Token导航 LogoToken导航

Agent Skill · 研究检索

greenfield(greenfield 搜索)

greenfield 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。

greenfield 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,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 65,351。

总安装 282周安装 12GitHub Stars 6下载 99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:greenfield(greenfield 搜索)
来源仓库:https://github.com/duc01226/easyplatform
仓库路径:skills/greenfield
安装命令:
npx skills add https://github.com/duc01226/easyplatform --skill greenfield
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/duc01226/easyplatform --skill greenfield

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。

用于查找、检索和筛选相关信息。greenfield 属于研究检索类 Skill,可作为该场景下的辅助能力补充。适合根据关键词或任务场景快速定位候选结果。可结合原始 README 进一步验证具体功能和使用方法。安装前建议确认权限范围和维护状态,避免意外执行命令。

安装方式:通过 GitHub 仓库安装,支持 Codex、Claude 等宿主。

来源仓库内路径:skills/greenfield

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/duc01226/easyplatform --skill greenfield;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

    它需要需要联网,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

greenfield 怎么安装?

在终端执行 npx skills add https://github.com/duc01226/easyplatform --skill greenfield。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

greenfield 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。

greenfield 需要什么权限?

权限级别是需要联网。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。

greenfield 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。

greenfield 用的人多吗?

公开数据是累计安装 282 次,近一周安装 12 次,下载 99 次,GitHub 6 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。

greenfield 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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

  • 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

  • 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
greenfield

greenfield 搜索 · 本页

2826需要联网未明确有提醒

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

MANDATORY IMPORTANT MUST ATTENTION use TaskCreate to break ALL work into small tasks BEFORE starting. MANDATORY IMPORTANT MUST ATTENTION use AskUserQuestion at EVERY stage — validate decisions before proceeding. MANDATORY IMPORTANT MUST ATTENTION NEVER ask tech stack upfront — business analysis and domain modeling first.

Quick Summary

Goal: Guide greenfield project inception from raw idea to an approved, implementable project plan using a full waterfall process.

Workflow (16 steps):

  1. Discovery (/idea) — Interview user about problem, vision, constraints, team skills, scale. DO NOT ask about tech stack — keep business-focused.
  2. Market Research (/web-research) — WebSearch for competitors, market landscape, existing solutions
  3. Deep Research (/deep-research) — WebFetch top sources, extract key findings
  4. Business Evaluation (/business-evaluation) — Viability assessment, risk matrix, value proposition
  5. Domain Analysis & ERD (/domain-analysis) — Bounded contexts, aggregates, entities, ERD diagram, domain events. Validate every context boundary with user.
  6. Tech Stack Research (/tech-stack-research) — Derive technical requirements from business + domain analysis. Research top 3 options per stack layer (backend, frontend, database, messaging, infra). Detailed pros/cons matrix, team-fit scoring, market analysis. Present comparison report for user to decide.
  7. Architecture Design (/architecture-design) — Research and compare top 3 architecture styles (Clean, Hexagonal, Vertical Slice, etc.). Evaluate design patterns (CQRS, Repository, Mediator). Audit against SOLID, DRY, KISS, YAGNI. Validate scalability, maintainability, IoC, technical agnosticism. Present comparison with recommendation.
  8. Implementation Plan (/plan) — Create phased plan using confirmed tech stack + architecture + domain model
  9. Security Audit (/security) — Review plan for OWASP Top 10, auth patterns, data protection concerns
  10. Performance Audit (/performance) — Review plan for performance bottlenecks, scalability, query optimization
  11. Plan Review (/plan-review) — Full plan review, risk assessment, approval
  12. Refine to PBI (/refine) — Transform idea + reviewed plan into actionable PBI with acceptance criteria
  13. User Stories (/story) — Break PBI into implementable user stories
  14. Plan Validation (/plan-validate) — Interview user with critical questions to validate plan + stories
  15. Test Strategy (/tdd-spec) — Test pyramid, frameworks, spec outline
  16. Workflow End (/workflow-end) — Clean up, announce completion

Key Rules:

  • PLANNING ONLY: never implement code
  • Every stage saves artifacts to plan directory
  • MANDATORY IMPORTANT MUST ATTENTION every stage requires AskUserQuestion validation before proceeding
  • Delegate architecture decisions to solution-architect agent
  • Present 2-4 options for every major decision with confidence %
  • Business-First Protocol: Tech stack is NEVER asked upfront. Business analysis (steps 1-5) + domain modeling (step 6) must complete first. Tech stack is derived from requirements through research and presented as a comparison report with options.
  • MANDATORY IMPORTANT MUST ATTENTION architecture design and scaffold steps MUST ATTENTION include code quality gate tooling setup — linter, static analyzer, formatter, pre-commit hooks, CI quality gates, and build-time enforcement are NON-SKIPPABLE infrastructure.

Entry Point

This skill is the explicit entry point for the greenfield-init workflow.

When invoked:

  1. Activate the greenfield-init workflow via /workflow-start greenfield-init
  2. The workflow handles step sequencing, task creation, and progress tracking
  3. Each step delegates to the appropriate skill (idea, web-research, domain-analysis, tech-stack-research, etc.)
  4. The solution-architect agent provides architecture guidance throughout

When to Use

  • Starting a brand-new project from scratch
  • No existing codebase (empty project directory)
  • Planning a new application before writing any code
  • Want structured waterfall inception with user collaboration at every step

When NOT to Use

  • Existing codebase with code (use /plan or /feature instead)
  • Bug fixes, refactoring, or feature implementation
  • Quick prototyping (use /cook-fast instead)

Output

All artifacts saved to plan directory:

plans/{id}/
  research/
    discovery-interview.md
    market-research.md
    deep-research.md
    business-evaluation.md
    domain-analysis.md
    tech-stack-comparison.md
    architecture-design.md
  phase-01-domain-model.md
  phase-02-tech-stack.md
  phase-02b-architecture.md
  phase-03-project-structure.md
  phase-04-test-strategy.md
  phase-05-backlog.md
  plan.md (master plan with YAML frontmatter)

After completion, recommend next step: /cook to scaffold the project structure.

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).


MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks — one per workflow step. MANDATORY IMPORTANT MUST ATTENTION validate with user at EVERY step — never auto-decide. MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality and identify fixes/enhancements.


Closing Reminders

  • MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
  • MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
  • MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
  • MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

平台分布

Codex

35.92%
按下载量换算36

Claude

30.17%
按下载量换算30

Cursor

20.26%
按下载量换算20

Gemini CLI

10.81%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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