Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
HEARTBEAT.md
text/markdown · 261 bytes
SKILL.md
text/markdown · 8582 bytes
boundaries.md
text/markdown · 2236 bytes
corrections.md
text/markdown · 1026 bytes
heartbeat-rules.md
text/markdown · 1843 bytes
heartbeat-state.md
text/markdown · 584 bytes
learning.md
text/markdown · 2951 bytes
memory-template.md
text/markdown · 1278 bytes
memory.md
text/markdown · 756 bytes
openclaw-heartbeat.md
text/markdown · 261 bytes
operations.md
text/markdown · 3435 bytes
reflections.md
text/markdown · 840 bytes
scaling.md
text/markdown · 2945 bytes
setup.md
text/markdown · 6347 bytes
Security Scan
Status
clean
OpenClaw
gpt-5-mini
OpenClaw analysis
The skill's requirements and instructions are coherent with its stated purpose: it is an instruction-only, local memory/learning helper that reads and writes a dedicated ~/self-improving/ workspace and may non-destructively update workspace steering files; it requests no credentials or exotic installs.
Confidence: high
VirusTotal
Type: OpenClaw Skill Name: self-improving Version: 1.2.16 The skill implements a structured, tiered memory system designed to help the agent learn from user corrections and self-reflection. It manages local files in `~/self-improving/` and includes a robust 'Security Boundaries' document (`boundaries.md`) that explicitly forbids storing credentials, financial data, or PII. While the setup process involves modifying core workspace configuration files like `SOUL.md` and `AGENTS.md` to establish persistence and steering, these actions are transparently documented and strictly aligned with the stated purpose of improving agent performance over time.