Agent Skills › happycapy-ai/Happycapy-skills › capy-cortex

capy-cortex

GitHub

自主学习能力系统，通过SQLite和sklearn自动从错误中学习、反思会话并优化规则。提供手动命令用于健康检查、规则检索、添加偏好及模型重训练，实现知识的持续积累与智能提升。

skills/capy-cortex/SKILL.md happycapy-ai/Happycapy-skills

Trigger Scenarios

需要系统自动从历史交互中学习和改进时手动管理AI行为规则、反模式或用户偏好时对自主学习系统进行健康检查或重新训练时

Install

npx skills add happycapy-ai/Happycapy-skills --skill capy-cortex -g -y

More Options

Use without installing

npx skills use happycapy-ai/Happycapy-skills@capy-cortex

指定 Agent (Claude Code)

npx skills add happycapy-ai/Happycapy-skills --skill capy-cortex -a claude-code -g -y

安装 repo 全部 skill

npx skills add happycapy-ai/Happycapy-skills --all -g -y

预览 repo 内 skill

npx skills add happycapy-ai/Happycapy-skills --list

SKILL.md

Frontmatter

{
    "name": "capy-cortex",
    "description": "Autonomous learning system - learns from mistakes, reflects on sessions, and gets smarter over time. The AI brain."
}

Capy Cortex - Autonomous Learning System

You have a persistent learning brain powered by SQLite + FTS5 + sklearn TF-IDF. Knowledge is automatically loaded via hooks. This file describes manual operations.

Architecture

Database: ~/.claude/skills/capy-cortex/cortex.db (SQLite + FTS5 + WAL)
Hooks (automatic, never call manually):
- SessionStart: Loads anti-patterns, preferences, principles
- UserPromptSubmit: Retrieves task-relevant rules via FTS5
- PreToolUse(Bash): Blocks known dangerous commands
- PostToolUseFailure: Records errors as anti-patterns
- Stop: Extracts corrections and preferences from conversation
Scripts (for manual/scheduled use):
- cortex.py: Core engine (retrieve, add rules, stats)
- reflect.py: Deep session analysis
- consolidate.py: Cluster rules into principles (sklearn)
- bootstrap.py: Mine historical sessions

Manual Commands

# Check system health
python3 ~/.claude/skills/capy-cortex/scripts/cortex.py stats

# Retrieve rules for a topic
python3 ~/.claude/skills/capy-cortex/scripts/cortex.py retrieve "react typescript"

# Add a rule manually
python3 ~/.claude/skills/capy-cortex/scripts/cortex.py add-rule "Always use TypeScript strict mode" "best_practice"

# Add an anti-pattern
python3 ~/.claude/skills/capy-cortex/scripts/cortex.py add-ap "Never force push to main" "critical"

# Add a preference
python3 ~/.claude/skills/capy-cortex/scripts/cortex.py add-pref "User prefers functional components over class components"

# Run consolidation (clusters rules into principles)
python3 ~/.claude/skills/capy-cortex/scripts/consolidate.py

# Retrain TF-IDF model
python3 ~/.claude/skills/capy-cortex/scripts/cortex.py retrain

# Apply confidence decay
python3 ~/.claude/skills/capy-cortex/scripts/cortex.py decay

How It Learns

Automatic (via hooks): Errors are captured, corrections noted, preferences extracted
Reflection: Deep analysis of session transcripts extracts patterns
Consolidation: sklearn clustering groups similar rules into principles
Decay: Old, unreinforced rules fade; validated rules strengthen
Retrieval: Two-stage FTS5 + TF-IDF returns only relevant knowledge (O(1) context)