Docs Gen
Generate and maintain documentation
legacy-rule-miner
by xiwen-haochi
Analyze legacy backend codebases and generate comprehensive AI-facing rule files (Markdown) that enable AI coding assistants to modify code correctly on the first attempt. Covers Java/Spring, PHP/ThinkPHP/Laravel, Python/Django/Flask, Node.js/Express/Koa/Egg, Go, and .NET projects. USE THIS SKILL whenever the user wants to: generate rules/instructions for an old or legacy project; create .cursorrules, .copilot-instructions.md, CLAUDE.md, or similar AI rule files from existing code; analyze a codebase to extract coding conventions, patterns, and pitfalls; document an undocumented project for AI consumption; or prepare a legacy codebase so AI can safely modify it. Also use when the user mentions "屎山", "老项目", "遗留代码", "legacy code", "rule mining", "extract conventions", or wants to ensure AI modifications are compatible with existing code style.
usdc-summarize
by elisymlabs
Summarize long text for 0.05 USDC per job (devnet)
geo-infer-comms
by ActiveInferenceInstitute
Communication systems for geospatial coordination. Use when implementing spatial messaging, multi-channel notifications (email/SMS/push), event streaming, spatial message routing, or subscriber management for geographic broadcasts.
modular-architecture-documentation-tech-stack-section
by vamseeachanta
'Sub-skill of modular-architecture-documentation: Tech-Stack.md Modular
opentui
by grota
Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for any TUI development task including components, layout, keyboard handling, animations, and testing.
geo-infer-intra
by ActiveInferenceInstitute
Central documentation hub and cross-module integration guides for GEO-INFER. Use when navigating documentation, finding cross-module integration patterns, understanding data flow architecture, or locating tutorials and API references.
specs
by petestewart
Create technical specifications from PRD.md and PROBLEM.md. Use when the user has a PRD and wants detailed technical specs for implementation. Also use when the user says "/specs", "create specs", "technical specifications", or "spec it out".
typora-markdown
by petestewart
Open markdown content in Typora for enhanced viewing. Use when creating plans, PR reviews, analysis reports, or substantial markdown content. Triggers on: plan files, /review-pr output, codebase analysis, documentation generation, or explicit user request to view in Typora.
cohesion
by toss
Use when 한 기능 수정 시 여러 디렉토리를 건드리거나, 같은 숫자/상수가 여러 파일에 흩어져 있거나, import 경로가 ../../..처럼 길어질 때
skill-creator
by liyecom
Claude Skills 创建指南与最佳实践
article-batch-illustration
by zephyrwang6
分析文章结构并批量生成AI配图，调用Gemini API为每个段落创建专业逻辑图/概念图。当用户说"批量配图"、"给文章配图"、"生成文章插图"、"为这篇文章配图"时触发。支持两种风格：简约手绘风和建筑蓝图编辑风。自动保存到Obsidian图片目录并插入文档。
topic-reviewer
by zephyrwang6
选题审核工具。检查选题是否符合发布标准，给出通过/不通过判断及修改建议。当用户说"审核选题"、"这个选题行不行"、"帮我看看这个能不能写"时触发。
web-article-translator
by zephyrwang6
翻译在线文章为中文并保存为 Markdown 格式。当用户需要翻译网页文章、博客文章时使用此技能，例如："翻译这篇文章 https://example.com/article"、"把这个 URL 的文章翻译成中文并保存"。
mem-monthly
by zephyrwang6
AI个人记忆系统的月度复盘功能。分析本月L2行为层更新，提炼思维模式到L3认知层，检查L4核心层是否需要校准。使用场景：(1) 用户说"月复盘"时；(2) 每月末定期回顾时；(3) 需要从行为模式提炼认知框架时。该skill会分析多个行为是否指向同一思维原则，尝试提炼到L3，并引导用户反思L4核心层。
podcast-workflow
by zephyrwang6
播客处理一站式工作流。支持两种入口： (1) 直接处理：提供 YouTube 链接，直接进入处理流程 (2) 更新检查：获取关注博主的最新更新，用户挑选后处理 功能：字幕提取 → content-digest 处理 → 自动保存飞书知识库。 触发词："获取播客更新"、"处理这个播客"、"播客工作流"、"有什么新播客"。
logo-batch-generator
by zephyrwang6
批量生成品牌Logo。支持两种入口：(1)用户描述品牌/用途后批量生成10个Logo变体 (2)用户上传参考图片后分析并生成Logo。提供7种主流风格选择。调用Gemini API生成，保存到Obsidian图片目录。触发词："生成Logo"、"设计Logo"、"做个Logo"、"批量Logo"、"帮我设计一个标志"。
topic-generator
by zephyrwang6
AI选题生成工具。从采集的热点中筛选TOP10，生成完整选题方案。当用户说"生成选题"、"筛选热点"、"哪些值得写"时触发。输出包含：事件描述、核心角度、标题、写作方式。
web-scraper
by zephyrwang6
Fetch and extract content from web pages, converting HTML to clean markdown. Use when users want to read web articles, extract information from URLs, scrape web content, or when the built-in WebFetch tool fails due to network restrictions. Trigger when user provides URLs to read, asks to fetch web content, or needs to extract text from websites.
Content Rewriting Skill - 内容仿写工作流
by zephyrwang6
"[çç½ï¼ä¸æ»ç»]"
storyboard-generator
by zephyrwang6
根据用户描述的故事内容，润色故事线并拆分为分镜脚本，批量生成风格一致的故事板插图。提供8种视觉风格选择，基于故事类型推荐最佳风格。调用Gemini API生成图片，保存到Obsidian图片目录。触发词："分镜故事"、"故事板"、"做个分镜"、"创建故事板"、"storyboard"、"画个故事"。
youtube-feed
by zephyrwang6
获取关注的 YouTube 博主/播客的最新更新。列出最近两天的新视频，包含标题、发布时间和简要描述。 触发词："获取播客更新"、"最近有什么新播客"、"YouTube 更新"、"播客更新"、"有什么新的播客"。 用于每日检查关注的 AI/科技播客是否有新内容更新。
doc-coauthoring
by zephyrwang6
Guide users through a structured workflow for co-authoring documentation, articles, or long-form content. Use when user wants to write documentation, proposals, articles, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting articles, or using "co-authoring" workflow.
markdown-to-image
by zephyrwang6
将 Markdown 内容转换为精美的图片海报。特别适合将播客摘要、文章内容转为社交媒体分享图片。固定 3:4 比例，支持 YouTube 视频封面作为头图。触发词：「转图片」「Markdown 转图片」「生成海报」「生成分享图」「把这个转成图片」。
youtube-transcript-cn
by zephyrwang6
从 YouTube 视频链接提取字幕并转换为中文文字稿。支持自动生成字幕和手动字幕。 使用场景：(1) 用户提供 YouTube 链接并要求提取字幕/文字稿，(2) 用户要求将 YouTube 视频内容转为文字， (3) 用户说"帮我把这个 YouTube 视频转成文字"或类似请求。 触发词：YouTube 字幕、视频转文字、提取字幕、YouTube transcript、视频文字稿。