con un clic
Look-Tongji-Notes
Look-Tongji-Notes contiene 11 skills recopiladas de WALKERKILLER, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
9-command agent skill suite for Tongji Look (look.tongji.edu.cn): setup, list, transcribe, take notes, manage materials, build course wiki, create cheat sheets, batch-process entire courses, and deploy course wiki to GitHub Pages.
Add supplementary materials (PDF, PPTX, DOCX, images) to a lecture session. Converts to Markdown via MarkItDown and indexes into the course wiki — without triggering transcription or slide download.
Generate a high-density A4 cheat sheet for open-book exams. Two output paths: LaTeX (XeLaTeX) or self-contained HTML with CSS print layout. Both paths produce visually consistent results.
Discover and select courses from Tongji Look (look.tongji.edu.cn). Lists recent or all courses, filters by keyword, and saves the chosen course for use with /trans, /note, and other commands. Prerequisite for all lecture workflows.
Generate study notes from a lecture transcript and slides. Runs transcript + slide download in parallel, then writes a Markdown note with timeline outline.
Deploy the built course wiki site/ to GitHub Pages via gh CLI. Pre-checks gh auth status and site/ existence.
Batch transcribe ALL playable lectures for a course in a persistent loop. Uses a JSON state file for checkpoint/resume. Runs until every lecture is transcribed or marked failed.
Configure Tongji Look credentials, check system dependencies (Python, Node.js, ffmpeg, vision-support, XeLaTeX), and set up the persistent course-wiki workspace.
Transcribe a single Tongji Look lecture video to SRT + TXT, optionally download slide snapshots in parallel.
Build and serve the static course knowledge base locally. Rebuilds from workspace data and starts an HTTP server on port 8765.
为非多模态模型（如 deepseek-v4-pro、GLM-5.1、mimo-v2.5-pro 等纯文本模型）提供图片识别能力。当主模型无法识别图片、用户发送了截图/设计稿/UI 截图需要分析、或者用户说'看看这张图'、'分析这个截图'、'这张图片有什么问题'时，自动触发此技能。也适用于用户粘贴了图片但当前模型不支持图片输入的任何场景。支持同时识别多张图片，通过配置多个识图模型实现主备回退。使用指令 /skill:vision-support 或 /vision 也可手动触发。铁律：本技能配置的模型仅用于图片内容识别，绝不参与主逻辑推理。注意：如果当前模型本身是多模态模型（如 Claude Sonnet 4、GPT-4o、Gemini 等可以直接识图的模型），不要使用此技能，直接让主模型识别即可。