Self-Evolving

Improve reusable agent workflows with reflective experiments, value checks, and local pattern memory.

This skill appears internally consistent: it will keep short local notes in ~/self-evolving/ to record experiments and only writes after notifying you. Before installing, consider whether you're comfortable with an agent creating and updating files in your home directory. If you install it: 1) Confirm the first-write notice appears before any files are created. 2) Inspect ~/self-evolving/ (memory.md, experiments.md, archive/) to ensure no sensitive content is stored. 3) Decline or revoke the skill if it later asks for external services, credentials, or permission to read other parts of your system. If you use other 'memory' or persistence skills, clarify how this skill interacts with them (it mentions 'main memory' but doesn't define whether it will read other skills' stores).

Type: OpenClaw Skill Name: self-evolving Version: 1.0.0 The 'self-evolving' skill is a framework for an AI agent to improve its own workflows by logging experiments and successful patterns in a local directory (~/self-evolving/). It contains explicit safety boundaries in boundaries.md and SKILL.md that prohibit modifying its own code, accessing sensitive files, or performing hidden actions. There are no indicators of data exfiltration, malicious execution, or unauthorized persistence.