course-generate
Skill1 starsChanged 7 months agoMITView on GitHub
Generate a complete course — learning objectives, syllabus, slides (LaTeX), scripts, and assessments — using the ADDIE multi-agent pipeline. Use when the user asks to "create a course on X", "generate teaching materials for X", "build an undergraduate/graduate course on X", or similar end-to-end course-authoring requests.
- Reads credentials
- Installs packages
In this repository3 other files it gives its agents.
- latex-compileSkill
- latex-to-pptxSkill
- slide-evaluateSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Do not invoke for:
- Very specific: line 27
Only evaluating existing slides → use slide-evaluate
- Distinctive: line 89
After generation you typically want to run:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Course Generate (Full ADDIE Pipeline)
Runs the complete multi-agent course generation pipeline:
- Phase 1 — Foundation deliberations (learning objectives, resource assessment, target audience, syllabus, assessment planning, final project)
- Phase 2 — Per-chapter development (slides, scripts, assessments via SlidesDeliberation)
- Phase 3 — Evaluation (Program Chair + Test Student review)
This is a long-running task — typically 20–60 minutes depending on model and number of chapters. Confirm scope with the user before launching.
When to invoke this skill
- User asks to generate a course / teaching materials / curriculum
- User provides a topic/subject and wants end-to-end output
- User wants to reproduce the paper's pipeline on new content
Do not invoke for:
- Just converting existing LaTeX → PPTX → use
latex-to-pptx - Only evaluating existing slides → use
slide-evaluate - Optimizing an existing slide chapter → (future:
slide-optimizeskill)
Prerequisites
pip install instructional-agentsOPENAI_API_KEYset in the environment- Disk space ~10–50 MB per course
Usage
python3 "${CLAUDE_PLUGIN_ROOT}/skills/course-generate/scripts/generate.py" \
--course "<course name>" \
[--model <model_name>] \
[--exp-name <tag>] \
[--catalog <catalog_name>] \
[--copilot <copilot_name>]Arguments
| Arg | Required | Description |
--course | yes | Course name/topic, e.g. "Reinforcement Learning" |
--model | no | LLM model (default: gpt-4o-mini) |
--exp-name | no | Subdirectory under exp/ (default: test) |
--catalog | no | Pre-loaded reference catalog name |
--copilot | no | Copilot mode with interactive feedback |
Example
python3 "${CLAUDE_PLUGIN_ROOT}/skills/course-generate/scripts/generate.py" \
--course "Introduction to Reinforcement Learning" \
--model gpt-4o \
--exp-name rl_undergrad_2026Output structure
exp/<exp-name>/
├── learning_objectives.md
├── resource_assessment.md
├── target_audience.md
├── syllabus.md
├── assessment_planning.md
├── final_project.md
├── chapter_1/
│ ├── slides.tex
│ ├── slides.pdf (if compiled)
│ ├── script.md
│ └── assessment.md
├── chapter_2/...
└── evaluation/
├── program_chair_review.md
└── test_student_review.mdFollow-up skills
After generation you typically want to run:
latex-compile→ produce PDFslatex-to-pptx→ produce editable PowerPoint (per chapter)slide-evaluate→ re-evaluate with different rubrics
Citation
This is the full pipeline from Instructional Agents (arXiv:2508.19611). Please cite if used in published work.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

