Self-Improving v2.0 - Jarvis Edition

AI agent that performs automatic tri-daily self-reflections, saves all dialogs and media, manages long-term memory, and continuously learns and improves.

Do not install or enable automatic scheduling until you confirm where the runtime scripts come from and what will actually be written to disk. Key questions to ask the author or maintainer: (1) Provide the missing runtime files (scripts/memory_manager.py, cron config) and let you review their code before running. (2) Explain exactly what data is captured and give options to exclude sensitive content (secrets, code snippets containing credentials, attachments). (3) Clarify how cron jobs are registered and how to opt out or inspect scheduled jobs. (4) If you will publish data (git push, ClawHub/GitHub), require explicit, manual consent and show which files would be committed. If you can't get those answers or the code, treat this package as unsafe: the behavior described (permanent retention of all dialogs and media, automatic scheduled runs) has real privacy/exfiltration risk and the bundle is missing the code it claims to run.

Type: OpenClaw Skill Name: self-improving-v2 Version: 2.0.0 The skill bundle describes a 'Self-Improving Agent' that is explicitly instructed in SKILL.md and README.md to perform full-scale, permanent logging of all user interactions, including text, images, and code. While this is framed as a 'memory' feature, the broad data collection instructions create a significant privacy risk and a centralized target for sensitive data theft. Crucially, the actual implementation logic (scripts/memory_manager.py and other referenced Python files) is missing from the provided content, making it impossible to verify if the collected data is exfiltrated to an external endpoint or handled securely.