译", "中译英", "Chinese to English" → Translation Module - "bib", "bibliography", "参考文献" → Bibliography Module - "deai", "去AI化", "humanize", "reduce AI traces" → De-AI Editing Module - "title", "标题", "title optimization", "create title" → Title Optimization Module
Convert content generated by general writing Skills into formats and styles suitable for publishing on Zhihu. Zhihu favors content styles with professional depth, clear logic, and well-supported arguments.
Main entry for cross-platform content creation. Coordinates the entire creation process: Research → Image Selection → Writing → Polishing → Platform Conversion. Used for creating articles, developing content, conducting topic research, and publishing to Zhihu/Xiaohongshu/WeChat Official Accounts.
Write node content documents. Read download.txt, integrate local materials for each node and write detailed, accurate, and complete Markdown documents. Each sub-agent processes one node in parallel, outputting a complete node document including overview, directory/mind map, flow chart, online image URL, and reference materials. Suitable for scenarios requiring systematic and structured content creation.
Process images and support adding captions to images. Two caption modes: bottom frame style (like a picture frame) and internal sticker style (similar to Xiaohongshu effect). Implemented with PIL/Pillow, supports Chinese and Emoji.
Generate battle-tested sales page copy through hostile validation, output only polished final copy
Conduct web research and material downloading for each node. Read node-list.txt, launch multiple sub-agents to perform parallel web research on node content, deeply retrieve relevant webpages/articles/blogs/literature, download and save them locally, and output a download.txt file to record the material sources for each node. Suitable for document writing scenarios that require extensive background information, data verification, and reference sources.
Perform web-based image searches for given topics to find suitable image materials. Use DuckDuckGo Image Search, supporting filtering by size, color, type, and copyright. Return structured information such as image URLs, thumbnails, sources, etc.
Conduct in-depth web-based research on given topics, collect and organize materials for subsequent content creation. Automatically detect available web search tools (WebSearch or MCP search tools), fall back to DDGS when no tools are available. Output structured Markdown data summary with source citations.