self-improving agent

CleanCK: Medium

by pskoett

464.0K downloads3.8K starsv3.0.2434 versions

Description

A skill where the agent logs it's own findings for self-improvement

Changelog

- Improved skill documentation for self-improvement logging, including detailed setup instructions for OpenClaw and generic agents. - Clarified initialization requirements: ensure `.learnings/` directory and key markdown files exist before use. - Added comprehensive quick-reference table mapping common situations (errors, corrections, requests) to specific log files. - Expanded promotion guidance for learnings, with clear targets for AGENTS.md, SOUL.md, TOOLS.md, and project memory. - New, structured markdown templates for logging learnings and errors, focusing on concise, non-sensitive summaries. - Guidance for integrating with OpenClaw sessions and optional auto-reminder hook workflow.

Published Jan 5, 2026Updated Jun 25, 2026

Security Analysis

ClawHub:

Clean

Clawkeeper:

CK: Medium

Risk Score4.0 / 10

Multiple risk signals — review findings before installing. Score is the sum of weighted findings below.

Findings

16 files analyzed

medium|+2.0 pts

Contains executable handler files (js/ts/sh/py)

medium|+1.5 pts

Binary file detected: hooks/openclaw/handler.ts (application/typescript)

low|+0.5 pts

16 files (typical skill has 1-3)

ClawHub scanned: Jun 25, 2026

Rescanned every 6 hours by Clawkeeper

Deploy Securely

Free to scan. Pro to deploy.