Commands: - /learn:analyze - Analyze conversation for patterns and gotchas - /learn:import - Import from other memory files (auto-build-memory.md, JSON) - /learn:reflect - Consolidate and clean memory - /learn:status - Show memory statistics Features: - Stop hook suggests /learn:analyze after significant sessions - Uses single memory file: .claude/rules/claude-learn-memory.md - Structured format for patterns (solutions) and gotchas (problems) - Import support for migrating existing memories 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
1.3 KiB
1.3 KiB
Claude Learn Plugin
This is the main plugin directory. For installation and usage instructions, see the main README.
Plugin Structure
plugin/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── commands/
│ ├── analyze.md # /learn:analyze command
│ ├── import.md # /learn:import command
│ ├── reflect.md # /learn:reflect command
│ └── status.md # /learn:status command
├── hooks/
│ └── hooks.json # Stop hook configuration
├── rules/
│ └── memory-format.md # Memory file format spec
├── templates/
│ └── memory-entry.json # JSON templates
└── README.md # This file
Development
To test locally:
claude --plugin-dir /path/to/claude-learn/plugin
Commands Overview
/learn:analyze
Analyzes the current conversation and proposes patterns/gotchas to save.
/learn:import
Imports memories from other files (auto-build-memory.md, JSON, etc.)
/learn:reflect
Consolidates duplicates, promotes frequent patterns to CLAUDE.md.
/learn:status
Shows memory statistics and suggestions.
Hook
The Stop hook triggers after significant conversations, suggesting /learn:analyze when appropriate.