Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计提醒

ansible-designer安塞布尔设计师

Agent Skill

ansible-designer 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

214

周安装

9

GitHub Stars

3

下载量

75
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:ansible-designer(安塞布尔设计师)
来源仓库:https://github.com/3a2dev/ansible-designer
仓库路径:skills/ansible-designer
安装命令:
npx skills add https://github.com/3a2dev/ansible-designer --skill ansible-designer
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/3a2dev/ansible-designer --skill ansible-designer

简介

ansible-designer 是一个 AI 辅助的 Ansible 项目脚手架工具。

  • 可生成符合 ansible-core 2.15+ 规范的新剧本、角色和模板。
  • 支持对现有剧本进行质量审查和更新迭代。
  • 安装前需确认权限范围、维护状态及是否涉及文件生成或远程执行。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

ansible-designer

AI-assisted Ansible authoring toolkit. Scaffolds, reviews, and updates Ansible projects with production-quality output following official ansible-core 2.15+ conventions.


Available Commands

Playbook Commands

CommandDescription
/ansible-designer:new-playbookCreate a new playbook (site, component, or AWX-ready)
/ansible-designer:review-playbookReview an existing playbook — severity report, no file modification
/ansible-designer:update-playbookUpdate a playbook — shows diff, requires confirmation

Role Commands

CommandDescription
/ansible-designer:new-roleScaffold a complete role — asks about multi-OS support
/ansible-designer:review-roleReview a role — severity report, no file modification
/ansible-designer:update-roleUpdate a role — shows diff, requires confirmation

Collection Commands

CommandDescription
/ansible-designer:new-collectionScaffold a new collection with galaxy.yml, plugins, roles structure
/ansible-designer:review-collectionReview a collection — severity report, no file modification
/ansible-designer:update-collectionUpdate a collection — shows diff, requires confirmation

ansible.cfg Commands

CommandDescription
/ansible-designer:new-confGenerate an annotated ansible.cfg for dev, CI, or AWX
/ansible-designer:review-confReview an ansible.cfg — severity report, no file modification
/ansible-designer:update-confUpdate ansible.cfg — shows diff, requires confirmation

Global Rules

Every sub-command enforces these rules without exception:

  1. Discovery first — At command start, read in order: CLAUDE.mdansible.cfgREADME.md → filesystem scan. Build internal context (roles, collections, paths, namespace). Skip if user already provided all required parameters inline. See references/discovery.md.
  2. Never overwrite silently — Before writing any file, show a summary (new files) or unified diff (modifications). Wait for explicit user confirmation (yes / y). Only write after confirmation.
  3. FQCN mandatory — Every module reference uses the Fully Qualified Collection Name. ansible.builtin.copy, never copy. ansible.builtin.service, never service. See references/best_practices.md for the complete mapping table.
  4. no_log: true on secrets — Every task handling passwords, tokens, API keys, vault variables, or credentials must include no_log: true.
  5. Tags on every task — Minimum: component name + action category (install, configure, service, validate, security, cleanup). No task may be untagged.
  6. review never modifiesreview-* commands produce a structured severity report (CRITICAL / WARNING / INFO) only. They never write, modify, or suggest sed commands. Report only.
  7. update always diffsupdate-* commands read the existing file, compute the change, show a unified diff, and wait for explicit confirmation before writing a single byte.
  8. Show file tree after writes — After any write operation, run find <path> -type f | sort and display the resulting file tree.
  9. Suggest next step — End every command with a concrete suggestion: which command to run next, or what to validate.

Standard Operational Flow

Every command follows this exact sequence:

Step 1 — Discovery

Read: CLAUDE.md → ansible.cfg → README.md → filesystem scan
Build: internal context (roles_path, collections_path, existing roles, collections, inventory)
Report: "Discovery complete: [summary of what was found]"

Skip Step 1 only if the user provided all required parameters inline.

Step 2 — Parameter Collection

  • If the user already provided all required parameters: proceed to Step 3.
  • Otherwise: ask one question at a time, using discovery context for smart defaults.
  • Never ask for something that can be inferred from discovery (e.g., don't ask for namespace if a collection already exists).

Step 3 — Pre-Write Confirmation

  • For new files: show a summary of what will be created (paths + brief description).
  • For update commands: show a unified diff (--- original, +++ proposed).
  • Wait for explicit user confirmation (yes, y, or equivalent) before proceeding.
  • If user says no: ask what to change and loop back to Step 2.

Step 4 — Execution

  • Write or modify files using bash commands.
  • Follow all global rules: FQCN, tags, no_log.
  • Use templates from the appropriate references/ file as the base.

Step 5 — Final Output

Show file tree of all created/modified files.
Suggest: "Next step: [specific actionable suggestion]"

Reference Files

FileUsed by
references/discovery.mdAll commands — Step 1
references/best_practices.mdAll commands — FQCN, tags, no_log, idempotency
references/playbook.mdnew-playbook, review-playbook, update-playbook
references/role.mdnew-role, review-role, update-role
references/collection.mdnew-collection, review-collection, update-collection
references/ansible_cfg.mdnew-conf, review-conf, update-conf
references/inventory.mdAll commands — inventory context

Installation

npx skills add 3A2DEV/ansible-designer -a claude-code

Requires Claude Code with bash_tool enabled.

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

33.06%
按下载量换算25

Claude

31.54%
按下载量换算24

Cursor

17.73%
按下载量换算13

Gemini CLI

8.19%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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