My Self Improving

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

This skill appears internally consistent and does what it says: it creates a local memory directory (~/self-improving/), logs corrections and preferences, and updates workspace steering files. Before installing or enabling it, consider: (1) Inspect the setup and heartbeat snippets to verify the exact edits to AGENTS.md/SOUL.md/HEARTBEAT.md and confirm they are non-destructive. (2) Understand that learning is stored in plaintext under ~/self-improving/ — don't allow sensitive data (credentials, medical, financial, third-party private info) to be written there and consider file permissions or encryption if required. (3) The skill may optionally install a companion 'Proactivity' skill via network only with your explicit consent — decline if you don't want additional network installs. (4) Periodically audit ~/self-improving/ and run the provided 'forget everything' flow if you want to purge learned data. If you want extra safety, restrict the agent's file-write privileges or test in a sandbox workspace first.

Type: OpenClaw Skill Name: my-self-improving Version: 1.0.0 The skill bundle implements a structured, tiered local memory system for agent self-improvement and preference tracking. It demonstrates high security awareness through the inclusion of 'boundaries.md', which explicitly forbids the storage of sensitive data such as credentials, PII, and financial information. While the skill modifies agent configuration files (SOUL.md, AGENTS.md) and utilizes a 'heartbeat' mechanism for maintenance, these actions are transparently documented, scoped to the '~/self-improving/' directory, and strictly aligned with the stated purpose of persistent learning without evidence of malicious intent or data exfiltration.