self-improving-agent
Universal self-improving agent that learns from all skill experiences using multi-memory architecture.
- Implements semantic, episodic, and working memory to extract patterns, abstract insights, and continuously evolve skill guidance across the codebase
- Auto-triggers on skill completion, errors, and session events via hooks-based integration; detects and corrects inaccurate guidance with traceable evolution markers
- Prioritizes updates across 10+ skill categories (PRD planning, architecture, API design, debugging, code review, performance, security, testing, deployment) based on pattern confidence and application frequency
- Consolidates feedback loops with user ratings, root cause analysis, and validation workflows to prevent over-generalization and maintain guidance accuracy
Self-Improving Agent
"An AI agent that learns from every interaction, accumulating patterns and insights to continuously improve its own capabilities." — Based on 2025 lifelong learning research
Overview
This is a universal self-improvement system that learns from ALL skill experiences, not just PRDs. It implements a complete feedback loop with:
- Multi-Memory Architecture: Semantic + Episodic + Working memory
- Self-Correction: Detects and fixes skill guidance errors
- Self-Validation: Periodically verifies skill accuracy
- Hooks Integration: Auto-triggers on skill events (before_start, after_complete, on_error)
- Evolution Markers: Traceable changes with source attribution
Research-Based Design
Based on 2025 research:
More from charon-fan/agent-playbook
planning-with-files
Uses persistent markdown files for general planning, progress tracking, and knowledge storage (Manus-style workflow). Use for multi-step tasks, research projects, or general organization WITHOUT mentioning PRD. For PRD-specific work, use prd-planner skill instead.
752security-auditor
Security vulnerability expert covering OWASP Top 10 and common security issues. Use when conducting security audits or reviewing code for vulnerabilities.
748skill-router
Intelligently routes user requests to the most appropriate Claude Code skill. ALWAYS use this skill FIRST when user asks for help, mentions "skill", "which", "how to", or seems unsure about which approach to take. This is the default entry point for all skill-related requests.
636architecting-solutions
Designs technical solutions and architecture. Use when user says "design solution", "architecture design", "technical design", or "方案设计" WITHOUT mentioning PRD. For PRD-specific work, use prd-planner skill instead.
613test-automator
Test automation framework expert for creating and maintaining automated tests. Use when user asks to write tests, automate testing, or improve test coverage.
583prd-planner
Creates PRDs using persistent file-based planning. Use when user explicitly says "PRD", "product requirements document", or "产品需求文档". Combines PRD methodology with planning-with-files to avoid context switching.
564