Token导航 LogoToken导航

Agent Skill · 研究检索

oma-dev-workflow(oma 开发工作流程)

oma-dev-workflow 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。

oma-dev-workflow 是研究检索类 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,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 40,130。

总安装 1,322周安装 54GitHub Stars 18下载 428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:oma-dev-workflow(oma 开发工作流程)
来源仓库:https://github.com/gracefullight/stock-checker
仓库路径:skills/oma-dev-workflow
安装命令:
npx skills add https://github.com/gracefullight/stock-checker --skill oma-dev-workflow
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/gracefullight/stock-checker --skill oma-dev-workflow

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

oma-dev-workflow 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限和维护状态。

使用前建议核实是否会触发联网、命令执行或文件读写操作。可结合原始 README 进一步了解具体用法和功能边界。

来源仓库内路径:skills/oma-dev-workflow

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/gracefullight/stock-checker --skill oma-dev-wo…;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

oma-dev-workflow 怎么安装?

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

oma-dev-workflow 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。

oma-dev-workflow 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。

oma-dev-workflow 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。

oma-dev-workflow 用的人多吗?

公开数据是累计安装 1,322 次,近一周安装 54 次,下载 428 次,GitHub 18 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。

oma-dev-workflow 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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。
  • 需要处理研究检索类任务、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。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
oma-dev-workflow

oma 开发工作流程 · 本页

1,32218接触敏感数据未明确未通过

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

Dev Workflow - Monorepo Task Automation Specialist

When to use

  • Running development servers for monorepo with multiple applications
  • Executing lint, format, typecheck across multiple apps in parallel
  • Managing database migrations and schema changes
  • Generating API clients or code from schemas
  • Building internationalization (i18n) files
  • Executing production builds and deployment preparation
  • Running parallel tasks in monorepo context
  • Setting up pre-commit validation workflows
  • Troubleshooting mise task failures or configuration issues
  • Optimizing CI/CD pipelines with mise

When NOT to use

  • Database schema design or query tuning -> use DB Agent
  • Backend API implementation -> use Backend Agent
  • Frontend UI implementation -> use Frontend Agent
  • Mobile development -> use Mobile Agent

Core Rules

  1. Always use mise run tasks instead of direct package manager commands
  2. Run mise install after pulling changes that might update runtime versions
  3. Use parallel tasks (mise run lint, mise run test) for independent operations
  4. Run lint/test only on apps with changed files (lint:changed, test:changed)
  5. Validate commit messages with commitlint before committing
  6. Run pre-commit validation pipeline for staged files only
  7. Configure CI to skip unchanged apps for faster builds
  8. Check mise tasks --all to discover available tasks before running
  9. Verify task output and exit codes for CI/CD integration
  10. Document task dependencies in mise.toml comments
  11. Use consistent task naming conventions across apps
  12. Enable mise in CI/CD pipelines for reproducible builds
  13. Pin runtime versions in mise.toml for consistency
  14. Test tasks locally before committing CI/CD changes
  15. Never use direct package manager commands when mise tasks exist
  16. Never modify mise.toml without understanding task dependencies
  17. Never skip mise install after toolchain version updates
  18. Never run dev servers without checking port availability first
  19. Never commit without running validation on affected apps
  20. Never ignore task failures - always investigate root cause
  21. Never hardcode secrets in mise.toml files
  22. Never assume task availability - always verify with mise tasks
  23. Never run destructive tasks (clean, reset) without confirmation
  24. Never skip reading task definitions before running unfamiliar tasks

Technical Guidelines

Prerequisites

# Install mise
curl https://mise.run | sh

# Activate in shell
echo 'eval "$(~/.local/bin/mise activate)"' >> ~/.zshrc

# Install all runtimes defined in mise.toml
mise install

# Verify installation
mise list

Project Structure (Monorepo)

project-root/
├── mise.toml            # Root task definitions
├── apps/
│   ├── api/            # Backend application
│   │   └── mise.toml   # App-specific tasks
│   ├── web/            # Frontend application
│   │   └── mise.toml
│   └── mobile/         # Mobile application
│       └── mise.toml
├── packages/
│   ├── shared/         # Shared libraries
│   └── config/         # Shared configuration
└── scripts/            # Utility scripts

Task Syntax

Root-level tasks:

mise run lint        # Lint all apps (parallel)
mise run test        # Test all apps (parallel)
mise run dev         # Start all dev servers
mise run build       # Production builds

App-specific tasks:

# Syntax: mise run //{path}:{task}
mise run //apps/api:dev
mise run //apps/api:test
mise run //apps/web:build

Common Task Patterns

Task TypePurposeExample
devStart development servermise run //apps/api:dev
buildProduction buildmise run //apps/web:build
testRun test suitemise run //apps/api:test
lintRun lintermise run lint
formatFormat codemise run format
typecheckType checkingmise run typecheck
migrateDatabase migrationsmise run //apps/api:migrate

Reference Guide

TopicResource FileWhen to Load
Validation Pipelineresources/validation-pipeline.mdGit hooks, CI/CD, change-based testing
Database & Infrastructureresources/database-patterns.mdMigrations, local Docker infra
API Generationresources/api-workflows.mdGenerating API clients
i18n Patternsresources/i18n-patterns.mdInternationalization
Release Coordinationresources/release-coordination.mdVersioning, changelog, releases
Troubleshootingresources/troubleshooting.mdDebugging issues

Task Dependencies

Define dependencies in mise.toml:

[tasks.build]
depends = ["lint", "test"]
run = "echo 'Building after lint and test pass'"

[tasks.dev]
depends = ["//apps/api:dev", "//apps/web:dev"]

Parallel vs Sequential Execution

Parallel (independent tasks):

# Runs all lint tasks simultaneously
mise run lint

Sequential (dependent tasks):

# Runs in order: lint → test → build
mise run lint && mise run test && mise run build

Mixed approach:

# Start dev servers in background
mise run //apps/api:dev &
mise run //apps/web:dev &
wait

Environment Variables

Common patterns for monorepo env vars:

# Database
DATABASE_URL=postgresql://user:pass@localhost:5432/db

# Cache
REDIS_URL=redis://localhost:6379/0

# API
API_URL=http://localhost:8000

# Frontend
PUBLIC_API_URL=http://localhost:8000

Output Templates

When setting up development environment:

  1. Runtime installation verification (mise list)
  2. Dependency installation commands per app
  3. Environment variable template (.env.example)
  4. Development server startup commands
  5. Common task quick reference

When running tasks:

  1. Command executed with full path
  2. Expected output summary
  3. Duration and success/failure status
  4. Next recommended actions

When troubleshooting:

  1. Diagnostic commands (mise config, mise doctor)
  2. Common issue solutions
  3. Port/process conflict resolution
  4. Cleanup commands if needed

Troubleshooting Guide

IssueSolution
Task not foundRun mise tasks --all to list available tasks
Runtime not foundRun mise install to install missing runtime
Task hangsCheck for interactive prompts, use --yes if available
Port already in useFind process: lsof -ti:PORT then kill
Permission deniedCheck file permissions, try with proper user
Missing dependenciesRun mise run install or app-specific install

How to Execute

Follow the core workflow step by step:

  1. Analyze Task Requirements - Identify which apps are affected and task dependencies
  2. Check mise Configuration - Verify mise.toml structure and available tasks
  3. Determine Execution Strategy - Decide between parallel vs sequential task execution
  4. Run Prerequisites - Install runtimes, dependencies if needed
  5. Execute Tasks - Run mise tasks with proper error handling
  6. Verify Results - Check output, logs, and generated artifacts
  7. Report Status - Summarize success/failure with actionable next steps

Execution Protocol (CLI Mode)

Vendor-specific execution protocols are injected automatically by oh-my-ag agent:spawn. Source files live under ../_shared/runtime/execution-protocols/{vendor}.md.

References

  • Clarification: ../_shared/core/clarification-protocol.md
  • Difficulty assessment: ../_shared/core/difficulty-guide.md

Knowledge Reference

mise, task runner, monorepo, dev server, lint, format, test, typecheck, build, deployment, ci/cd, parallel execution, workflow, automation, tooling

平台分布

Codex

33%
按下载量换算141

Claude

28.33%
按下载量换算121

Cursor

19.52%
按下载量换算84

Gemini CLI

9.53%
按下载量换算41

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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