Scans .learnings/ entries for recurring error patterns and suggests promotions. Use when: "scan patterns", "check recurrence", "review learnings", "promote learnings", "掃描 pattern", "檢查重複", "查看學習記錄", or after logging an error to .learnings/.
Use when user says "回顧修正", "整理 feedback", "session reflect", or wants to review current session corrections and update skills, rules, or memory.
Claude Code plugin for automatic error detection and recurring pattern tracking.
.learnings/ directory with Pattern-Key matching| Skill | Description |
|---|---|
/self-improving:session-reflect | Review current session corrections and update skills, rules, or memory |
/self-improving:pattern-scan | Scan .learnings/ entries for recurring patterns and suggest promotions |
Project-level .learnings/ directory (cross-tool compatible):
<project-root>/
└── .learnings/
├── LEARNINGS.md # Corrections, knowledge gaps, best practices
└── ERRORS.md # Command failures, exceptions
Add to ~/.claude/plugins/known_marketplaces.json:
"self-improving-local": {
"source": {
"source": "directory",
"path": "/path/to/self-improving"
}
}
Then install:
claude plugin install self-improving@self-improving-local
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub yulin0629/self-improving --plugin self-improvingComprehensive guide for installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use
Self-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically
Self-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically
Intelligent command history tracking with automatic failure detection. Tracks all bash commands Claude runs (successful and failed) with semantic directory aliasing and command mapping.
Operational memory for coding agents: recall past mistakes before you act, encode the lesson when something goes wrong.
Meta-Cognition tool for Claude Code with 22 MCP tools for session history analysis, error tracking, quality scanning, work patterns, timelines, and bug detection. Focused, fast, and data-driven.
Session feedback analysis - capture skill bugs, enhancements, and positive patterns as GitHub issues
Intelligent error tracking and solution recall system. Learns from every error you solve, providing instant access to past solutions with multi-level matching and confidence scores.