continuous-learning-v2

name	continuous-learning-v2
description	Cross-session instinct learning with confidence-based promotion and global scope
version	0.1.0
level	3
triggers	["/instinct-status","/instinct-export","/instinct-import","/evolve","learned patterns","session observations"]
context_files	["context/learnings.md","context/project.md"]
steps	[{"name":"Load Instincts","description":"Read project instincts from ~/.claude/homunculus/"},{"name":"Filter by Domain/Confidence","description":"Apply filters if specified"},{"name":"Display or Modify","description":"List, add, apply, or promote instincts"},{"name":"Update Storage","description":"Persist changes to JSON with atomic writes"},{"name":"Evaluate for Promotion","description":"Check if confidence >= 0.8 for global promotion"},{"name":"Cluster into Skills","description":"Group related instincts for /evolve command"}]

Continuous Learning v2 Skill

Cross-session learning system that captures behavioral patterns as instincts with confidence scoring and automatic promotion to global scope.

What Claude Gets Wrong Without This Skill

Without continuous learning, Claude:

1. Rewrites skills manually instead of learning from patterns
2. Forgets project-specific patterns between sessions
3. Cannot differentiate high-confidence vs low-confidence patterns
4. Applies one-size-fits-all rules instead of context-specific instincts
5. Has no path for local instincts to become global best practices

Continuous learning tracks what works, increases confidence with successful applications, and promotes proven patterns globally.

The Instinct System

Instinct: Atomic behavioral unit with trigger (when), action (what), and confidence (0.0-1.0).

Example:

{
  "id": "inst_001",
  "trigger": "writing test file",
  "action": "colocate test next to source (src/user.ts -> src/user.test.ts)",
  "confidence": 0.85,
  "domain": "testing",
  "evidence": ["2026-03-28: Created tests/user.test.ts next to src/user.ts"],
  "scope": "project",
  "apply_count": 12
}