Continuous Learning V2 — Development skill for Claude Code
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
How to install Continuous Learning V2
Installs to ~/.claude/skills/rustidi-ml-portfolio-continuous-learning-v2/SKILL.md
mkdir -p ~/.claude/skills/rustidi-ml-portfolio-continuous-learning-v2 && curl -fsSL https://raw.githubusercontent.com/rustidi/ml-portfolio/HEAD/skills/continuous-learning-v2.md -o ~/.claude/skills/rustidi-ml-portfolio-continuous-learning-v2/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Continuous Learning V2 does
name: continuous-learning-v2 description: 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. 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 behavior
Alternatives in Development
- Claudeception — A Claude Code skill for autonomous skill extraction and continuous learning 2.2k ★
- Instinct Export — Export instincts from project/global scope to a file 1.9k ★
- Continuous Claude — Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Unity Instincts
Manage the project's instinct library — view, promote, evolve, export, or import atomic learned behaviors capt
Harvest
Harvest friction events from observation logs into typed instincts (env_issue, permission_block, wrong_approac
Instinct Import
从文件或 URL 导入直觉(Instincts)到项目/全局作用域
Instill
Use when distilling instincts or reusable rules from the current session. Extracts compact patterns from conve
Agent Instincts
Show the learned instinct overlay for a specific agent, or list all overlays with instinct counts.
Continuous Improvement
Reflect on the current session, analyze observations for patterns, and show instinct status. Runs on-demand to
Related Agents
Adaptive Mentor
Dynamic learning style optimization with real-time pedagogical adaptation. Provides personalized mentoring tha
Learning Adapter
Use this agent for dynamic improvement through experience and feedback. Specializes in continuous learning, st
Gagarin CI
Wires a repository's CI pipeline to deploy to Gagarin Cloud on push — mints a scoped deploy credential, stores