Token导航 LogoToken导航

Agent Skill · 研究检索

requirements-gatherer(需求收集者)

requirements-gatherer 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。

requirements-gatherer 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,权限为操作浏览器;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 45,401。

总安装 853周安装 17GitHub Stars 23下载 140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:requirements-gatherer(需求收集者)
来源仓库:https://github.com/camoa/claude-skills
仓库路径:skills/requirements-gatherer
安装命令:
npx skills add https://github.com/camoa/claude-skills --skill requirements-gatherer
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/camoa/claude-skills --skill requirements-gatherer

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。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 命令从指定仓库安装,需确认权限与维护状态。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。

requirements-gatherer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/requirements-gatherer

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/camoa/claude-skills --skill requirements-gathe…;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

    它需要操作浏览器,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

requirements-gatherer 怎么安装?

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

requirements-gatherer 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。

requirements-gatherer 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

requirements-gatherer 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。

requirements-gatherer 用的人多吗?

公开数据是累计安装 853 次,近一周安装 17 次,下载 140 次,GitHub 23 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。

requirements-gatherer 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。

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
requirements-gatherer

需求收集者 · 本页

85323操作浏览器未明确通过

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

Requirements Gatherer

Ask structured questions to define project requirements.

Activation

Activate when:

  • Invoked by project-initializer after project setup
  • User says "Gather requirements" or "Define requirements"
  • Starting Phase 1 on a new project

Workflow

1. Load Project Context

Use Read to get {project_path}/project_state.md. Extract:

  • Project name
  • Current scope (if any)
  • Existing requirements (if resuming)

2. Ask Questions by Category

Ask one category at a time. Wait for response before proceeding.

Category 1: Project Type & Scope

What type of project is this?
- [ ] New Drupal module (starting from scratch)
- [ ] Feature for existing module
- [ ] Core issue/patch
- [ ] Theme or sub-theme
- [ ] Configuration/site building
- [ ] Other (Claude Code plugin, documentation, etc.)

What does this project include?
- [ ] A single Drupal module
- [ ] Multiple related modules
- [ ] A theme or sub-theme
- [ ] Configuration/site building
- [ ] Mix of the above

Please describe:

Category 2: Core Functionality

What is the main purpose?
1. What problem does it solve?
2. What are the must-have features?
3. What are nice-to-have features?

Category 3: User Roles

Who will use this?
1. Which user roles need access?
2. What permissions are needed?
3. Any role-specific features?

Category 4: Data Requirements

What data is involved?
1. New content types or entities needed?
2. New fields on existing types?
3. Configuration data to store?
4. Relationships to existing content?

Category 5: Integrations

What existing systems does this connect to?
1. Existing Drupal modules to integrate with?
2. External APIs or services?
3. ECA workflows needed?
4. Third-party libraries?

Category 6: UI Requirements

What interfaces are needed?
1. Admin forms or pages?
2. Frontend display requirements?
3. Specific UX patterns to follow?
4. Mobile considerations?

Category 7: Constraints

What limitations should we know about?
1. Drupal version (10.x, 11.x)?
2. Performance requirements?
3. Accessibility requirements (WCAG level)?
4. Browser support needs?

3. Handle Responses

For each category:

  • Accept the answer
  • Allow "skip" or "not sure yet" - mark as open question
  • Summarize understanding back to user
  • Proceed to next category

4. Update project_state.md

After all categories, use Edit tool to update the Requirements section:

## Requirements

### Project Type
- {new module, existing feature, core issue, theme, config, other}

### Scope
- {what project includes}

### Core Functionality
- {requirement 1}
- {requirement 2}

### User Roles
| Role | Permissions | Features |
|------|-------------|----------|
| {role} | {perms} | {features} |

### Data Requirements
- {data type}: {storage approach}

### Integrations
- {module/service}: {integration type}

### UI Requirements
- {element}: {requirement}

### Constraints
- {constraint}: {details}

### Open Questions
- {questions marked as "not sure yet"}

5. Confirm Requirements

Show summary to user:

Requirements gathered for {project_name}:

Core: {1-2 sentence summary}
Roles: {list roles}
Integrations: {list integrations}
Open questions: {count}

Does this look complete? (yes/no/add more)

If "add more", ask what category to expand.

6. Transition to Task Definition

After user confirms requirements are complete:

Requirements complete!

Now let's define your first task. What feature or component do you want to work on first?

Examples:
- "Add settings form for API configuration"
- "Create custom entity for storing data"
- "Build admin dashboard"

Each task will go through:
1. Research (understand & find patterns)
2. Architecture (design the approach)
3. Implementation (build with TDD)

Enter your first task:

IMPORTANT: Do NOT suggest /research or /design at the project level. Tasks are what go through phases, not the project.

7. Create First Task

When user provides a task name:

  1. Validate task name - convert to lowercase with underscores (e.g., "Add settings form" → settings_form)
  2. Confirm task creation: Creating task: {task_name} Brief description (one sentence - what does this task accomplish?):
  3. Wait for user to provide description
  4. Invoke research phase: Starting research phase for: {task_name} Then invoke /drupal-dev-framework:research {task_name}

CRITICAL: Do NOT start research until:

  • Task name is confirmed
  • User provides a description
  • Task creation is acknowledged

Stop Points

STOP and wait for user after:

  • Each category question
  • Showing summary for confirmation
  • Asking for first task
  • After asking for task description (Step 7.2)
  • User says "add more"

平台分布

Codex

37.81%
按下载量换算53

Claude

27.34%
按下载量换算38

Cursor

19.53%
按下载量换算27

Gemini CLI

9.77%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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