← Back to Skills Marketplace
2770
Downloads
0
Stars
53
Active Installs
1
Versions
Install in OpenClaw
/install self-improving-1-2-10
Description
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use befo...
Usage Guidance
Install only if you want the agent to keep local cross-session memory about corrections, preferences, and work patterns. Review any AGENTS.md, SOUL.md, or HEARTBEAT.md changes before applying them, avoid storing secrets or sensitive personal data, periodically inspect ~/self-improving/, and confirm whether you want an export before using any full-wipe command.
Capability Assessment
Purpose & Capability
The artifacts consistently implement the stated purpose: self-reflection, learning from corrections, and local memory organization under ~/self-improving/.
Instruction Scope
Activation and memory commands are broad, but the files also document ignore cases, namespace limits, source citation, sensitive-data exclusions, and confirmation for permanent or destructive changes.
Install Mechanism
Setup creates local files and optionally edits AGENTS.md, SOUL.md, and HEARTBEAT.md, but there are no executable scripts, dependency installs, hidden installers, or network calls.
Credentials
Requested access is limited to the skill's own local memory directory and optional agent steering files; the skill explicitly says not to read outside ~/self-improving/ or access calendar, email, contacts, or network resources.
Persistence & Privilege
Cross-session persistence is central and disclosed. Users should still review retention, export, and deletion behavior, especially the export-before-wipe wording in boundaries.md.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install self-improving-1-2-10 - After installation, invoke the skill by name or use
/self-improving-1-2-10 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Sharper setup: now lists relevant memory before starting non-trivial work, emphasizing proactive self-reflection.
- Title updated to highlight proactive self-reflection as a core feature.
- Improved documentation of triggers for self-reflection and logging corrections.
- Clear description of memory architecture and promotion/demotion rules.
- Enhanced transparency: sources cited for memory actions and digest/export features described.
Metadata
Frequently Asked Questions
What is Self Improving 1.2.10?
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use befo... It is an AI Agent Skill for Claude Code / OpenClaw, with 2770 downloads so far.
How do I install Self Improving 1.2.10?
Run "/install self-improving-1-2-10" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Self Improving 1.2.10 free?
Yes, Self Improving 1.2.10 is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Self Improving 1.2.10 support?
Self Improving 1.2.10 is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Self Improving 1.2.10?
It is built and maintained by yiyi-9 (@yiyi-9); the current version is v1.0.0.
More Skills