agentsclimarketplace

Memory extraction

Skill OnestarQQ/Samantha/skills/memory-extraction

🌟 AI Companion System — Memory, Skills & Self-Evolution. Built on OpenClaw.

Install
npx -y skills add OnestarQQ/Samantha --skill memory-extraction

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.0 KB, 382 tokens by cl100k_base, as published. Nobody here has run it

自动记忆提取规则

核心原则

  • 只记长期有价值的信息，不记一次性对话
  • 每次提取先检查是否已存在，避免重复
  • 置信度分级：confirmed(用户明确说)=1.0, inferred(推断)=0.7, mentioned(提及)=0.5

什么值得记忆

  1. 用户偏好/习惯（沟通风格、审美、工作方式）
  2. 重要事实（人物关系、项目信息、技术决策）
  3. 纠正/修正（用户指出错误的信息）
  4. 情绪模式（什么让用户开心/焦虑）

什么不记

  • 临时性信息（"今天天气怎么样"）
  • 容易搜索到的公共知识
  • 大段代码/日志
  • 已在 MEMORY.md 中的信息

记录方式

提取到信息 → 用 memory_search 检查是否已存在 → 写入对应位置:

  • 用户偏好 → MEMORY.md User 段
  • 人物信息 → knowledge/graph/people.json
  • 项目事实 → MEMORY.md Active Projects 段
  • 经验教训 → MEMORY.md Lessons 段

冲突处理

新信息与旧信息矛盾 → 以最新用户确认为准，替换旧条目

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.