360 Secure SkillHub
360 安全技能中心

Auto Improve

该技能按扫描、提议、应用三步运行：读取错误记录、学习记录和相关记忆文件，识别重复错误、用户纠正、过期事实等模式；低风险变更直接应用，中风险应用并通知，高风险仅生成提案，目标包括技能学习段、代理协议和记忆文件。

dodge1218
dodge1218
热度 42.89
最近更新 2026-05-18 11:39:30
分类：知识依赖：读写文件应用场景：工作流 / 笔记整理

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add dsb-auto-improve
Metadata
name
active-self-improvement
description
Self-improvement loop that reads learnings, errors, and memory — detects patterns — and updates skills/protocols automatically. Use when the agent should get smarter without being prompted.

Auto-Improve

Loop

SCAN → PROPOSE → APPLY

Scan

Read .learnings/ERRORS.md, .learnings/LEARNINGS.md, relevant memory files.

Look For

Repeated errors, repeated user corrections, stale facts, valuable unused wins.

Apply

  • Low-risk reversible → apply directly.
  • Medium-risk → apply + notify.
  • High-risk → write proposal only.

Targets

Skill Learned sections, SOUL.md, AGENTS.md, memory facts, reminder/ticket files.

Rule

Logging alone is not improvement. Update the playbook.