Skip to content
Back to skills

Continuous Learning V2

ASecurity

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\".

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 19, 2026
ai-agentspythongoreactgit

Works with

  • claude code
  • mcp

Security analysis

A100/100

Pro scans all 12 files and shows the line behind each finding

Scanned September 19, 2026

npx -y skills add majinmagros/magros.ai-skills --skill continuous-learning-v2 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Continuous Learning V2?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Continuous Learning V2
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-continuous-learning-v2/badge)](https://www.skillsdirectory.com/skills/majinmagros-continuous-learning-v2)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
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.md2.8 KB
  • agents/observer-loop.sh13.2 KB
  • agents/observer.md6.7 KB
  • agents/session-guardian.sh6.2 KB
  • agents/start-observer.sh7.9 KB
  • config.json135 B
  • hooks/observe.sh22.5 KB
  • scripts/detect-project.sh10.8 KB
  • scripts/instinct-cli.py87.6 KB
  • scripts/lib/homunculus-dir.sh1010 B
  • scripts/migrate-homunculus.sh2.2 KB
  • scripts/test_parse_instinct.py50.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…