Token导航 LogoToken导航

Agent Skill · 开发

ring%3adev-devops(环%3adev devops)

用于辅助云资源、部署、容器、基础设施和运维自动化任务。它适合让 Agent 检查配置、整理部署步骤、分析资源状态、生成排障思路或辅助云服务接入。使用时需要明确目标环境、账号权限、区域和资源组,区分本地测试与生产操作;涉及删除资源、重启服务、修改网络或权限配置时,应先确认影响范围。

ring%3adev-devops 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,暂无第三方扫描结果,按安装量在开发类的 21,746 个 Skill 里排第 13,600。

总安装 865周安装 35GitHub Stars 180下载 272核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:ring%3adev-devops(环%3adev devops)
来源仓库:https://github.com/lerianstudio/ring
仓库路径:skills/ring%3Adev-devops
安装命令:
npx skills add https://github.com/lerianstudio/ring --skill ring:dev-devops
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/lerianstudio/ring --skill ring:dev-devops

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

用于辅助云资源、部署、容器和运维自动化任务,适合检查配置与生成排障思路。支持明确目标环境与账号权限,区分本地测试与生产操作。涉及资源删除或服务重启时应先确认影响范围。通过 GitHub 仓库获取技能定义,需结合原始 README 确认具体用法。

ring%3adev-devops 属于开发类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ring%3Adev-devops

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/lerianstudio/ring --skill ring:dev-devops;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ring%3adev-devops 怎么安装?

在终端执行 npx skills add https://github.com/lerianstudio/ring --skill ring:dev-devops。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ring%3adev-devops 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ring%3adev-devops 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

ring%3adev-devops 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ring%3adev-devops 用的人多吗?

公开数据是累计安装 865 次,近一周安装 35 次,下载 272 次,GitHub 180 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ring%3adev-devops 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 要求有安全扫描结论才肯安装的团队。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
ring%3adev-devops

环%3adev devops · 本页

865180接触敏感数据未明确未收录

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

DevOps Setup (Gate 1)

Overview

This skill configures the development and deployment infrastructure:

  • Creates or updates Dockerfile for the application
  • Configures docker-compose.yml for local development
  • Documents environment variables in.env.example
  • Verifies the containerized application works

CRITICAL: Role Clarification

This skill ORCHESTRATES. DevOps Agent IMPLEMENTS.

WhoResponsibility
This SkillGather requirements, prepare prompts, validate outputs
DevOps AgentCreate Dockerfile, docker-compose,.env.example, verify

Step 1: Validate Input

<verify_before_proceed>

  • unit_id exists
  • language is valid (go|typescript|python)
  • service_type is valid (api|worker|batch|cli)
  • implementation_files is not empty </verify_before_proceed>
REQUIRED INPUT (from ring:dev-cycle orchestrator):
- unit_id: [TASK id — runs at task cadence, not per subtask]
- language: [go|typescript|python]
- service_type: [api|worker|batch|cli]
- implementation_files: [union of changed files across all subtasks of this task]
- gate0_handoffs: [array of per-subtask Gate 0 handoffs — one entry per subtask]

OPTIONAL INPUT:
- new_dependencies: [deps added in Gate 0]
- new_env_vars: [env vars needed]
- new_services: [postgres, redis, etc.]
- existing_dockerfile: [true/false]
- existing_compose: [true/false]

if any REQUIRED input is missing:
  → STOP and report: "Missing required input: [field]"
  → Return to orchestrator with error

Step 2: Analyze DevOps Requirements

1. Check existing files:
   - Dockerfile: [EXISTS/MISSING]
   - docker-compose.yml: [EXISTS/MISSING]
   - .env.example: [EXISTS/MISSING]

2. Determine actions needed:
   - Dockerfile: CREATE / UPDATE / NONE
   - docker-compose.yml: CREATE / UPDATE / NONE
   - .env.example: CREATE / UPDATE / NONE

3. Identify services needed:
   - From new_services input
   - From language (Go → alpine base, TS → node base)
   - From service_type (api → expose port, worker → no port)

Step 3: Initialize DevOps State

devops_state = {
  unit_id: [from input],
  dockerfile_action: "pending",
  compose_action: "pending",
  env_action: "pending",
  services: [],
  verification: {
    build: null,
    startup: null,
    health: null
  },
  iterations: 0,
  max_iterations: 3
}

Step 4: Dispatch DevOps Agent

<dispatch_required agent="ring:devops-engineer"> Create/update Dockerfile, docker-compose.yml, and.env.example for containerization. </dispatch_required>

Task:
  subagent_type: "ring:devops-engineer"
  description: "Create/update DevOps artifacts for [unit_id]"
  prompt: |
    ⛔ MANDATORY: Create all DevOps Artifacts

    ## Input Context
    - **Unit ID:** [unit_id]
    - **Language:** [language]
    - **Service Type:** [service_type]
    - **Implementation Files:** [implementation_files]
    - **New Dependencies:** [new_dependencies or "None"]
    - **New Environment Variables:** [new_env_vars or "None"]
    - **New Services Needed:** [new_services or "None"]

    ## Existing Files
    - Dockerfile: [EXISTS/MISSING]
    - docker-compose.yml: [EXISTS/MISSING]
    - .env.example: [EXISTS/MISSING]

    ## Standards Source (Cache-First Pattern)

    **Standards Source (Cache-First Pattern):** This sub-skill reads standards from `state.cached_standards` populated by dev-cycle Step 1.5. If invoked outside a cycle (standalone), it falls back to direct WebFetch with a warning. See `shared-patterns/standards-cache-protocol.md` for protocol details.

    ## Standards Reference

    URL: https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/devops.md

    **Cache-first loading protocol:**
    For each required standards URL:
      IF state.cached_standards[url] exists:
        → Read content from state.cached_standards[url].content
        → Log: "Using cached standard: {url} (fetched {state.cached_standards[url].fetched_at})"
      ELSE:
        → WebFetch url (fallback — should not happen if orchestrator ran Step 1.5)
        → Log warning: "Standard {url} was not pre-cached; fetched inline"

    You MUST implement all sections from devops.md.

    ## Requirements

    ### Dockerfile
    - Multi-stage build (builder → production)
    - Non-root USER (appuser)
    - Specific versions (no :latest)
    - HEALTHCHECK instruction
    - Layer caching optimization

    ### docker-compose.yml
    - Version: 3.8
    - App service with build context
    - Database/cache services as needed
    - Named volumes for persistence
    - Health checks with depends_on conditions
    - Network: app-network (bridge)

    ### .env.example
    - all variables with placeholders
    - Comments explaining each
    - Grouped by service
    - Required vs optional marked
    - **MANDATORY: Multi-tenant variables** (for ALL services):

# Multi-tenant configuration (MANDATORY) MULTI_TENANT_ENABLED=false MULTI_TENANT_URL=


    ## Required Output Format

    ### Standards Coverage Table
    | # | Section (from devops.md) | Status | Evidence |
    |---|--------------------------|--------|----------|
    | 1 | Containers | ✅/❌ | Dockerfile:[line] |
    | 2 | Docker Compose | ✅/❌ | docker-compose.yml:[line] |
    | 3 | Environment | ✅/❌ | .env.example:[line] |
    | 4 | Health Checks | ✅/❌ | [file:line] |

    ### Files Created/Updated
    | File | Action | Key Changes |
    |------|--------|-------------|
    | Dockerfile | Created/Updated | [summary] |
    | docker-compose.yml | Created/Updated | [summary] |
    | .env.example | Created/Updated | [summary] |

    ### Verification Commands

    <verify_before_proceed>
    - docker-compose build succeeds
    - docker-compose up -d starts all services
    - docker-compose ps shows healthy status
    - docker-compose logs shows JSON format
    </verify_before_proceed>

    Execute these and report results:
    1. `docker-compose build` → [PASS/FAIL]
    2. `docker-compose up -d` → [PASS/FAIL]
    3. `docker-compose ps` → [all healthy?]
    4. `docker-compose logs app | head -5` → [JSON logs?]

    ### Compliance Summary
    - **all STANDARDS MET:** ✅ YES / ❌ no
    - **If no, what's missing:** [list sections]

Step 5: Validate Agent Output

Parse agent output:

1. Extract Standards Coverage Table
2. Extract Files Created/Updated
3. Extract Verification results

if "all STANDARDS MET: ✅ YES" and all verifications PASS:
  → devops_state.dockerfile_action = [from table]
  → devops_state.compose_action = [from table]
  → devops_state.env_action = [from table]
  → devops_state.verification = {build: PASS, startup: PASS, health: PASS}
  → Proceed to Step 7

if any section has ❌ or any verification FAIL:
  → devops_state.iterations += 1
  → if iterations >= max_iterations: Go to Step 8 (Escalate)
  → Re-dispatch agent with specific failures

Step 6: Re-Dispatch for Fixes (if needed)

Task:
  subagent_type: "ring:devops-engineer"
  description: "Fix DevOps issues for [unit_id]"
  prompt: |
    ⛔ FIX REQUIRED - DevOps Standards Not Met

    ## Issues Found
    [list ❌ sections and FAIL verifications]

    ## Standards Reference

    URL: https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/devops.md

    **Cache-first loading protocol:**
    For each required standards URL:
      IF state.cached_standards[url] exists:
        → Read content from state.cached_standards[url].content
        → Log: "Using cached standard: {url} (fetched {state.cached_standards[url].fetched_at})"
      ELSE:
        → WebFetch url (fallback — should not happen if orchestrator ran Step 1.5)
        → Log warning: "Standard {url} was not pre-cached; fetched inline"

    Fix all issues and re-run verification commands.
    Return updated Standards Coverage Table with all ✅.

After fix → Go back to Step 5

Step 7: Prepare Success Output

Generate skill output:

## DevOps Summary
**Status:** PASS
**Unit ID:** [unit_id]
**Iterations:** [devops_state.iterations]

## Files Changed
| File | Action | Summary |
|------|--------|---------|
| Dockerfile | [CREATED/UPDATED/UNCHANGED] | [summary] |
| docker-compose.yml | [CREATED/UPDATED/UNCHANGED] | [summary] |
| .env.example | [CREATED/UPDATED/UNCHANGED] | [summary] |

## Services Configured
| Service | Image | Port | Health Check |
|---------|-------|------|--------------|
| app | [built] | [port] | [healthcheck] |
| [db] | [image] | [port] | [healthcheck] |
| [cache] | [image] | [port] | [healthcheck] |

## Verification Results
| Check | Status | Output |
|-------|--------|--------|
| Build | ✅ PASS | Successfully built |
| Startup | ✅ PASS | All services Up |
| Health | ✅ PASS | All healthy |
| Logging | ✅ PASS | JSON structured |

## Handoff to Next Gate
- DevOps status: COMPLETE
- Services: [list]
- Env vars: [count] documented
- Verification: all PASS
- Ready for Gate 2 (SRE): YES

Step 8: Escalate - Max Iterations Reached

Generate skill output:

## DevOps Summary
**Status:** FAIL
**Unit ID:** [unit_id]
**Iterations:** [max_iterations] (MAX REACHED)

## Files Changed
[list what was created/updated]

## Issues Remaining
[list unresolved issues]

## Verification Results
[list PASS/FAIL for each check]

## Handoff to Next Gate
- DevOps status: FAILED
- Ready for Gate 2: no
- **Action Required:** User must manually resolve issues

⛔ ESCALATION: Max iterations (3) reached. User intervention required.

Severity Calibration

SeverityCriteriaExamples
CRITICALSecurity risk, deployment blocked:latest tags, secrets in image, root user, missing HEALTHCHECK
HIGHBuild fails, services brokendocker-compose build fails, services don't start, no health checks
MEDIUMConfiguration gaps, optimization issuesMissing layer caching, no named volumes, incomplete.env.example
LOWBest practices, documentationMissing comments in Dockerfile, suboptimal ordering

Report all severities. CRITICAL = immediate fix. HIGH = fix before gate pass. MEDIUM = fix in iteration. LOW = document.


Pressure Resistance

See shared-patterns/shared-pressure-resistance.md for universal pressure scenarios.

User SaysYour Response
"Skip Docker, runs fine locally""Docker ensures consistency. Dispatching ring:devops-engineer now."
"Demo tomorrow, no time""Docker takes 30 min. Better than environment crash during demo."
"We'll containerize later""Later = never. Containerizing now."

Anti-Rationalization Table

See shared-patterns/shared-anti-rationalization.md for universal anti-rationalizations.

Gate 1-Specific Anti-Rationalizations

RationalizationWhy It's WRONGRequired Action
"Works fine locally"Your machine ≠ productionContainerize for consistency
"Docker is overkill"Docker is baseline, not overkillCreate Dockerfile
"Just need docker run"docker-compose is reproducibleUse docker-compose
"Lambda doesn't need Docker"SAM uses Docker locallyUse SAM containers

Execution Report Format

## DevOps Summary
**Status:** [PASS|FAIL|PARTIAL]
**Unit ID:** [unit_id]
**Duration:** [Xm Ys]
**Iterations:** [N]

## Files Changed
| File | Action |
|------|--------|
| Dockerfile | [CREATED/UPDATED/UNCHANGED] |
| docker-compose.yml | [CREATED/UPDATED/UNCHANGED] |
| .env.example | [CREATED/UPDATED/UNCHANGED] |

## Services Configured
| Service | Image | Port |
|---------|-------|------|
| [name] | [image] | [port] |

## Verification Results
| Check | Status |
|-------|--------|
| Build | ✅/❌ |
| Startup | ✅/❌ |
| Health | ✅/❌ |
| Logging | ✅/❌ |

## Handoff to Next Gate
- DevOps status: [COMPLETE|PARTIAL|FAILED]
- Ready for Gate 2: [YES|no]

平台分布

Codex

34.29%
按下载量换算93

Claude

28.4%
按下载量换算77

Cursor

18.66%
按下载量换算51

Gemini CLI

9.08%
按下载量换算25

安全审计

暂无安全审计结果可展示。

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills