← Back to Skills Marketplace
15132
Downloads
11
Stars
129
Active Installs
1
Versions
Install in OpenClaw
/install self-improving-proactive-agent
Description
A unified OpenClaw skill that merges self-improvement and proactivity: learn from corrections, maintain active state, recover context fast, and keep work mov...
Usage Guidance
Install this if you want an agent to keep local preference, correction, and task-state notes across sessions. Review the ~/self-improving/ and ~/proactivity/ files periodically, avoid putting secrets there, and approve any edits to workspace steering files before relying on them.
Capability Assessment
Purpose & Capability
The stated purpose is self-improvement, context recovery, and proactive follow-through; the artifact contents consistently support that purpose.
Instruction Scope
It instructs the agent to update local memory and heartbeat state, but also says to ask before messaging others, spending money, deleting data, publishing, committing, scheduling, or changing unrelated files.
Install Mechanism
The package contains only markdown files, declares no required binaries, and includes no executable scripts, dependencies, or install-time commands.
Credentials
The skill uses disclosed local paths under ~/self-improving/ and ~/proactivity/, with optional workspace steering files such as AGENTS.md only for user-wanted integration.
Persistence & Privilege
Persistent local memory is central to the skill and can influence future agent behavior, but this is disclosed and bounded by instructions not to store credentials or secrets.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install self-improving-proactive-agent - After installation, invoke the skill by name or use
/self-improving-proactive-agent - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release. Combines self-improvement and proactivity into one unified OpenClaw skill.
Metadata
Frequently Asked Questions
What is Self-Improving Proactive Agent?
A unified OpenClaw skill that merges self-improvement and proactivity: learn from corrections, maintain active state, recover context fast, and keep work mov... It is an AI Agent Skill for Claude Code / OpenClaw, with 15132 downloads so far.
How do I install Self-Improving Proactive Agent?
Run "/install self-improving-proactive-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Self-Improving Proactive Agent free?
Yes, Self-Improving Proactive Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Self-Improving Proactive Agent support?
Self-Improving Proactive Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Self-Improving Proactive Agent?
It is built and maintained by Yueyanc (@yueyanc); the current version is v1.0.0.
More Skills