How does confidence scoring work?

Instincts start with a low confidence score (0.3) and increase as patterns are repeatedly observed and accepted by the user, eventually reaching a 'near-certain' level (0.9).

Is my code shared or uploaded externally?

No, all observations and instincts are stored locally on your machine. The system analyzes patterns locally using a background agent to ensure privacy.

Can I share my learned instincts with teammates?

Yes, the skill includes /instinct-export and /instinct-import commands to allow users to share or migrate their learned instinct libraries between machines.

How does the system capture information?

It uses deterministic hooks (PreToolUse and PostToolUse) to capture 100% of session activity, ensuring every tool call and correction is analyzed for pattern detection.

What are project-scoped instincts?

Project-scoped instincts are behaviors isolated to a specific repository, ensuring that React-specific patterns in one project don't interfere with Python conventions in another.

Continuous Learning v2

Name: Continuous Learning v2
Author: hieuck

byhieuck

0•

Herramientas para Desarrolladores

Automates the extraction of project-specific and global coding patterns into reusable instincts and skills through deterministic session observation.

Continuous Learning v2 is an advanced instinct-based learning system for Claude Code that captures developer patterns, error resolutions, and specific preferences in real-time. By utilizing deterministic hooks and an background AI observer, it builds a library of confidence-weighted 'instincts' that evolve into structured skills or agents. Version 2.1 introduces sophisticated project-scoping, ensuring that specific framework conventions remain isolated to relevant repositories while universal best practices, such as security and git workflows, are promoted to a global scope for use across all your development environments.

Características Principales

01Atomic instinct system with confidence-weighted behavior scoring

02Project-scoped isolation to prevent cross-project pattern contamination

03Deterministic PreToolUse and PostToolUse hooks for 100% reliable session capture

04Automatic evolution of raw observations into structured skills, commands, and agents

05Promotion engine to upgrade high-confidence project patterns to global defaults

060 GitHub stars

Casos de Uso

01Migrating learned developer behaviors across different machines via instinct export/import

02Personalizing Claude’s coding style based on past corrections and preferred patterns

03Automatically capturing unique codebase conventions without manual documentation

Características Principales

01Atomic instinct system with confidence-weighted behavior scoring

02Project-scoped isolation to prevent cross-project pattern contamination

03Deterministic PreToolUse and PostToolUse hooks for 100% reliable session capture

04Automatic evolution of raw observations into structured skills, commands, and agents

05Promotion engine to upgrade high-confidence project patterns to global defaults

060 GitHub stars

Casos de Uso

01Migrating learned developer behaviors across different machines via instinct export/import

02Personalizing Claude’s coding style based on past corrections and preferred patterns

03Automatically capturing unique codebase conventions without manual documentation