ClaudeSuperPower

self-improving-systems

Skill

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

Install

git clone https://github.com/ooiyeefei/ccc.git ~/.claude/skills/self-improving-systems

What 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 read

Self-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.