mdf-teaching-script-generator

中文文档

Generate runnable lesson-level MarkdownFlow teaching scripts from structured lesson materials with controlled interaction and reusable variable flow.

Use Cases

• Generate per-lesson MarkdownFlow prompts from pre-segmented course materials.
• Keep script structure stable while adapting content to each lesson.
• Reuse variables across lesson flow with explicit interaction checkpoints.

Boundaries

• This component generates lesson scripts only, not full course packaging.
• It does not rewrite source facts or change canonical teaching intent from upstream materials.
• It expects structured lesson input (already adapted/segmented).

Quickstart (3 minutes)

python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
mdf-teaching-script-generator --input examples/lesson_input.json --output output/lesson_output.json
python -m json.tool output/lesson_output.json | head -n 40

Minimal Runnable Example

Input: examples/lesson_input.json

Output includes:

• lesson_id
• lesson_title
• mdf_script
• used_variables
• depends_on_lessons

Architecture: Skill Core + Adapters

• Skill Core: src/mdf_teaching_script_generator/core.py
  • Platform-agnostic script generation from lesson JSON.
• CLI Adapter: src/mdf_teaching_script_generator/cli.py
  • Local runnable interface for automation pipelines.
• OpenClaw Adapter: adapters/openclaw
• Claude Adapter: adapters/claude
• Codex Adapter: adapters/codex

Multi-Agent Compatibility

• OpenClaw example: examples/openclaw_call.md
• Claude example: examples/claude_call.md
• Codex example: examples/codex_call.md

AI-Shifu Ecosystem

This repository is one reusable component in AI-Shifu's course production workflow.

• Website: https://ai-shifu.com

Development

pip install -e ".[dev]"
ruff check .
pytest -q