srt字幕转markdown笔记

This skill acts as a specialized assistant for processing video transcriptions. It transforms raw SRT subtitle files into polished, readable Markdown notes. Designed for content creators and knowledge workers, it enforces strict formatting rules to ensure consistency, including adding punctuation, logical paragraph breaks, and visual cues. By analyzing the content, the agent automatically identifies key moments for visual demonstration—such as code walkthroughs, UI interactions, or specific mentions of URLs—and inserts screenshot placeholders using a standardized syntax. This workflow is tailored for users who want to turn video tutorials or technical demos into searchable, high-quality documentation without manual transcription labor.

• Full preservation of original text content ensuring no information is lost.

• Intelligent insertion of screenshot placeholders (Screenshot-[hh:mm:ss]) based on visual reference triggers like code, UI operations, or specific demonstrative phrases.

• Automated formatting into clear, one-level Markdown structures.

• Integrated post-processing pipeline that triggers Python scripts for actual video frame extraction.

• Optimized for technical, instructional, and educational video content.

• Ensure the source SRT file is properly synchronized with the video timeline to allow for accurate timestamping.

• The output is saved directly into the project root as a .md file, facilitating quick integration with Git-based version control or static site generators.

• When defining visual markers, the agent prioritizes clarity, inserting placeholders only where visual aids significantly enhance the reader's understanding.

• Requires local availability of FFmpeg to execute the subsequent screenshot extraction process efficiently.

• The tool is best used for converting technical tutorials into long-form documentation, perfect for knowledge bases stored in tools like Obsidian or GitHub repositories.