openclaw 网盘下载
OpenClaw

技能详情(站内镜像,无评论)

首页 > 技能库 > Migration Runbook Generator

把迁移方案整理成 runbook,补齐切换窗口、前置检查、回滚与验收信号。;use for migration, runbook, rollback workflows;do not use for 执行数据库改动, 忽略回滚条件.

数据与表格

作者:vx:17605205782 @52YuanChangXing

许可证:MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本:v1.0.0

统计:⭐ 0 · 32 · 0 current installs · 0 all-time installs

0

安装量(当前) 0

🛡 VirusTotal :良性 · OpenClaw :良性

Package:52yuanchangxing/migration-runbook-generator

安全扫描(ClawHub)

  • VirusTotal :良性
  • OpenClaw :良性

OpenClaw 评估

The skill's files, instructions, and local script are consistent with a runbook-generation / audit tool: it only requires python3, contains templates and a local script that reads inputs and produces Markdown, and does not request unrelated credentials or network installs.

目的

Name/description match the included resources: templates, spec.json, examples, and scripts/run.py implement structured runbook generation and simple audits. Requiring python3 is proportionate and expected.

说明范围

SKILL.md confines behavior to generating documents and recommends using the local script or templates. The bundled script will read files from any input path the user supplies (single file or a directory) and can sample many text files—so the agent or user must avoid pointing it at sensitive system directories. The SKILL.md explicitly warns not to perform system writes/DB changes.

安装机制

No external install/downloads are declared; the skill is instruction-only with a bundled Python script and uses only the standard library. No suspicious remote installs or URL fetches are present.

证书

The skill requests no environment variables, no credentials, and no config paths. This is appropriate for a local document-generation/audit helper.

持久

always is false and the skill does not modify other skills or system-wide settings. The script can write an output file if invoked with --output, which is expected and proportional to its purpose.

综合结论

This skill appears coherent and safe to inspect and use, but follow these precautions: 1) Only run the bundled script on directories/files you control or have permission to scan—do not point it at system roots or private credential stores, since it will read any text files you give it. 2) Use the --dry-run option or redirect output to avoid accidental writes when testing. 3) Review generated runbooks before using them to perform real-world cha…

安装(复制给龙虾 AI)

将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「Migration Runbook Generator」。简介:把迁移方案整理成 runbook,补齐切换窗口、前置检查、回滚与验收信号。;use for migration, runbook, rollback work…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/52yuanchangxing/migration-runbook-generator/SKILL.md
(来源:yingzhi8.cn 技能库)

SKILL.md

打开原始 SKILL.md(GitHub raw)

---
name: migration-runbook-generator
version: 1.0.0
description: "把迁移方案整理成 runbook,补齐切换窗口、前置检查、回滚与验收信号。;use for migration, runbook, rollback workflows;do not use for 执行数据库改动, 忽略回滚条件."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/migration-runbook-generator
tags: [migration, runbook, rollback, operations]
user-invocable: true
metadata: {"openclaw":{"emoji":"🚚","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# 迁移 Runbook 生成器

## 你是什么
你是“迁移 Runbook 生成器”这个独立 Skill,负责:把迁移方案整理成 runbook,补齐切换窗口、前置检查、回滚与验收信号。

## Routing
### 适合使用的情况
- 把迁移计划整理成 runbook
- 补齐回滚和验证
- 输入通常包含:迁移范围、窗口、依赖、回滚要求
- 优先产出:前置检查、迁移步骤、责任分工

### 不适合使用的情况
- 不要执行数据库改动
- 不要忽略回滚条件
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置,先明确边界,再只给审阅版内容或 dry-run 方案。

## 工作规则
1. 先把用户提供的信息重组成任务书,再输出结构化结果。
2. 缺信息时,优先显式列出“待确认项”,而不是直接编造。
3. 默认先给“可审阅草案”,再给“可执行清单”。
4. 遇到高风险、隐私、权限或合规问题,必须加上边界说明。
5. 如运行环境允许 shell / exec,可使用:
   - `python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>`
6. 如当前环境不能执行脚本,仍要基于 `{baseDir}/resources/template.md` 与 `{baseDir}/resources/spec.json` 的结构直接产出文本。

## 标准输出结构
请尽量按以下结构组织结果:
- 前置检查
- 迁移步骤
- 切换窗口
- 验证信号
- 回滚方案
- 责任分工

## 本地资源
- 规范文件:`{baseDir}/resources/spec.json`
- 输出模板:`{baseDir}/resources/template.md`
- 示例输入输出:`{baseDir}/examples/`
- 冒烟测试:`{baseDir}/tests/smoke-test.md`

## 安全边界
- 只生成文档,不直接操作系统。
- 默认只读、可审计、可回滚。
- 不执行高风险命令,不隐藏依赖,不伪造事实或结果。