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 字节
SKILL.md
text/markdown · 8582 字节
boundaries.md
text/markdown · 2236 字节
corrections.md
text/markdown · 1026 字节
heartbeat-rules.md
text/markdown · 1843 字节
heartbeat-state.md
text/markdown · 584 字节
learning.md
text/markdown · 2951 字节
memory-template.md
text/markdown · 1278 字节
memory.md
text/markdown · 756 字节
openclaw-heartbeat.md
text/markdown · 261 字节
operations.md
text/markdown · 3435 字节
reflections.md
text/markdown · 840 字节
scaling.md
text/markdown · 2945 字节
setup.md
text/markdown · 6347 字节
Security Scan
状态
clean
OpenClaw
gpt-5-mini
OpenClaw 分析
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.
置信度: 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.