mcpField
L
lesson

lesson

github.com/cortexreachAgent workflows4.5k395 installsUpdated 1w ago
Repository

About lesson

A skill for extracting technical pitfalls and behavioral principles from recent conversation context and storing them in memory. It is intended for agents that need to preserve lessons, verify retrieval, and report what was saved.

Key features

  1. 01Extracts pitfalls and key insights
  2. 02Stores technical facts and principles
  3. 03Verifies entries with memory recall
  4. 04Reports saved lessons

Use cases

  1. 01Save a bug fix discussed in a conversation
  2. 02Record a reusable behavioral rule
  3. 03Check that stored lessons can be retrieved

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cortexreach/memory-lancedb-pro --skill lesson

After installing, type/lessonin Claude Code to confirm it loaded.

Details

From the project README

Lesson Extraction & Storage

When triggered, extract and store lessons from the recent conversation context.

Steps

  1. Scan recent context — identify the pitfall, bug fix, or key insight just discussed
  2. Store technical layer (category: fact, importance ≥ 0.8): 
    Pitfall: [symptom]. Cause: [root cause]. Fix: [solution]. Prevention: [how to avoid].
  3. Store principle layer (category: decision, importance ≥ 0.85): 
    Decision principle ([tag]): [behavioral rule]. Trigger: [when]. Action: [what to do].
  4. Verify — memory_recall with anchor keywords to confirm both entries retrievable
  5. Report — tell Master what was stored (brief summary)

Rules

  • Keep entries short and atomic (< 500 chars each)
  • If the lesson also affects a checklist or SKILL.md, update those files too
  • If no clear lesson is found in recent context, ask Master what to store

Comments

Markdown supported