self-improving-agent
Universal self-improving agent that learns from all skill experiences using multi-memory architecture.
What it does
- 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 (beforestart, aftercomplete, onerror)
- Evolution Markers: Traceable changes with source attribution
- User says "自我进化", "self-improve", "从经验中学习"
- User says "分析今天的经验", "总结教训"
Requirements & configuration
- | "Net APY position ambiguous" | "UI specs need exact relative positions" | prd-planner |
- | CLI/runtime code | Automation semantics | Require tests |
- If you need manual setup, add hook entries to Claude Code settings at the
Configuration: SKILLAGENTSTOOL_NAMETOOL_INPUTTOOL_OUTPUTEXIT_CODE
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
Universal self-improving agent that learns from all skill experiences using multi-memory architecture.
Source
Repository: https://github.com/charon-fan/agent-playbook
self-improving-agent FAQ
What does the self-improving-agent skill do?
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction. Multi-Memory Architecture: Semantic + Episodic + Working memory Self-Correction: Detects and fixes skill guidance errors
What does self-improving-agent require?
| "Net APY position ambiguous" | "UI specs need exact relative positions" | prd-planner | | CLI/runtime code | Automation semantics | Require tests | If you need manual setup, add hook entries to Claude Code settings at the Configuration keys: SKILL, AGENTS, TOOL_NAME, TOOL_INPUT, TOOL_OUTPUT, EXIT_CODE.
How do I install self-improving-agent?
Run: npx -y skills add https://github.com/charon-fan/agent-playbook --skill self-improving-agent --agent claude-code — the source lives at github.com/charon-fan/agent-playbook.
Maintain self-improving-agent?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/charon-fan-agent-playbook-self-improving-agent?ref=badge) npx agentictools info skills/charon-fan-agent-playbook-self-improving-agent The second line is the CLI lookup for this page — handy in READMEs and docs.
Related skills
ckm:slides Agent skill from nextlevelbuilder/ui-ux-pro-max-skill.
byted-web-search Agent skill from skills.volces.com.
golang-how-to Agent skill from samber/cc-skills-golang.
weread-skills Agent skill from tencent/wechatreading.
setup-ts-deep-modules Agent skill from mattpocock/skills.
gsap-plugins Complete toolkit for GSAP plugins: scroll, DOM layout, dragging, text splitting, SVG morphing, easing, and physics.