continuous-learning-v2
Lets the agent learn from interactions and create new skills. It's useful for improving the agent's performance over time.
What it does
This system learns from your AI conversations. It identifies patterns in your work and turns them into 'instincts' - small tips on how to do something. Over time, these instincts can become more complete tools.
When to use it
- ✓When you want the AI to learn from your coding sessions.
- ✓To organize and reuse AI learnings.
- ✓To turn useful tips into automatic commands or skills.
Example of what to ask your AI
“Turn my code sessions into reusable learnings.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The AI observes your interactions, identifies repeated patterns or corrections you make. It saves these patterns as 'instincts' with a confidence score. These instincts can be grouped and turned into larger skills.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add affaan-m/ECC --skill continuous-learning-v2Or download just the file:
curl -L https://raw.githubusercontent.com/affaan-m/ECC/main/skills/continuous-learning-v2/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
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:
---
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
## Action
Use functional patterns over classes when appropriate.
## Evidence
- Observed 5 instances of functional pattern preference
- User corrected class-based approach to functional on 2025-01-15
Properties:
- Atomic -- one trigger, one action
- Confidence-weighted -- 0.3 = tentative, 0.9 = near certain
- Domain-tagged -- code-style, testing, git, debugging, workflow, etc.
- Evidence-backed -- tracks what observations created it
- Scope-aware --
project(default) orglobal
How It Works
Session Activity (in a git repo)
|
| Hooks capture prompts + tool use (100% reliable)
| + detect project context (git remote / repo path)
v
+---------------------------------------------+
| projects/<project-hash>/observations.jsonl |
| (prompts, tool calls, outcomes, project) |
+---------------------------------------------+
|
| Observer agent reads (background, Haiku)
v
+---------------------------------------------+
| PATTERN DETECTION |
| * User corrections -> instinct |
| * Error resolutions -> instinct |
| * Repeated workflows -> instinct |
| * Scope decision: project or global? |
+---------------------------------------------+
|
| Creates/updates
v
+---------------------------------------------+
| projects/<project-hash>/instincts/personal/ |
| * prefer-functional.yaml (0.7) [project] |
| * use-react-hooks.yaml (0.9) [project] |
+---------------------------------------------+
| instincts/personal/ (GLOBAL) |
| * always-validate-input.yaml (0.85) [global]|
| * grep-before-edit.yaml (0.6) [global] |
+---------------------------------------------+
|
| /evolve clusters + /promote
v
+---------------------------------------------+
| projects/<hash>/evolved/ (project-scoped) |
| evolved/ (global) |
| * commands/new-feature.md |
| * skills/testing-workflow.md |
| * agents/refactor-specialist.md |
+---------------------------------------------+
Project Detection
The system automatically detects your current project:
…
FAQ
What are 'instincts'?
They are small lessons the AI learns about how you do things, like preferring a coding style or a way to solve a problem. They have a confidence score to indicate how sure the AI is about that learning.
How does the AI know which project I'm working on?
It checks if you are using a Git repository or a specific environment variable to identify the project. This ensures that learnings from one project don't mix with those from another.
Can I use my learnings in other projects?
Yes. Instincts that are useful across multiple projects can be promoted from a project scope to a global scope, making them available anywhere.
Details
Original description by the author
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. Use when capturing lessons from a session, managing instincts, or promoting them into skills, commands, or agents.
repo: affaan-m/ECC
Popularity
- GitHub stars
- 280k
- Ranking position
- #162
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
accessibility
Helps your agent create interfaces that everyone can use. Ensures websites and apps work well for people with disabilities, like those who are blind or have reduced mobility.
affaan-m/ECC
agent-architecture-audit
Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.
affaan-m/ECC
agent-eval
Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.
affaan-m/ECC
agent-harness-construction
Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.
affaan-m/ECC
Similar skills
mcp-builder
Helps your agent create servers that connect LLMs to external services. Essential for integrating APIs and services using Python or Node/TypeScript.
anthropics/skills
prepare-mcp-integration
Prepares vendor (MCP) integrations through research and human approval. It follows a guided process for new integrations.
paperclipai/paperclip
first-task
Guides the agent on the user's first task. It interprets the initial answer, clarifies the goal, and proposes a plan or single task for approval.
paperclipai/paperclip