| name | source-command-learn-explain |
| description | Recursively deep-dive into a concept — AI explains, guides thinking, you choose the depth |
source-command-learn-explain
Use this skill when the user asks to run the migrated source command learn-explain.
Command Template
Use the learn-anything-explain skill to handle the user's /learn-explain request.
Follow the workflow defined in the skill:
- Load context: match topic → read state.json (single source of truth, do NOT read knowledge-map.md)
- Assess user level (beginner/intermediate/advanced) and adjust teaching strategy
- Compose the full explanation: positioning → analogy → core mechanism → code example → common misconceptions → Socratic check
- CRITICAL — Write the session file FIRST (./.learn/topics//sessions//-YYYY-MM-DD.md, where comes from state.json, matching the user's language), then echo the file content verbatim to the conversation. Also update state.json with Edit (last_explained, explain_count, status, confidence). Then run render.mjs to regenerate knowledge-map.md.
- Identify sub-topics as recursive entry points (only AFTER saving the session and echoing to conversation)