Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

create-runbook创建操作手册

Agent Skill

create-runbook 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

343

周安装

14

GitHub Stars

1

下载量

110
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:create-runbook(创建操作手册)
来源仓库:https://github.com/ethpandaops/mcp
仓库路径:skills/create-runbook
安装命令:
npx skills add https://github.com/ethpandaops/mcp --skill create-runbook
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/ethpandaops/mcp --skill create-runbook

简介

将多数据源调查过程转化为可复用操作手册。

  • 适用于复杂故障诊断和知识沉淀场景。create-runbook 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 提取 Xatu、Prometheus、Loki、Dora 等数据源查询模式。
  • 安装需确认 runbooks/ 目录和 YAML frontmatter 格式。
  • 输出包含步骤、数据源和结论的结构化 Markdown 文件。

SKILL.md

Create Runbook

Extract procedural knowledge from this conversation into a reusable runbook.

When to use this

After completing a multi-step investigation that:

  • Spanned multiple datasources (Xatu, Prometheus, Loki, Dora)
  • Followed a diagnostic pattern others could reuse
  • Discovered insights that would help future investigations

Runbook format

Create a markdown file with YAML frontmatter in the runbooks/ directory:

---
name: [Imperative title, e.g., "Investigate Finality Delay"]
description: [1-2 sentence summary for semantic search matching]
tags: [keywords for search, 3-6 tags]
prerequisites: [datasources needed, e.g., xatu, prometheus, dora]
---

[Opening paragraph explaining WHEN this runbook applies and WHAT problem it solves.
Use MUST/SHOULD/MAY keywords inline to indicate requirement levels.]

## Approach

1. **[Step title]** - [Description with MUST/SHOULD/MAY constraints inline]

[Optional: Example code if helpful, but prefer referencing search_examples]


1. **[Next step]** - Use `search_examples("relevant query")` for the query pattern. You SHOULD [constraint]. You MAY [optional action].

## Key Thresholds

[If applicable, include a table of healthy/warning/critical thresholds]

## Notes

- [Key insight or gotcha learned during the investigation]
- [Threshold values or timing considerations]

Constraint keywords (RFC 2119)

Use these keywords inline in the prose to indicate requirement levels:

  • MUST - Non-negotiable requirement. The investigation will fail or produce wrong results without this.
  • SHOULD - Strongly recommended. Skip only with good reason and document why.
  • MAY - Optional. Use judgment based on context and time available.

Guidelines for extraction

  1. Focus on the diagnostic pattern, not the specific incident details
  2. Reference examples instead of embedding queries - use search_examples("...")
  3. Include key thresholds discovered during the investigation
  4. Document gotchas - what would have tripped you up without prior knowledge?
  5. Keep it actionable - every step should tell the user what to do, not just what to think about

Naming conventions

  • File name: kebab-case.md (e.g., finality_delay.md, block-propagation.md)
  • Runbook name: Imperative mood (e.g., "Investigate X", "Diagnose Y", "Debug Z")
  • Tags: lowercase, single words or short phrases

Output

Save the runbook to: runbooks/[kebab-case-name].md

After creating the runbook, verify it loads correctly:

  1. The server should log "Runbook registry loaded" with the updated count
  2. The runbook should be searchable via search_runbooks

$ARGUMENTS

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.63%
按下载量换算41

Claude

32.49%
按下载量换算36

Cursor

17.65%
按下载量换算19

Gemini CLI

9.76%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills