chubbyskills
把中文全渠道内容（抖音 / B站 / 小红书 / 公众号 / X / 播客）采集进个人知识库的 14 个 AI Skill：图文存图、视频转文字稿、字幕优先免 GPU、RSS/YouTube 订阅调度与每日
What is chubbyskills?
把中文全渠道内容（抖音 / B站 / 小红书 / 公众号 / X / 播客）采集进个人知识库的 14 个 AI Skill：图文存图、视频转文字稿、字幕优先免 GPU、RSS/YouTube 订阅调度与每日情报简报，附带知识库 MCP server。｜ Ingest Chinese content into your personal knowledge base — image/video routing, subtitle-first transcription, feed subscriptions with daily digests, and a KB MCP server.
Overview of chubbyskills
What it is
Chubby Skills is a set of 14 Agent Skills and command-line tools for content creators and personal knowledge bases. You can install skills on demand to let an Agent process materials, or run commands directly to chain ingestion, storage, search, and export. Output is saved as local Markdown files, usable with Obsidian, text editors, or your Agent.
Key features
- Save platform materials: video subtitles and transcription, podcast transcription, article and image-text collection - Import existing files: Markdown, TXT, PDF text layer, preserving source and local attachments - Search and retrieve: keyword search, optional semantic search, original text reading; index auto-updated after ingestion - Export research packs: Markdown/JSON with excerpts, line numbers, sources, and file summaries - Agent-ready: standalone skill packages and an optional MCP server providing search and text reading tools - Subscribe to public RSS/Atom/JSON feeds, YouTube channels, and custom provider outputs; discovery, review, transcription, and ingestion are separated - Platform support: Bilibili/YouTube (stable, subtitle-first), WeChat public accounts (testing), Douyin/TikTok/Weibo/Zhihu (heavy dependencies), podcasts (heavy dependencies), X/Xiaohongshu (manual fallback), local documents (stable, zero dependencies)
Use cases
- Save videos, podcasts, articles, and local documents as searchable Markdown - Import existing materials and keep original sources - Find evidence during writing via keyword or semantic search - Compile a research pack with excerpts and citations - Let an Agent use the knowledge base via skills or MCP - Continuously track reliable sources via RSS, YouTube, or custom feeds
Getting started
bash git clone https://github.com/chubbyguan/chubbyskills.git cd chubbyskills python3 tools/chubby.py init --vault $PWD/creator-vault python3 tools/chubby.py ingest https://x.com/OpenAI/status/1663696190960173056 --no-enrich python3 tools/chubby.py search ChatGPT For importing your own files: bash mkdir -p demo-input cat > demo-input/notes.md # (add your content) python3 tools/chubby.py ingest demo-input/notes.md --source-url https://example.com Requires Python 3.11+. See repository README for full details.
License and pricing
MIT license. Open source.
Based on the project's public README and repository metadata.
