Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Generate professional GitHub project README.md with standard structure including project intro, features, installation, usage, documentation, FAQ, contact info, donation, statistics, roadmap, and license. Auto-detects project type and tech stack.
为 OpenPrd 工作区生成归档学习包、题材模板、证据清单、图文讲解模块和 HTML 电子书阅读器。
Transcribe a call recording with speaker diarization, summarize it, and create Obsidian vault notes (call note, transcript, person notes for participants). Works with video or audio files. Supports local transcription (mlx_whisper + pyannote) or ElevenLabs Scribe.
使用 Wan2.7-image 生成公众号封面图、小红书封面图、种草图和海报改版视觉稿，并支持文生视频、静态图转丝滑动态视频、参考图 / 参考视频转视频，以及为视频自动补 Edge TTS 配音与字幕烧录。视频任务兼容 Wan 2.6 与 Wan 2.7 模型，可通过 config.yaml 默认配置或输入 JSON 的 model 字段覆盖。用于把标题、副标题、卖点、品牌色、结构化 JSON、参考图或参考视频转成真实图片或视频输出；当用户提到封面图、头图、配图、种草图、视觉稿、海报重排版、横版改竖版、文生视频、图片转视频、静态图转动态视频、参考图转视频、参考视频转视频、丝滑动态视频、视频配音、字幕烧录、Edge TTS 配音时，必须优先考虑这个技能。支持 Prompt 构建、场景选择、真实 Wan API 调用、PNG / MP4 文件输出与 prompt sidecar 保存。
为 Obsidian 微信公众号转换器生成受约束的 AI 编排结果。只在需要把文章内容映射为公众号安全 block JSON、诊断编排结果、优化 layout schema、分析 fallback 介入原因时使用。遇到教程、案例、产品介绍、截图型内容时应优先考虑这个 skill。
获取并解析微信公众号文章。从微信文章链接中提取标题、作者、公众号名称、正文内容、图片和元数据。当用户提供微信文章链接(mp.weixin.qq.com/s/...)并希望阅读、提取、下载或转换文章内容时使用。适用场景包括获取/下载微信文章、提取微信文章文字或元数据、将微信文章转换为Markdown、将微信文章连同图片保存到本地。关键词：微信公众号、文章获取、文章抓取、文章下载。
Extract the AJTBD structure from customer-interview files you already have — segments by Core Jobs, personas, the Consideration Set, existing Solutions and Problems, and value hypotheses — using Ivan Zamesin's Next Move Theory / Advanced Jobs To Be Done methodology. Input — one or many files (transcripts, notes, sales or support calls, survey open-ends), AJTBD or not. It reads each interview in its own context so it never overflows, scores each extraction's confidence, clusters into segments by similar Core Jobs, and writes one report — data-quality summary, segments with personas, structured Solutions and Problems, a Consideration Set, value hypotheses, and what to interview next. Use for "analyze my interviews", "extract jobs from these transcripts", "find the segments in these calls". Defaults to English.
Generate a formatted FF&E specification schedule from raw product data — notes, CSV, or pasted lists. Outputs a structured schedule compatible with the 33-column master schema.