Recovery
MigoXLab/webqa-agent
Structured error recovery for failed or ineffective browser actions.
AI会话管理与优化系统。解决会话上下文限制问题，通过三级文档系统、自动化脚本和上下文压缩实现快速恢复。包含：STATUS.md快速索引、memory详细记录、自动更新脚本、上下文压缩策略、信息识别机制。适用于长期AI项目、多任务并行、需要高效会话恢复的场景。触发词：会话恢复、session recovery、上下文压缩、快速恢复、会话管理。
MITAuto-check passed
Install Session Recovery
$ npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills session-recovery --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/session-recovery .claude/skills/session-recovery && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "session-recovery" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/session-recovery into .claude/skills/session-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-recovery", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/session-recoveryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills session-recovery --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/session-recovery .agents/skills/session-recovery && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "session-recovery" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/session-recovery into .agents/skills/session-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-recovery", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills session-recovery --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/session-recovery .cursor/skills/session-recovery && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "session-recovery" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/session-recovery into .cursor/skills/session-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-recovery", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/session-recovery--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills session-recovery --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/session-recovery .gemini/skills/session-recovery && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "session-recovery" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/session-recovery into .gemini/skills/session-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-recovery", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills session-recoveryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/session-recovery .github/skills/session-recovery && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "session-recovery" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/session-recovery into .github/skills/session-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-recovery", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills session-recovery --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/session-recovery .opencode/skills/session-recovery && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "session-recovery" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/session-recovery into .opencode/skills/session-recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "session-recovery", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
session-recovery- GitHub stars
- 2.2k
- Token cost
- ~2.4k tokens
- SKILL.md length
- 511 words
- Files
- 12 (incl. scripts, references)
- Skills in repo
- 1,235
- Repo updated
- First seen
- Licence
- MIT
At a glance
AI会话管理与优化系统。解决会话上下文限制问题，通过三级文档系统、自动化脚本和上下文压缩实现快速恢复。包含：STATUS.md快速索引、memory详细记录、自动更新脚本、上下文压缩策略、信息识别机制。适用于长期AI项目、多任务并行、需要高效会话恢复的场景。触发词：会话恢复、session recovery、上下文压缩、快速恢复、会话管理。
- Works in 12 steps: quick_recovery.sh（快速恢复）⚡ → update_status.sh（自动更新状态）🔄 → new_daily_log.sh（创建每日记录）📝 → …
- SKILL.md covers 🎯 核心问题与解决方案, 📂 三级文档系统, 🤖 自动化脚本系统 and 🗜️ 上下文压缩策略, plus 3 more sections
- Runs Shell and Python scripts from its folder; calls python3 and git
What it does
Session Recovery is an agent skill from LeoYeAI/openclaw-master-skills. AI会话管理与优化系统。解决会话上下文限制问题，通过三级文档系统、自动化脚本和上下文压缩实现快速恢复。包含：STATUS.md快速索引、memory详细记录、自动更新脚本、上下文压缩策略、信息识别机制。适用于长期AI项目、多任务并行、需要高效会话恢复的场景。触发词：会话恢复、session recovery、上下文压缩、快速恢复、会话管理。
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts and reference files (for example `README.md`, `_meta.json` and `references/SESSION_RECOVERY_OPTIMIZATION.md`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
Example prompts
- “/session-recovery”
Requirements
- Python 3
- A Bash shell
Workflow steps
12 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 5 files in scripts/ (Shell and Python), which the agent can run.
Shell commands in SKILL.md call:
python3git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Session Recovery loads about 2.4k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 511 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 511 words, ~2,435 tokens.
Download SKILL.mdSave it as
.claude/skills/session-recovery/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- session-recovery
- description
- AI会话管理与优化系统。解决会话上下文限制问题，通过三级文档系统、自动化脚本和上下文压缩实现快速恢复。包含：STATUS.md快速索引、memory详细记录、自动更新脚本、上下文压缩策略、信息识别机制。适用于长期AI项目、多任务并行、需要高效会话恢复的场景。触发词：会话恢复、session recovery、上下文压缩、快速恢复、会话管理。
- version
- 1.0.0
- license
- MIT
Session Recovery - AI会话管理与优化系统
版本： 1.0 适用场景： 长期AI项目、多任务并行、需要高效会话恢复
🎯 核心问题与解决方案
问题
- 会话恢复慢 - 每次需要10-30分钟恢复上下文
- 上下文太长 - AI处理变慢，成本增加
- 信息丢失 - 关键决策和状态容易遗忘
- 维护成本高 - 手动更新文档繁琐
解决方案
- 三级文档系统 - 快速恢复（30秒-1.5分钟）
- 上下文压缩 - 减少70-90%上下文
- 自动化脚本 - 减少维护成本60%
- 智能识别 - 保留重要信息，丢弃冗余
📂 三级文档系统
第1级：STATUS.md（状态看板）⚡
恢复时间： 30秒 用途： 日常快速恢复
内容：
# 📊 状态看板
**最后更新：** YYYY-MM-DD HH:MM
**状态：** 活跃
## 🎯 当前任务（最多5个）
| 任务 | 状态 | 进度 | 下一步 | 截止 |
|------|------|------|--------|------|
| 任务1 | ✅ | 100% | 完成 | - |
| 任务2 | 🔄 | 80% | 测试 | - |
## 📋 待办事项
### 🔥 高优先级
- [ ] 待办1
- [ ] 待办2
## 📂 快速访问文件
- 文件1
- 文件2
## ⚠️ 阻塞问题
（当前阻塞）
## 🔑 必须记住的约束
| 约束 | 要求 | 状态 |
|------|------|------|
| 约束1 | 要求1 | ✅ |第2级：QUICK_RECOVERY.md（快速索引）
恢复时间： 1分钟 用途： 完整上下文恢复
内容：
# ⚡ 快速恢复索引
**更新：** YYYY-MM-DD HH:MM
## 🎯 项目概览
### 任务1
- 状态：✅ 完成
- 关键信息：...
- 下一步：...
### 任务2
- 状态：🔄 进行中
- 关键信息：...
- 下一步：...
## 📂 关键目录
（目录结构）
## 🔑 关键决策
| 决策 | 选择 | 理由 |
|------|------|------|
| 决策1 | 选择1 | 理由1 |
## ⚠️ 重要约束
（约束列表）
## 📋 待办事项
（待办清单）
## 🔗 关键链接
（服务器信息、工具路径等）第3级：memory/YYYY-MM-DD.md（详细记录）
恢复时间： 深度查询 用途： 完整工作记录
内容：
# YYYY-MM-DD 工作记录
**会话时间：** YYYY-MM-DD HH:MM - HH:MM
**主要任务：** （一句话描述）
## 📋 完成的任务
### 任务名称
**详情：** ...
**产出：** ...
## 🎯 关键决策
### 决策1
**背景：** ...
**选择：** ...
**理由：** ...
## 📚 学到的经验
### 经验1
**问题：** ...
**解决：** ...
**教训：** ...
## 📂 文件操作记录
### 创建的文件
- 文件名 - 说明
## 🎯 下次会话重点
### 高优先级
- [ ] 待办1🤖 自动化脚本系统
1. quick_recovery.sh（快速恢复）⚡
用途： 一键恢复会话上下文
功能：
- 显示 STATUS.md（当前状态）
- 显示待办事项
- 显示今日工作记录
使用：
./scripts/quick_recovery.sh效果： 30秒看到所有状态
2. update_status.sh（自动更新状态）🔄
用途： 从今日记录提取信息，更新 STATUS.md
功能：
- 读取 memory/YYYY-MM-DD.md
- 统计完成任务数
- 更新 STATUS.md 时间戳
使用：
# 会话结束时
./scripts/update_status.sh效果： 2分钟完成状态更新
3. new_daily_log.sh（创建每日记录）📝
用途： 快速创建标准化的每日记录模板
功能：
- 检查今日记录是否存在
- 创建标准模板
- 提供编辑指南
使用：
# 每天开始时
./scripts/new_daily_log.sh
# 或
python3 scripts/template_generator.py效果： 10秒创建标准模板
4. weekly_archive.sh（每周归档）📦
用途： 归档旧的每日记录，生成每周摘要
功能：
- 归档本周的 .md 文件
- 生成 WEEKLY_SUMMARY.md
- 清理 memory/ 目录
使用：
# 每周日
./scripts/weekly_archive.sh效果： 5分钟完成周归档
5. template_generator.py（智能模板生成）🧠
用途： 根据项目状态，智能生成每日记录模板
功能：
- 生成标准化模板
- 包含完整结构
- 支持 Markdown 格式
使用：
python3 scripts/template_generator.py效果： 1分钟生成标准模板
🗜️ 上下文压缩策略
什么是上下文压缩？
上下文压缩 = 用AI总结历史对话，用摘要替换原文
类比：
- 📚 重读整本书（250页） → 看读书笔记（5页）
- 🎬 重看电影（2小时） → 看影评摘要（2分钟）
- 📝 重读对话历史（15000 tokens） → 读摘要（1500 tokens）
压缩效果
| 指标 | 不压缩 | 压缩后 | 提升 |
|---|---|---|---|
| 上下文 | 15000 tokens | 1500 tokens | 10倍 |
| AI速度 | 10秒 | 1秒 | 10倍 |
| 成本 | $0.30/次 | $0.03/次 | 90%节省 |
压缩时机
触发条件：
- ✅ 上下文超过15000 tokens
- ✅ AI响应时间超过10秒
- ✅ 完成一个大任务
推荐策略：
完成任务 → 开启新会话 → 从 STATUS.md 恢复三种压缩方法
方法1：手动压缩（推荐）✅
操作：
1. 完成一个大任务（如除冰机方案）
2. 我总结关键信息
3. 写入 memory/YYYY-MM-DD.md
4. 你开启新会话
5. 我从 STATUS.md 恢复效果： 50-70%压缩
方法2：半自动压缩⭐⭐
操作：
# 会话结束时
./scripts/compress_context.sh脚本功能：
- 总结本次会话
- 更新 STATUS.md
- 归档到 memory/
- 提示开启新会话
效果： 70-80%压缩
方法3：全自动压缩（高级）⭐⭐⭐
操作： AI自动监控和压缩
触发条件：
- 上下文 > 15000 tokens
- AI响应 > 10秒
- 完成一个任务
效果： 80-90%压缩
🔍 信息识别机制
会丢失的信息（不重要）✅
| 信息类型 | 会丢失 | 原因 |
|---|---|---|
| 闲聊内容 | ✅ | "你好"、"哈哈"等 |
| 重复信息 | ✅ | 同样的内容说多次 |
| 临时想法 | ✅ | 最终未采用的方案 |
| 详细步骤 | ✅ | 只保留结果 |
| 错误尝试 | ✅ | 只保留正确方案 |
不会丢失的信息（重要）❌
| 信息类型 | 不会丢失 | 原因 |
|---|---|---|
| 任务目标 | ❌ | 核心信息 |
| 关键决策 | ❌ | 影响后续工作 |
| 文件路径 | ❌ | 查找文件必需 |
| 当前状态 | ❌ | 恢复上下文必需 |
| 重要约束 | ❌ | 避免违反规则 |
| 学到的经验 | ❌ | 长期价值 |
如何识别重要信息？
AI自动判断（85-90%准确）
重要信息的特征：
1. 包含关键词：
- "预算"、"成本"、"决策"
- "必须"、"不能"、"约束"
- 文件路径、日期、数字
2. 影响后续工作：
- 任务目标
- 技术决策
- 文件操作
3. 用户明确强调：
- "记住这个"
- "重要"
- "必须"不重要的特征：
- 闲聊："你好"、"哈哈"
- 重复：同样的内容说多次
- 临时想法："可能"、"也许"
- 中间过程："正在分析..."人工判断（95-99%准确）
检查清单：
## 必须保留的信息
- [ ] 任务目标
- [ ] 关键决策 + 理由
- [ ] 文件路径
- [ ] 重要约束
- [ ] 当前状态
- [ ] 待办事项
- [ ] 学到的经验💾 原文保存机制
压缩后原文会保存吗？
答案：❌ 不会自动保存完整原文
实际保存：
| 内容 | 保存？ | 位置 |
|---|---|---|
| 完整对话历史 | ❌ | - |
| AI回复内容 | ❌ | - |
| 工具调用详情 | ❌ | - |
| 关键信息摘要 | ✅ | STATUS.md, memory/ |
这是问题吗？
✅ 通常不是问题
原因：
- 摘要已包含所有关键信息
- 足够恢复上下文
- 完整对话太大（每天50-100KB）
如需完整对话
方法1：手动导出
# 会话结束时
./scripts/export_conversation.sh
# 保存到 logs/conversations/YYYY-MM-DD.log方法2：自动记录
- 需要额外开发
- 自动保存每轮对话
🎯 完整工作流程
每次会话开始（恢复）
# 方式1：快速恢复（30秒）
./scripts/quick_recovery.sh
# 方式2：完整恢复（1.5分钟）
1. 读取 STATUS.md（30秒）
2. 读取 QUICK_RECOVERY.md（1分钟）
3. 如需详情，查 memory/YYYY-MM-DD.md会话进行中（记录）
1. 我自动记录关键信息
2. 你可以手动添加笔记到 memory/YYYY-MM-DD.md
3. 重要决策立即记录会话结束（更新）
# 方式1：手动更新（推荐）
1. 我总结本次会话
2. 更新 memory/YYYY-MM-DD.md
3. 你快速检查
# 方式2：自动更新
./scripts/update_status.sh完成大任务后（压缩）
# 方式1：开启新会话（手动压缩）
1. 完成大任务（如除冰机方案）
2. 我总结关键信息
3. 你开启新会话
4. 我从 STATUS.md 恢复
# 方式2：运行压缩脚本（半自动）
./scripts/compress_context.sh每周维护（归档）
# 每周日运行
./scripts/weekly_archive.sh
# 功能：
1. 归档本周记录
2. 生成每周摘要
3. 清理 memory/ 目录📊 效果对比
效率提升
| 操作 | 优化前 | 优化后 | 提升 |
|---|---|---|---|
| 日常恢复 | 5分钟 | 30秒 | 10倍 |
| 完整恢复 | 10-30分钟 | 1.5分钟 | 10-20倍 |
| 更新文档 | 5分钟 | 2分钟 | 2.5倍 |
| 查找信息 | 1分钟 | 10秒 | 6倍 |
| 每周归档 | 30分钟 | 5分钟 | 6倍 |
上下文优化
| 指标 | 不压缩 | 压缩后 | 提升 |
|---|---|---|---|
| 上下文大小 | 15000 tokens | 1500 tokens | 90%减少 |
| AI响应速度 | 10秒 | 1秒 | 10倍 |
| API成本 | $0.30/次 | $0.03/次 | 90%节省 |
Show full SKILL.md (203 more words)Show less
维护成本
| 项目 | 手动 | 自动化 | 减少 |
|---|---|---|---|
| 每次更新 | 5分钟 | 2分钟 | 60% |
| 每周维护 | 30分钟 | 10分钟 | 67% |
| 文档大小 | 7KB | 3KB | 57% |
🛠️ 安装与使用
1. 安装脚本
# 赋予执行权限
chmod +x scripts/*.sh
chmod +x scripts/*.py2. 创建初始文档
# 创建 STATUS.md
./scripts/new_daily_log.sh
# 创建今日记录
python3 scripts/template_generator.py3. 试用快速恢复
# 测试快速恢复
./scripts/quick_recovery.sh4. 设置别名（可选）
# 添加到 ~/.bashrc 或 ~/.zshrc
alias recover='./scripts/quick_recovery.sh'
alias newlog='python3 scripts/template_generator.py'
alias update='./scripts/update_status.sh'
alias archive='./scripts/weekly_archive.sh'使用：
recover # 快速恢复
newlog # 创建记录
update # 更新状态
archive # 每周归档💡 最佳实践
1. 定期更新
时机：
- ✅ 每次会话结束时
- ✅ 完成一个大任务后
- ✅ 做出重要决策后
操作：
./scripts/update_status.sh2. 定期归档
时机：
- ✅ 每周日
- ✅ 完成一个项目后
操作：
./scripts/weekly_archive.sh3. 定期压缩
时机：
- ✅ AI响应变慢（>10秒）
- ✅ 上下文超过15000 tokens
- ✅ 完成一个大任务
操作：
# 方式1：开启新会话
# 方式2：运行压缩脚本
./scripts/compress_context.sh4. 检查完整性
时机：
- ✅ 每周一次
- ✅ 开启新会话前
操作：
# 手动检查 STATUS.md 和 memory/ 是否完整⚠️ 注意事项
1. 信息丢失风险
风险： 丢失看似不重要但实际重要的信息
解决：
- ✅ 明确标记重要信息（[重要]、[决策]）
- ✅ 会话结束时人工检查
- ✅ 使用多层摘要（快速/标准/详细）
2. 原文不保存
风险： 完整对话历史不保存
解决：
- ✅ 摘要已包含关键信息（通常够用）
- ✅ 如需完整对话，手动导出
- ✅ 定期检查摘要完整性
3. 维护成本
风险： 需要定期维护
解决：
- ✅ 使用自动化脚本（减少60%工作量）
- ✅ 设置提醒（每周日归档）
- ✅ 建立习惯（会话结束必更新）
📚 参考资源
相关文档
上下文压缩_简单解释.md- 上下文压缩详细说明上下文压缩_原文保存机制.md- 原文保存机制说明上下文压缩_信息丢失与识别.md- 信息识别机制说明SESSION_RECOVERY_OPTIMIZATION.md- 优化建议完整文档
脚本文件
scripts/quick_recovery.sh- 快速恢复脚本scripts/update_status.sh- 自动更新脚本scripts/new_daily_log.sh- 创建每日记录scripts/weekly_archive.sh- 每周归档脚本scripts/template_generator.py- 模板生成器
🎯 适用场景
✅ 推荐使用
长期项目（>1个月）
- 需要跨会话记忆
- 多个并行任务
多任务并行（>3个任务）
- 任务切换频繁
- 需要快速恢复
团队协作
- 需要标准化文档
- 多人共享上下文
AI响应慢
- 上下文过长
- 成本过高
⚠️ 不推荐使用
一次性任务（<1周）
- 简单项目
- 无需长期记忆
单任务项目
- 任务简单
- 不需要复杂管理
短期项目（<2周）
- 上下文不会太长
- 维护成本>收益
🚀 进阶优化
1. Git Hook集成
# .git/hooks/pre-commit
./scripts/update_status.sh
git add STATUS.md memory/效果： 每次提交前自动更新状态
2. 定时任务（Cron）
# 每周五17:00自动归档
0 17 * * 5 cd /path/to/project && ./scripts/weekly_archive.sh3. AI辅助维护
未来功能：
- 自动识别需要更新的内容
- 智能建议下一步操作
- 自动生成周报/月报
💬 常见问题
Q1: 会丢失重要信息吗？
A: 可能会，但概率很低（AI准确率85-90%，人工95-99%）。建议会话结束时人工检查。
Q2: 原文不保存怎么办？
A: 摘要已包含所有关键信息，通常够用。如需完整对话，可手动导出。
Q3: 压缩后AI还能理解吗？
A: 能。摘要保留了所有关键信息，AI可以快速恢复上下文。
Q4: 维护成本高吗？
A: 使用自动化脚本后，维护成本减少60%（每次2分钟）。
Q5: 适合我的项目吗？
A: 如果你的项目：
- 持续时间>1个月
- 并行任务>3个
- AI响应变慢
- 需要长期记忆
那么✅ 适合使用本系统。
🎉 总结
核心价值
Session Recovery = 时间倍增器 + 成本节省器
- ⚡ 恢复时间：减少95%（10-30分钟 → <1分钟）
- ⚡ AI速度：提升10倍（通过上下文压缩）
- 💰 API成本：节省90%
- 📊 维护成本：减少60%
关键特性
- 三级文档系统 - 30秒-1.5分钟快速恢复
- 自动化脚本 - 5个脚本减少维护成本
- 上下文压缩 - 减少70-90%上下文
- 智能识别 - 85-99%准确率保留重要信息
- 灵活扩展 - 支持Git Hook、Cron等集成
立即开始
# 1. 试用快速恢复
./scripts/quick_recovery.sh
# 2. 创建今日记录
python3 scripts/template_generator.py
# 3. 会话结束时更新
./scripts/update_status.sh享受10-20倍的效率提升！ 🚀
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 11 other files (scripts, references) in skills/session-recovery of LeoYeAI/openclaw-master-skills.
- SKILL.md
- README.md
- _meta.json
- references/SESSION_RECOVERY_OPTIMIZATION.md
- references/上下文压缩_信息丢失与识别.md
- references/上下文压缩_原文保存机制.md
- references/上下文压缩_简单解释.md
- scripts/new_daily_log.sh
- scripts/quick_recovery.sh
- scripts/template_generator.py
- scripts/update_status.sh
- scripts/weekly_archive.sh
Open the folder on GitHubat commit e5199b5
Compare with similar skills
Session Recovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Session Recovery this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.4k | Automated safety check: Pass | MIT | |
| RecoveryMigoXLab/webqa-agent | 232 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Backup Recoverysickn33/agentic-awesome-skills | 47k | 2 repos | ~3k | Automated safety check: Warn | MIT | |
| Disaster Recoverysickn33/agentic-awesome-skills | 47k | 2 repos | ~3k | Automated safety check: Pass | MIT | |
| Testing Ransomware Recovery Proceduresmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Validating Backup Integrity For Recoverymukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Backup Recovery
sickn33/agentic-awesome-skills
Implement backup and recovery strategies. An agent skill from sickn33/agentic-awesome-skills.
Disaster Recovery
sickn33/agentic-awesome-skills
Implement disaster recovery strategies and runbooks. An agent skill from sickn33/agentic-awesome-skills.
Testing Ransomware Recovery Procedures
mukul975/Anthropic-Cybersecurity-Skills
Tests and validates ransomware recovery procedures - backup restore operations (e.g.
Validating Backup Integrity For Recovery
mukul975/Anthropic-Cybersecurity-Skills
Validates backup integrity through cryptographic hash verification, automated restore testing, corruption detection, and recoverability checks to confirm backups are reliable for disaster recovery…
Debugging and Error Recovery
addyosmani/agent-skills
Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.
More from LeoYeAI/openclaw-master-skills
All 1,235 skills in this repoDevOps Pipeline Management
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
Feishu Document Collaboration
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
Files Memory System
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
GEO-Claw AI Visibility Agent
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
Google Workspace CLI
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
HealthFit Health Advisors
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Questions about Session Recovery
What does Session Recovery do?
AI会话管理与优化系统。解决会话上下文限制问题，通过三级文档系统、自动化脚本和上下文压缩实现快速恢复。包含：STATUS.md快速索引、memory详细记录、自动更新脚本、上下文压缩策略、信息识别机制。适用于长期AI项目、多任务并行、需要高效会话恢复的场景。触发词：会话恢复、session recovery、上下文压缩、快速恢复、会话管理。. Session Recovery is an agent skill from LeoYeAI/openclaw-master-skills.
How do I install Session Recovery in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a claude-code`. Or copy the skill folder (skills/session-recovery in LeoYeAI/openclaw-master-skills) into .claude/skills/session-recovery in your project. Claude Code loads it when a task matches its description.
How do I install Session Recovery in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a codex`. Or copy the skill folder (skills/session-recovery in LeoYeAI/openclaw-master-skills) into .agents/skills/session-recovery in your project. Codex loads it when a task matches its description.
Can I use Session Recovery in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill session-recovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/session-recovery, .gemini/skills/session-recovery, .github/skills/session-recovery and .opencode/skills/session-recovery in your project.
What does Session Recovery need to run?
Going by SKILL.md and its folder, Session Recovery needs a shell and Python for the scripts in its folder and the command-line tools its instructions call (python3 and git). Our summary lists: Python 3; A Bash shell.
Does Session Recovery access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Session Recovery safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Session Recovery use?
Session Recovery is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Session Recovery use?
About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.4k tokens, read only when the agent opens those files.
What are the alternatives to Session Recovery?
Skills that share tags, products or a category with Session Recovery: Recovery (MigoXLab/webqa-agent, 232 stars), Backup Recovery (sickn33/agentic-awesome-skills, 47k stars), Disaster Recovery (sickn33/agentic-awesome-skills, 47k stars) and Testing Ransomware Recovery Procedures (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Session Recovery?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.