Continuous Learning

This is the deprecated v1 version that runs a Stop hook at session end to extract reusable patterns from your Claude Code conversations and save them as learned skills. It checks if your session hit a minimum message count, identifies patterns like error resolutions or user corrections, and writes them to your learned skills directory. The v2 version is what you actually want now since it uses PreToolUse/PostToolUse hooks for 100% reliable observation instead of probabilistic skill firing, plus it breaks learning into atomic instincts with confidence scoring rather than full skills. This v1 is kept around for backward compatibility and archival reference, but route new continuous learning work to v2.

skills.sh installs: 5.5K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill continuous-learning --agent claude-code

Installs into .claude/skills of the current project.

Files

Continuous Learning Skill - DEPRECATED

DEPRECATED 2026-04-28. Use continuous-learning-v2 instead. v2 is a strict superset: stop-hook observation becomes PreToolUse/PostToolUse observation, full skills become atomic instincts with confidence scoring, and global-only storage becomes project-scoped plus global promotion.

This file is kept for archival reference and backward compatibility with existing installs.

Original v1 Documentation (archival)

Automatically evaluates Claude Code sessions on end to extract reusable patterns that can be saved as learned skills.

When to Activate

Setting up automatic pattern extraction from Claude Code sessions
Configuring the Stop hook for session evaluation
Reviewing or curating learned skills in ~/.claude/skills/learned/
Adjusting extraction thresholds or pattern categories
Comparing v1 (this) vs v2 (instinct-based) approaches

Status

This v1 skill is still supported, but continuous-learning-v2 is the preferred path for new installs. Keep v1 when you explicitly want the simpler Stop-hook extraction flow or need compatibility with older learned-skill workflows.