Documents skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
qiaomu-cut
把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video; build English-learning movie mixes, person profiles, explainers, product launch videos, cinematic shorts, social clips, course/PPT videos, AI image/video/TTS/music-assisted stories, stock-footage stories, or multi-source montage. Routes across 33台词, ClipSeek/Pexels/Pixabay/open media, local files, ListenHub/MarsWave generation and content extraction, Coli local ASR, agent image generation, HTML/motion graphics, Manim-style explainers, ffmpeg-full rendering, subtitles, transitions, masks, and quality checks.
volcengine-avatar
Create AI digital humans using Volcengine Avatar. Use when you need to: (1) create AI avatar presenters, (2) generate avatar videos with speech, or (3) build virtual spokespersons for content.
yida-export-conversation
导出 AI 对话记录，生成结构化的 Markdown 文档。支持 Claude Code 自动检测，其他环境通过 --input 手动指定。适用于保存和回顾 AI 编程过程记录。
yida-flash-note-to-prd
从钉钉闪记、会议记录或需求文档中提取产品需求，生成结构化 PRD。支持文本、图片、链接三种输入方式。适用于将会议产出快速转化为可执行需求文档。
youtube-video-analyzer
YouTube视频分析工具，提取视频数据和表现指标，分析内容策略、受众互动和增长机会
data-diagnostics
Run data quality checks on a CSV file. Reports shape, types, missing values, summary statistics, outlier flags, and duplicates without modifying the source file.
doc-summarizer
Summarize documents of any size by extracting them with the document-converter engine, chunking to fit context, and fanning chunks out to subagents that produce structured summaries, then synthesizing one unified summary. Handles PDF, DOCX, PPTX, XLSX, HTML, CSV, TXT, MD and more. Use when the user wants to: (1) summarize a single document, (2) summarize multiple documents in batch, (3) condense content from large files that exceed context limits, (4) get a quick overview of document contents. Triggers on: "summarize this document", "what's in this PDF", "give me a summary of these files", "extract key points from", "condense this document", "TL;DR of this file".