Back to skills
SKILL.md
Continuous Learning V2
ASecurityUse when instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination. Triggers on \"continuous-learning-v2\", \"continuous learning v2\".
- 2 stars
- 0 votes
- 0 copies
- 1 view
- Added September 19, 2026
Works with
Security analysis
100/100Pro scans all 12 files and shows the line behind each finding
npx -y skills add majinmagros/magros.ai-skills --skill continuous-learning-v2 --agent claude-codeAre you the author of Continuous Learning V2?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/majinmagros-continuous-learning-v2)---
name: continuous-learning-v2
description: "Use when instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination. Triggers on \"continuous-learning-v2\", \"continuous learning v2\"."
metadata:
origin: ECC
version: 2.1.0
---
# Continuous Learning v2.1 - Instinct
-Based Architecture
An advanced learning system that turns your Claude Code sessions into reusable knowledge through atomic "instincts" - small learned behaviors with confidence scoring.
**v2.1** adds **project-scoped instincts** — React patterns stay in your React project, Python conventions stay in your Python project, and universal patterns (like "always validate input") are shared globally.
## When to Activate
- Setting up automatic learning from Claude Code sessions
- Configuring instinct-based behavior extraction via hooks
- Tuning confidence thresholds for learned behaviors
- Reviewing, exporting, or importing instinct libraries
- Evolving instincts into full skills, commands, or agents
- Managing project-scoped vs global instincts
- Promoting instincts from project to global scope
## What's New in v2.1
| Feature | v2.0 | v2.1 |
|---------|------|------|
| Storage | Global (`~/.claude/homunculus/`) | Project-scoped (`${XDG_DATA_HOME:-~/.local/share}/ecc-homunculus/projects/<hash>/`) |
| Scope | All instincts apply everywhere | Project-scoped + global |
| Detection | None | git remote URL / repo path |
| Promotion | N/A | Project → global when seen in 2+ projects |
| Commands | 4 (status/evolve/export/import) | 6 (+promote/projects) |
| Cross-project | Contamination risk | Isolated by default |
## What's New in v2 (vs v1)
| Feature | v1 | v2 |
|---------|----|----|
| Observation | Stop hook (session end) | PreToolUse/PostToolUse (100% reliable) |
| Analysis | Main context | Background agent (Haiku) |
| Granularity | Full skills | Atomic "instincts" |
| Confidence | None | 0.3-0.9 weighted |
| Evolution | Direct to skill | Instincts -> cluster -> skill/command/agent |
| Sharing | None | Export/import instincts |
## The Instinct Model
An instinct is a small learned behavior:
```yaml
---
id: prefer-functional-style
trigger: "when writing new functions"
confidence: 0.7
domain: "code-style"
source: "session-observation"
scope: project
project_id: "a1b2c3d4e5f6"
project_name: "my-react-app"
---
# Prefer Functional Style
## Split personal-vs-site (leva YouTube rodada 9)
Duas classes de licao: pessoal (como-eu-trabalho: markdown editavel, so licao duravel, nunca sai da maquina) vs site/compartilhada (como-o-site-funciona: ex. filtro escondido, cross-user). Promocao pessoal-para-global so com evidencia em 3+ sessoes. Para schedules/triggers pagos e MCP two-ways, registre custo e dono.
Files in this skill
- SKILL.md
- agents/observer-loop.sh
- agents/observer.md
- agents/session-guardian.sh
- agents/start-observer.sh
- config.json
- hooks/observe.sh
- scripts/detect-project.sh
- scripts/instinct-cli.py
- scripts/lib/homunculus-dir.sh
- scripts/migrate-homunculus.sh
- scripts/test_parse_instinct.py
Attribution
Comments
Loading comments…