codex2course
Codex2Course
Overview
Create a course package from a topic or outline: detailed teaching handouts first, then slide units, then one Imagegen-generated raster image per slide, then a PDF assembled from those images. The core rule is that slides are generated image pages, not .pptx, HTML, Markdown, SVG, canvas, screenshot, or locally rendered pages.
REQUIRED SUB-SKILL: Use imagegen for every generated slide page, cover image, visual metaphor, diagram-like bitmap, or style variant.
Non-Negotiable Output Routing
When this skill is active, imagegen is the only route for producing slide visuals.
Allowed local scripts:
scripts/split_handout.pymay deriveslide-units/fromhandout.md.scripts/images2pdf.pymay assemble existingslides/*.pngfiles into a PDF.
More from likefallwind/courseskills
pdf2video
Use when turning a codex2course-produced course package (outline.md + handout.md + slide-units/ + slides/*.png) into a narrated lecture video — writes per-slide narration, synthesizes voice via either MINIMAX TTS (paid, higher quality) or Microsoft Edge TTS (free), and assembles slides + audio into a single mp4 with ffmpeg.
2makecourse
Use when publishing an AI-generated course directory into the aistudy101 website. The user provides the generated course path and says which curriculum course it corresponds to; Codex must register the course, keep the source repo link, copy generated lesson videos into website assets through sync, update data, run build verification, and leave source videos untouched.
2ai-tutorials
Use when designing, writing, or structuring AI courses, tutorials, lectures, and hands-on projects. Also use when user asks to create syllabus, write lecture notes, or design coding exercises about AI/ML/LLM topics.
2movecourse
Use when publishing AI-generated course lesson mp4 files into the aistudy101 website course-assets tree, especially from lesson*/ directories into static/course-assets/<course-id>/lesson*/video.
1