Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计通过

memory-onboarding-wizard内存加载向导

Agent Skill

memory-onboarding-wizard 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

4,158

周安装

175

GitHub Stars

公开资料未说明

下载量

1,456
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:memory-onboarding-wizard(内存加载向导)
来源仓库:https://github.com/stevojarvisai-star/memory-onboarding-wizard
安装命令:
openclaw skills install memory-onboarding-wizard
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install memory-onboarding-wizard

简介

memory-onboarding-wizard 引导新代理快速初始化 MEMORY.md 与相关配置文件。

  • 适合首次部署 OpenClaw 代理时的快速上手场景。
  • 通过三个问题自动创建日常内存文件与心跳监测机制。
  • 安装命令为 openclaw skills install memory-onboarding-wizard,需文件创建权限。
  • 初始配置应根据实际用途调整,避免通用模板不适用。

SKILL.md

name
memory-onboarding-wizard
description
Bootstrap a new OpenClaw agent's memory system in one command. Sets up MEMORY.md, daily memory files, HEARTBEAT.md, and USER.md by asking 3 quick questions. Use when a user is setting up OpenClaw for the first time, when memory files are missing, or when asked to "set up my memory system", "initialize my agent", "bootstrap my agent", or "run the memory wizard". Solves the #1 OpenClaw pain point — agents waking up with no context about who they're serving.

Memory Onboarding Wizard

Built by GetAgentIQgetagentiq.ai *The home of premium OpenClaw skills, packs, and agent blueprints.*

One command to give your OpenClaw agent its memory. Walks through the complete memory system setup interactively.

Quick Start

python3 scripts/memory-onboarding-wizard.py

Run from the OpenClaw workspace directory (default: ~/.openclaw/workspace).

What It Does

  1. MEMORY.md — Creates long-term memory file with starter template if missing
  2. memory/YYYY-MM-DD.md — Creates today's daily note file (creates memory/ dir if needed)
  3. HEARTBEAT.md — Creates a starter heartbeat checklist if missing
  4. USER.md — Asks 3 quick questions (name, timezone, main use case) and writes them
  5. Validation — Checks all files exist and prints a ✅ summary
  6. Next steps — Suggests the first 3 things to try

Options

python3 scripts/memory-onboarding-wizard.py --workspace /path/to/workspace
python3 scripts/memory-onboarding-wizard.py --non-interactive   # skip questions, use defaults

Memory System Overview

FilePurposeWhen Loaded
MEMORY.mdLong-term curated memoryMain sessions only
memory/YYYY-MM-DD.mdDaily raw notesEvery session
HEARTBEAT.mdPeriodic task checklistOn heartbeat polls
USER.mdWho the agent is servingEvery session

After Setup

Your agent will read these files at the start of each session to maintain continuity. Update MEMORY.md with important events and decisions. Let daily files accumulate naturally.


🧠 Want the Full Memory Pack?

This wizard gets you started. The GetAgentIQ Memory Pack takes it further:

  • Auto-compaction — keeps MEMORY.md lean and fast automatically
  • Semantic search — find anything across all memory files instantly
  • Session recall — 7-day keyword recall tester
  • Memory health dashboard — health score + gap detection
  • Consolidation cron — nightly memory distillation, runs while you sleep

👉 Get the Memory Pack free: getagentiq.ai/memory-pack Use code CLAWHUB100 at checkout for 100% off.

*Built by GetAgentIQ — getagentiq.ai*

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

93.52%
按下载量换算1,362

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills