memory-setup

Name: memory-setup
Author: L-LesterYu

Other Community

Repo stars 42
Author updated Live
Author repo OpenClaw-hot-skills-zh

Fluxly profile Facts only: domain, agents, trust score, runtime, permissions and network

Domain: Other
Compatible agents: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
Trust score: 88 / 100 · community maintained
Author / version / license: @L-LesterYu · no license declared
Token usage: Lean
Setup complexity: Guided setup
External API key: Required · OpenAI
Operating systems: Unspecified (assume cross-platform)
Runtime requirements: No special requirements
Permissions: Read-only
Write / modify
Network behavior: External requests
Install commands: 26 variants

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview memory-setup.preview

---
name: memory-setup
description: 让你的 Agent 从金鱼变成大象。本技能帮助配置 Moltbot/Clawdbot 的持久化记忆功能。 添加到 ~/.clawdbot/clawdbot.json（或 moltbot.jso…
category: other
runtime: no special runtime
---

# memory-setup output preview

## PART A: Task fit
- Use case: 让你的 Agent 从金鱼变成大象。本技能帮助配置 Moltbot/Clawdbot 的持久化记忆功能。 添加到 ~/.clawdbot/clawdbot.json（或 moltbot.json）： "memorySearch": { "enabled": true, "provider": "voyage", requires OpenAI API key. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “快速设置 / 1. 在配置中启用记忆搜索 / 2. 创建记忆目录结构” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “让你的 Agent 从金鱼变成大象。本技能帮助配置 Moltbot/Clawdbot 的持久化记忆功能。 添加到 ~/.clawdbot/clawdbot.json（或 moltbot.json）： "memorySearch": { "enabled": true, "provider": "voyage", requires OpenAI API key. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “快速设置 / 1. 在配置中启用记忆搜索 / 2. 创建记忆目录结构” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; may access external network resources; requires OpenAI API keys.

## Running Rules
- read files, write/modify files; may access external network resources; requires OpenAI API keys.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.

SKILL.md SKILL.md

---
name: memory-setup
description: 让你的 Agent 从金鱼变成大象。本技能帮助配置 Moltbot/Clawdbot 的持久化记忆功能。 添加到 ~/.clawdbot/clawdbot.json（或 moltbot.jso…
category: other
source: L-LesterYu/OpenClaw-hot-skills-zh
---

# memory-setup

## When to use
- 让你的 Agent 从金鱼变成大象。本技能帮助配置 Moltbot/Clawdbot 的持久化记忆功能。 添加到 ~/.clawdbot/clawdbot.json（或 moltbot.json）： "memorySearch": {…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.

## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.

## Execution rules
- Organize steps around “快速设置 / 1. 在配置中启用记忆搜索 / 2. 创建记忆目录结构” and keep inference separate from source facts.
- read files, write/modify files; may access external network resources; requires OpenAI API keys.
- Validate with a small sample before expanding the task.

## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.

Evidence boundary and execution chain

The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.

skill "memory-setup" {
  input      -> user goal + target files + boundaries + acceptance criteria
  context    -> 快速设置 / 1. 在配置中启用记忆搜索 / 2. 创建记忆目录结构
  rules      -> SKILL.md triggers / order / output contract
  runtime    -> no special runtime | read files, write/modify files | may access external network resources
  guardrails -> requires OpenAI API keys + small-sample validation + diff/log review
  output     -> copyable result + checklist + next iteration
}

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: 让你的 Agent 从金鱼变成大象。本技能帮助配置 Moltbot/Clawdbot 的持久化记忆功能。添加到 ~/.clawdbot/clawdbot.json（或 moltbot.json）： "memorySearch": { "enabled":…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “快速设置”, “1. 在配置中启用记忆搜索”, “2. 创建记忆目录结构”, “3. 初始化 MEMORY.md”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name memory-setup directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “快速设置 / 1. 在配置中启用记忆搜索 / 2. 创建记忆目录结构” before expanding.

Boundaries And Review

Dependencies: Prepare OpenAI API keys before running a full task.
Permissions: Declared permissions include read / write; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

记忆设置技能

让你的 Agent 从金鱼变成大象。本技能帮助配置 Moltbot/Clawdbot 的持久化记忆功能。

快速设置

1. 在配置中启用记忆搜索

添加到 ~/.clawdbot/clawdbot.json（或 moltbot.json）：

{
  "memorySearch": {
    "enabled": true,
    "provider": "voyage",
    "sources": ["memory", "sessions"],
    "indexMode": "hot",
    "minScore": 0.3,
    "maxResults": 20
  }
}

2. 创建记忆目录结构

在工作区中创建：

workspace/
├── MEMORY.md              # 长期精炼记忆
└── memory/
    ├── logs/              # 每日日志 (YYYY-MM-DD.md)
    ├── projects/          # 项目特定上下文
    ├── groups/            # 群聊上下文
    └── system/            # 偏好设置、安装笔记

3. 初始化 MEMORY.md

在工作区根目录创建 MEMORY.md：

# MEMORY.md — 长期记忆

## 关于 [用户名]
- 关键信息、偏好、上下文

## 活跃项目
- 项目摘要和状态

## 决策与经验教训
- 做出的重要选择
- 吸取的教训

## 偏好
- 沟通风格
- 工具和工作流

配置选项说明

设置项	用途	推荐值
`enabled`	启用记忆搜索	`true`
`provider`	嵌入向量提供商	`"voyage"`
`sources`	索引范围	`["memory", "sessions"]`
`indexMode`	索引时机	`"hot"`（实时）
`minScore`	相关性阈值	`0.3`（值越低结果越多）
`maxResults`	最大返回片段数	`20`

提供商选项

voyage — Voyage AI 嵌入向量（推荐）
openai — OpenAI 嵌入向量
local — 本地嵌入向量（无需 API 密钥）

数据源选项

memory — MEMORY.md + memory/*.md 文件
sessions — 历史会话记录
both — 全部上下文（推荐）

每日日志格式

每天创建 memory/logs/YYYY-MM-DD.md：

# YYYY-MM-DD — 每日日志

## [时间] — [事件/任务]
- 发生了什么
- 做出的决策
- 需要跟进的事项

## [时间] — [另一个事件]
- 详细信息

Agent 指令（AGENTS.md）

将以下内容添加到 AGENTS.md 中以控制 Agent 行为：

## 记忆回忆
在回答关于过往工作、决策、日期、人物、偏好或待办事项的问题前：
1. 使用 memory_search 进行相关查询
2. 需要时使用 memory_get 提取具体行
3. 如果搜索后信心不足，说明已检查过记忆

故障排除

记忆搜索不工作？

检查配置中 memorySearch.enabled: true 是否已设置
确认工作区根目录存在 MEMORY.md
重启网关：clawdbot gateway restart

搜索结果不相关？

将 minScore 降低到 0.2 以获取更多结果
将 maxResults 增加到 30
检查记忆文件中是否有有意义的内容

提供商报错？

Voyage：在环境变量中设置 VOYAGE_API_KEY
OpenAI：在环境变量中设置 OPENAI_API_KEY
如无 API 密钥，使用 local 提供商

验证

测试记忆功能是否正常工作：

用户："你还记得关于 [过去的话题] 的什么事吗？"
Agent：[应该搜索记忆并返回相关上下文]

如果 Agent 没有记忆，说明配置未生效。请重启网关。

完整配置示例

{
  "memorySearch": {
    "enabled": true,
    "provider": "voyage",
    "sources": ["memory", "sessions"],
    "indexMode": "hot",
    "minScore": 0.3,
    "maxResults": 20
  },
  "workspace": "/path/to/your/workspace"
}

为什么这很重要

没有记忆：

Agent 每次会话都会忘记一切
重复提问，丢失上下文
项目缺乏连续性

有记忆后：

能回忆过去的对话
了解你的偏好
追踪项目历史
随时间建立关系

金鱼 → 大象。🐘

Install command

One-click installPick a runner, click Copy, paste into your terminal, press enter

npx skills add L-LesterYu/OpenClaw-hot-skills-zh/skills/memory-setup-zh -y

Open general install guide

View skill source

Works with

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

Security audit

88 / 100

Community

未声明 license/许可。
未声明 version。
未限定 allowed-tools，默认拥有全部工具权限。

Metadata

Source: github
L-LesterYu/OpenClaw-hot-skills-zh
中文

More by @L-LesterYu

Category & tags

Category Other