Document-first development. Automate only what's proven.
| K-Line | Why Related |
|---|---|
| moollm/ | Core MOOLLM methodology |
| play-learn-lift/ | Sister scripts ARE the LIFT stage output |
| skill/ | Sister scripts become skills |
| sniffable-python/ | Sister scripts follow this structure |
| plain-text/ | Scripts persist as files |
| yaml-jazz/ | Comments carry meaning |
| constructionism/ | Document → Procedure → Automation |
| postel/ | Liberal input, conservative output |
| debugging/ | Document how you debugged |
Quick Links:
- Full Specification — complete protocol
- Template: PROCEDURE.md — procedure template
- Template: SISTER.yml — script relationship
The document is the source of truth. Scripts are its children. This is the LIFT stage of play-learn-lift.
Sister scripts follow sniffable-python conventions — structured so both humans and LLMs can understand them from the first 50 lines.
📄 Document → 💻 Commands → 📋 Procedure → 🤖 Sister Script (Sniffable Python)
- Start with natural language (PLAY)
- Add manual commands (PLAY/LEARN)
- Document working procedures (LEARN)
- Generate automation (LIFT) → sniffable-python format
Sister scripts should be structured so the LLM can sniff the header:
#!/usr/bin/env python3
"""tool-name: One-line description.
Docstring becomes --help AND is visible to LLM.
"""
import argparse
def main():
"""CLI structure — sniff this to understand the tool."""
parser = argparse.ArgumentParser(description=__doc__.split('\n')[0])
# ... CLI tree here ...One sniff and you smell success.
- Document → Script: Proven procedures become automated
- Script → Document: Automation insights improve docs