← Back to Skills Marketplace
474
Downloads
0
Stars
4
Active Installs
2
Versions
Install in OpenClaw
/install self-improve
Description
A pluggable self-improvement framework for AI agents. Automatically learns from mistakes, corrections, and feedback to continuously improve execution quality...
Usage Guidance
This skill contains many local Node scripts that will read and write files under whatever storage root you configure — including the ability to create directories, add cron tasks, and propose changes that can be applied to system files (AGENTS.md, SKILL.md, openclaw.json, etc.). Before installing or running it: 1) Inspect setup.mjs and any code that modifies cron or writes to openclaw.json to understand exactly what will be changed. 2) Ensure user-config.yaml storage.root and knowledge_root point to an isolated directory you control (not the global .openclaw, agent home, or system config directories). 3) Run the skill in a sandbox or test environment first. 4) Confirm that the approval workflow actually prevents automatic writes to critical system files (review scripts that perform 'execution' after approval). 5) Limit filesystem permissions for the directory the skill uses so it cannot accidentally overwrite global agent configs. If you cannot audit the setup & execution scripts yourself, avoid enabling cron/automatic runs or limit the skill to manual invocations only.
Capability Analysis
Type: OpenClaw Skill
Name: self-improve
Version: 2.2.1
The 'self-improve' bundle is a comprehensive framework designed to allow OpenClaw agents to learn from user feedback and session logs. It implements a multi-tiered memory system (HOT/WARM/COLD) and an approval-based workflow for modifying system configurations. While the system possesses high-privilege capabilities, such as scanning workspace logs and proposing Cron tasks (via setup.mjs and ENGINE.md), these actions are transparently documented and aligned with the stated goal of autonomous self-improvement. No evidence of data exfiltration, unauthorized persistence, or malicious prompt injection was found.
Capability Assessment
Purpose & Capability
The name/description match the included scripts: they scan feedback, distill rules, maintain HOT/WARM/COLD memories, propose changes, and can create/maintain knowledge files. That capability set is coherent with a self-improvement framework. However the skill is explicitly designed to operate at a system/shared scope (engine text: scanning '/path/to/self-improve' and 'read each agent's session logs (if accessible)') and to write system files (AGENTS.md, openclaw.json, SKILL.md) when proposals are 'solidified'. Those system-level operations are more powerful than a purely local/self-contained improvement tool and warrant caution.
Instruction Scope
SKILL.md and ENGINE.md instruct the agent to run setup, register a cron entry, scan memory logs, and propose or write to system files. The scripts will read and write many files under the configured SELF_IMPROVE_ROOT (feedback, corrections, hot/warm/cold memory, proposals). The framework also states it can create new directories/files without asking and that only 'solidification' requires confirmation — but many non-system outputs are written automatically. If the configured storage paths point to shared/global agent directories (e.g., .openclaw, /path/to/learned, or root of agent system), the skill will read other agents' logs and write to system files, which goes beyond a narrowly scoped tool.
Install Mechanism
No install spec — instruction-only. That reduces supply-chain risk, but the package includes runnable Node.js scripts (setup.mjs, run scripts). Running these local scripts will execute code on disk (no external downloads), so risk shifts to runtime file operations rather than package download vectors.
Credentials
The skill requests no environment variables or external credentials (good). But it relies entirely on user-configured paths (user-config.yaml / storage.root / knowledge_root / workspace_root). Those path settings control what the skill reads/writes; if mis-set to global/system locations, the skill gains broad access. The number of required env/creds is proportionate, but the path configuration gives it broad potential reach.
Persistence & Privilege
always:false (normal), and the skill is user-invocable and can be autonomously invoked by the agent. More importantly, SKILL.md/ENGINE.md state the setup writes a Cron entry (and mentions writing a prompt to Cron configuration), and the framework can create directories/files and update indexes automatically. Combined, these grant the skill persistent, periodic execution and the ability to modify system/shared files — a significant privilege if storage paths are global.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install self-improve - After installation, invoke the skill by name or use
/self-improve - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.2.1
Update installation instructions for ClawHub
v2.2.0
Self-Improve 2.2.0 introduces a clearer framework overview and improved setup instructions.
- Expanded documentation with detailed usage, memory tiers, and workflow explanations.
- Added step-by-step installation and configuration guidance.
- Enhanced description of when and how self-improvement runs (cron, manual, post-event).
- Clarified directory structure and file roles.
- Specified dependencies and approval workflow for proposed improvements.
Metadata
Frequently Asked Questions
What is Self-Improve?
A pluggable self-improvement framework for AI agents. Automatically learns from mistakes, corrections, and feedback to continuously improve execution quality... It is an AI Agent Skill for Claude Code / OpenClaw, with 474 downloads so far.
How do I install Self-Improve?
Run "/install self-improve" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Self-Improve free?
Yes, Self-Improve is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Self-Improve support?
Self-Improve is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Self-Improve?
It is built and maintained by Don Li (@don068589); the current version is v2.2.1.
More Skills