Oc Extract Memories

v1.0.0

Extract key memories from conversation into topic files. Triggers: extract memories, 提炼记忆, /extract-memories. Auto-triggers on conversation end words.

⭐ 0· 93·1 current·1 all-time

by@sky-lv

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for sky-lv/oc-extract-memories.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "Oc Extract Memories" (sky-lv/oc-extract-memories) from ClawHub.
Skill page: https://clawhub.ai/sky-lv/oc-extract-memories
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install sky-lv/oc-extract-memories

ClawHub CLI

Package manager switcher

npx clawhub@latest install oc-extract-memories

Security Scan

VirusTotal

Pending

View report →

OpenClaw

Benign

high confidence

✓

Purpose & Capability

The skill's name/description (extract memories into topic files) aligns with its runtime instructions (create topic files under memory/topics/ and append an entry to MEMORY.md). It does not request unrelated binaries, env vars, or config paths.

ℹ

Instruction Scope

Instructions explicitly tell the agent to analyze the current conversation and write topic files and an index entry. This is consistent with the stated purpose but does grant the skill the ability to persist conversation content to disk; it does not instruct reading unrelated system files or exfiltrating data externally.

✓

Install Mechanism

Instruction-only skill with no install steps or downloads — lowest-risk deployment model.

✓

Credentials

No environment variables, credentials, or config paths are requested. The declared requirements are minimal and proportional to the task of local memory persistence.

ℹ

Persistence & Privilege

always is false (normal). The skill is allowed to invoke autonomously (platform default) and is designed to auto-trigger at conversation end phrases; that means it may write files regularly without an explicit user command — intended behavior but something to be aware of.

Assessment

This skill is internally coherent but it will persist parts of conversations to memory/topics/ and update MEMORY.md automatically when it detects end-of-conversation phrases. Before installing, confirm where your agent stores workspace files and who can access them; do not let the skill store secrets, credentials, full source code, or other sensitive data. If you prefer manual control, consider disabling or restricting the skill's autonomous invocation or reviewing written topic files regularly and setting strict file permissions. If anything about where files are stored or how often they are written is unclear, ask the skill author for details before enabling it.

Like a lobster shell, security has layers — review code before you run it.

latestvk9785kq7vy4evpgsmkpjt5jghx859f8n

93downloads

0stars

1versions

Updated 6d ago

v1.0.0

MIT-0

extract-memories v3.1.0 — 对话记忆提炼

对话结束时主动分析本轮对话，将值得持久化的信息写入 memory/topics/ 下的独立 topic 文件，同时更新 MEMORY.md 索引。

自动触发

检测对话结束词：再见 / bye / 下次见 / 拜拜 / 结束了 / 先这样 / see you / that's all

四类记忆类型

类型	存什么	格式要求
`user`	用户角色/偏好/知识	一段文字
`feedback`	用户纠正或确认	正文 + Why + How to apply
`project`	截止/动机/约束	正文 + Why + How to apply
`reference`	外部系统URL/路径	URL/路径 + 用途

禁止存储（6条）

代码结构/文件路径（可从源码读）
Git 历史（git log 是权威）
调试方案（修复在代码里）
AGENTS.md/MEMORY.md 已有内容
临时任务状态
PR 列表/活动摘要

Topic 文件格式

---
name: 名称
description: 一句话描述
type: user / feedback / project / reference
---
正文内容

**Why:** 原因（feedback/project 必须）
**How to apply:** 何时适用（feedback/project 必须）

MEMORY.md 更新

追加一行：- [名称](topics/文件名.md) — 一句话 hook（≤150字符）

输出格式

已为您提炼本轮记忆 ✅
写入位置：memory/topics/
提炼结果：N条

Comments

Loading comments...