self-improving-systems
SkillDecide whether your agent actually needs persistent memory, feedback loops, or closed-loop learning, then design the smallest thing that pays for itself. Use when the user says "add memory", "give my agent context management", "make my agent learn", "self-improving / closed-loop", "Reflexion / mem0
Install
git clone https://github.com/ooiyeefei/ccc.git ~/.claude/skills/self-improving-systemsWhat is self-improving-systems?
Decide whether your agent actually needs persistent memory, feedback loops, or closed-loop learning, then design the smallest thing that pays for itself. Use when the user says "add memory", "give my agent context management", "make my agent learn", "self-improving / closed-loop", "Reflexion / mem0 / Letta / MemGPT", "AriGraph", "agent memory architecture", "long-term memory for chatbot", "why does my agent keep forgetting / making the same mistake", "fine-tune from agent traces", or asks for a memory schema / experience store / reward model. Filters ruthlessly — most teams want a state cache, not memory + learning. Default position is scratchpad-only with a stateless agent shipped first.
What this can do
Capabilities declared in this component's own frontmatter — not inferred.
Inherit all session tools
Declares no tool restrictions — inherits every session tool
~174 tokens of context used while enabled, before you invoke anything
Documentation
README · ~13 min readSelf-Improving Systems
A prescriptive Q&A skill for adding memory, feedback loops, and closed-loop learning to agentic systems — only when justified.
Headline message: most agents shouldn't have persistent memory.
Memory is a liability surface (drift, poisoning, debugging difficulty, GDPR/HIPAA exposure). Persistent memory is the second move, not the first. The skill's job is to filter ruthlessly so the user doesn't ship a mem0/Letta build for a problem that a 200-line conversation summary would solve.
The first 2 stages of the Q&A flow exist to stop most users from over-engineering. By the end of stage 2, ~60% of users will discover they want a state cache (or stateless RAG), not memory + learning. That's the win.
Quick Start
User just asks:
"Add memory to my agent"
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just skills.
Skillssimilar to this one
All skills →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
235.3K stars
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
88.9K stars
mem0
Universal memory layer for AI Agents
62K stars
Subagents
All subagents →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
235.3K stars
architecture-critic
Reviews proposed target architectures and transformed code against modern best practice. Adversarial — looks for over-engineering, missed requirements, and simpler alternatives.
32.8K stars
patch-generator
Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.
32.8K stars
MCP Servers
All mcp servers →codebase-memory-mcp
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
36.7K stars
notion-mcp-server
Official Notion MCP Server
4.6K stars
dbhub
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
3.3K stars
Plugins
All plugins →claude-md-management
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
32.9K stars
hookify
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
32.9K stars
feature-dev
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
32.9K stars
Commands
All commands →feature-dev
Guided feature development with codebase understanding and architecture focus
32.8K stars
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests
32.8K stars
modernize-extract-rules
Mine business logic from legacy code into testable, human-readable rule specifications
32.8K stars
Hooks
All hooks →PostToolUse (mcp__.*__find_columns|mcp__.*__get_dataset_columns|mcp__.*__get_dataset)
Pre-query column validation via schema caching. Catches unknown column errors before they hit the API by building a per-session schema cache from find_columns / get_dataset_columns / get_dataset results.
PreToolUse (mcp__.*__run_query)
Pre-query column validation via schema caching. Catches unknown column errors before they hit the API by building a per-session schema cache from find_columns / get_dataset_columns / get_dataset results.