Auto Evolution

Build and maintain a self-evolving skill system that silently captures feedback, graduates repeated feedback into formal rules, improves low-performing skill...

This skill appears to do what it says (detect feedback and propose rule/skill changes) and does not require external credentials, but it is privacy- and persistence-sensitive: - It is designed to silently capture corrective user messages and store them under .claude/feedback/ by default. Make sure you and your users are comfortable with that behavior and update privacy/retention policies if needed. - The repository does not include the 'feedback-observer' component; the detect script only signals matches and evolution_runner only reads feedback files. Before deploying, confirm how your controller will: (a) call detect_feedback_signal, (b) create structured feedback files, and (c) present proposals and require explicit human confirmation before any edits. - The feedback detection is keyword/regex-based and will generate false positives; tune patterns and thresholds (occurrence counts) for your environment. - Ensure the agent/controller has minimal filesystem permissions (limit writes to a designated feedback directory) and audit who can read the feedback directory. Consider encrypting or access-controlling stored feedback if it may contain sensitive data. - Test in a sandbox first: verify that proposals are only suggestions and that no automatic edits occur without human approval. If you need the skill to be low-risk for privacy, require explicit opt-in for silent recording, review and implement the observer code with consent flows, and restrict file write/read scopes for the agent.

Type: OpenClaw Skill Name: veezvg-auto-evolution Version: 2.0.1 The skill bundle implements a 'self-evolving' mechanism that monitors user interactions for corrective feedback and proposes modifications to the agent's core instructions and rule files (e.g., CLAUDE.md). While the logic in SKILL.md and scripts/evolution_runner.py includes a mandatory human-in-the-loop confirmation step and the scripts themselves lack overt malicious code, the capability for an agent to modify its own governing rules is a high-risk behavior. The 'silent' background capture of feedback, although aligned with the stated purpose, introduces a stealthy mechanism for potential persistent instruction injection if the user confirmation process is bypassed or manipulated.