← 返回 Skills 市场
Runbooks
作者
mikeclaw007
· GitHub ↗
· v1.0.0
· MIT-0
135
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install runbooks
功能描述
Operational procedures: triggers, steps, verification, rollback. Use when writing ops docs or improving incident speed.
安全使用建议
This skill is low-risk and internally consistent: it only contains procedural guidance for runbooks and does not request credentials, files, or installs. Before using: (1) verify outputs—do not paste secrets or environment-specific credentials into prompts; (2) remember the skill’s source/homepage is unspecified (provenance is limited), so prefer using it for drafting and review rather than executing automated changes; (3) if you enable autonomous invocation for agents, monitor their actions, but autonomous invocation here is the platform default and not, by itself, a problem.
功能分析
Type: OpenClaw Skill
Name: runbooks
Version: 1.0.0
The skill bundle is a purely instructional guide for creating and managing operational runbooks. The SKILL.md file defines a standard four-stage workflow (context, design, implementation, and iteration) for the AI agent to follow, with no evidence of malicious code, data exfiltration, or harmful prompt injection.
能力评估
Purpose & Capability
Name/description (runbooks — operational procedures, triggers, steps, verification, rollback) match the SKILL.md content. The skill requests no binaries, env vars, or config paths — consistent with a purely procedural guidance tool.
Instruction Scope
SKILL.md contains only workflow guidance: ask for context, propose stages, checklist, and quality bar. It does not instruct the agent to read files, access environment variables, call external endpoints, or exfiltrate data. The scope stays within authoring/consulting on runbooks.
Install Mechanism
No install spec and no code files — instruction-only. Nothing will be written to disk or downloaded as part of installation (lowest-risk install profile).
Credentials
No required environment variables, credentials, or config paths are declared or referenced in the instructions. Requested access is proportionate (none) to the skill's purpose.
Persistence & Privilege
always is false; the skill is user-invocable and may be invoked autonomously (platform default). There is no indication it modifies other skills or requests persistent system privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install runbooks - 安装完成后，直接呼叫该 Skill 的名称或使用
/runbooks触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of Runbooks Skill, providing structured operational guidance.
- Introduces a four-stage workflow: context clarification, planning, execution with validation/rollback, and post-run operation.
- Offers clear criteria for when to use structured runbook guidance versus freeform feedback.
- Includes actionable checklists, trade-off analysis, and verification steps.
- Emphasizes adaptability to user preference (structured workflow or freeform).
- Designed for producing practical, step-by-step operational procedures.
元数据
常见问题
Runbooks 是什么？
Operational procedures: triggers, steps, verification, rollback. Use when writing ops docs or improving incident speed. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 135 次。
如何安装 Runbooks？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install runbooks」即可一键安装，无需额外配置。
Runbooks 是免费的吗？
是的，Runbooks 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Runbooks 支持哪些平台？
Runbooks 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Runbooks？
由 mikeclaw007（@mikeclaw007）开发并维护，当前版本 v1.0.0。
推荐 Skills