sleep
睡觉技能。执行睡觉流程：将当前 session 中未完成的事项记录到 preview 文件，通过 Gateway API reset session。醒来时 hook 自动读取并注入未完成事项到新 session 上下文。触发方式：Agent 自行判断适合入睡时调用，强制入睡用 /sleep。
Best use case
sleep is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
睡觉技能。执行睡觉流程：将当前 session 中未完成的事项记录到 preview 文件，通过 Gateway API reset session。醒来时 hook 自动读取并注入未完成事项到新 session 上下文。触发方式：Agent 自行判断适合入睡时调用，强制入睡用 /sleep。
Teams using sleep should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/openclaw-sleep/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How sleep Compares
| Feature / Agent | sleep | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
睡觉技能。执行睡觉流程：将当前 session 中未完成的事项记录到 preview 文件，通过 Gateway API reset session。醒来时 hook 自动读取并注入未完成事项到新 session 上下文。触发方式：Agent 自行判断适合入睡时调用，强制入睡用 /sleep。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Sleep — 睡前记录 + 醒来续接
## 核心原则
**只记录未完成的，已完成的从记忆里回忆即可。**
## 触发条件
⚠️ **本 skill 的完整流程依赖 session reset（`/new` 或 `/reset`），不仅仅是激活 skill。**
触发方式：
- **Agent 判断**：Agent 认为当前 session 适合结束/暂停时，主动调用
- **强制触发**：`/sleep` 命令，用户或 Agent 强制执行睡觉流程
**Skill 本身只负责写 preview 文件 + 调用 Gateway API reset session**
- **Reset 触发 `agent:bootstrap` 事件 → hook 在 bootstrap 时注入 preview**
如果只激活 skill 而不调用 Gateway API，session 不会 reset，hook 不会触发。
## 记录要求
执行 /sleep 时，逐项回答以下问题：
1. **本次 session 做了什么？**（一句话概括）
2. **有哪些未完成的事？**
- 每条尽量详细：具体要做什么、做到哪一步、卡在哪里
- 不要省略技术细节：代码路径、配置值、API 端点、错误信息
- 只要没完成，不管多小都记
3. **醒来后第一步做什么？**
## Preview 文件格式
```markdown
# Sleep Preview — {sessionKey}
# 生成时间：YYYY-MM-DD HH:mm
## 本次 session 摘要
[一句话描述本次 session 做了什么]
## 未完成事项
- [ ] [事项1：具体描述，要做到哪一步]
- [ ] [事项2：具体描述]
## 醒来后第一步
[醒来后最先要处理的事情]
## 关键上下文
[技术细节：代码路径、配置值、决策结论等，尽量详尽]
## 状态
pending / all_done
```
## 执行流程
### Step 1：获取当前 Session Key
**这是最关键的步骤——必须睡你自己的 session，不是别人的。**
执行以下命令获取当前 session 的 key：
```bash
openclaw session current
```
输出格式如：`agent:main:feishu:group:oc_87d0d49f1f81f9e1b8dd1d5ad5f9ec72`
**记录下来，后续两步都要用到这个 key。**
### Step 2：评估并记录
根据"记录要求"逐项填写上述格式，写入：
```
$HOME/.openclaw/workspace/previews/{你的sessionKey}.md
```
⚠️ **路径说明**：
- 把 preview 写到**你自己**工作空间下的 `previews/` 目录
- main agent 路径是 `$HOME/.openclaw/workspace/previews/`
- 文件名用**你刚获取的 session key**，不是别人的
### Step 3：判断状态
- 有未完成事项 → 状态写 `pending`
- 全部完成 → 状态写 `all_done`
### Step 4：通过 Gateway API reset 你自己的 session
写入文件后，必须调用 Gateway API 才能真正 reset session：
```bash
#!/bin/bash
# 以下全部使用你自己的 session key
AGENT_SESSION_KEY="agent:main:feishu:group:oc_87d0d49f1f81f9e1b8dd1d5ad5f9ec72" # 替换为 Step 1 获取的值
PREVIEW_DIR="$HOME/.openclaw/workspace/previews" # 替换为你的工作空间路径
mkdir -p "$PREVIEW_DIR"
TOKEN="$(cat ~/.openclaw/openclaw.json | python3 -c "import json,sys; c=json.load(sys.stdin); print(c['gateway']['auth']['token'])")"
openclaw gateway call sessions.reset \
--token "$TOKEN" \
--json \
--params "{\"key\":\"$AGENT_SESSION_KEY\"}"
```
⚠️ **关键提醒**：
- `$AGENT_SESSION_KEY` 必须填**你自己的 session key**，不是 main 或其他 agent 的
- **只写 preview 不调用 reset** = hook 不会触发，preview 不会被注入
- Reset 的是**你自己的 session**，Gateway 会触发 `agent:bootstrap`，hook 会在你重新被唤醒时注入 preview
## 设计原则
- **只记未完成的**：已完成的不需要记录，记忆里可以回忆
- **细节越多越好**：宁可写多也不要写少，特别是技术上下文
- **文件独立**：每个 session key 独立文件，互不影响
- **Reset 才触发**：Hook 只在 `agent:bootstrap` 时触发，对应 `/new` 或 `/reset`
- **温和 reset**：使用 `sessions.reset` API 重置上下文，不删除 session 文件，不断开连接Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成（播客、视频、幻灯片、测验、思维导图等）、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述