Douyin Copy Extractor
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_4ef54573/lihang2026.
About this skill
Problem
Spoken content in short videos is often scattered across audio, captions, and platform pages, making manual capture tedious. lihang-douyin-text turns a Douyin link into an archivable Markdown transcript. If the user already provides a title and body text, it can skip download and transcription and proceed directly to semantic segmentation and knowledge-base sync.
Core workflow
The skill follows a fixed pipeline:
- Download the video with douyin-download-v2 and capture the video ID and title
- Transcribe Chinese audio with a local Whisper small model
- Segment the text by logical paragraphs rather than sentences, preserving colloquial tone and internet phrasing
- Number paragraphs as **① Section title** and separate them with ---
- Save the result as {videoID}_{videoTitle}.md, query the largest existing Lexiang sequence number, and upload it as Article N+1
Boundaries
It is best for personal or small-team archiving of spoken content, not a generic subtitle tool. It depends on a local model, the video download path, and Lexiang MCP configuration. Slow CDNs, zero-byte downloads, rate limits, or 500 errors may require timeout, retry, or connector-status checks. If the request is imitation writing rather than extraction, it switches to the specified persona and tone, which is separate from transcript extraction.
Use Cases
- Capture a Douyin video link and turn its spoken content into archivable Markdown, then sync it to Lexiang.
- With an existing title and body, segment the text into numbered logical paragraphs, format it with dividers, and upload it as the next Lexiang article.
- After local transcription of Chinese audio, preserve colloquial tone and internet phrasing while organizing scattered sentences into numbered paragraphs.
- Draft an imitation of a Douyin spoken script using the specified post-00s office worker persona and casual, low-formal style.
Best For
- Operators or content editors who archive Douyin spoken content into a personal knowledge base each week.
- Creators who need archivable Markdown transcripts from local Chinese audio without hand-writing formatting rules.
- Team knowledge managers who format existing copy into fixed numbered paragraphs and sync it to Lexiang.
- Copywriters who need Douyin spoken-style imitations without formal writing or motivational tone.
Related Skills
Search Huawei Cloud official docs and product pages to find ECS, OBS, RDS, CCE product specs, parameters, documentation, and API references without login.
OCR-based recognition for movie, train, flight, and event tickets in images or PDFs, extracting key fields into Markdown or JSON reports.
Turns notes, research, and meeting summaries into actionable next moves, plans, decisions, experiments, and decision-changing gaps.
A local wiki knowledge base manager that compiles raw documents into sourced, indexed Markdown pages with wikilinks, query support, and health checks.