Token导航 LogoToken导航

Agent Skill · 研究检索

agile-intake(敏捷摄入)

agile-intake 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。

agile-intake 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,权限为只读;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 66,030。

总安装 269周安装 11GitHub Stars 公开资料未说明下载 87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:agile-intake(敏捷摄入)
来源仓库:https://github.com/djalmajr/essential-skills
仓库路径:skills/agile-intake
安装命令:
npx skills add https://github.com/djalmajr/essential-skills --skill agile-intake
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/djalmajr/essential-skills --skill agile-intake

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。

agile-intake 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。它将模糊问题或未结构化请求转化为清晰可操作的 intake 文档,支持多语言输出与模板本地化。

通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 核验具体用法和模板翻译。使用前应确认权限范围、维护状态,并评估是否触发文件读取或知识库查询操作。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。

来源仓库内路径:skills/agile-intake

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/djalmajr/essential-skills --skill agile-intake;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

agile-intake 怎么安装?

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

agile-intake 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。

agile-intake 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

agile-intake 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。

agile-intake 用的人多吗?

公开数据是累计安装 269 次,近一周安装 11 次,下载 87 次。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。

agile-intake 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 只想先试试效果、不希望它改动本地文件的人。

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
agile-intake

敏捷摄入 · 本页

269—只读未明确通过

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

Intake

Use this skill to transform vague problems, initial ideas, or unstructured requests into clear, actionable intake documents.

Initial context received via slash: $ARGUMENTS

If $ARGUMENTS is filled (e.g., file path, text, issue reference, URL), use as starting point for the intake. If empty, start by asking for a short description of the problem.

Language

Write the artifact in the user's language. Apply correct grammar and any required diacritics or script-specific characters. If the user's language is unclear, ask before generating output. Templates are in English — translate headers and content to match.

Objective

  • Make the problem or opportunity explicit before planning
  • Identify constraints, premises, and open questions
  • Define the next step in the flow: /agile-roadmap, /agile-epic, or /agile-story
  • Avoid work starting without clarity about what is being solved

When to use

  • Someone brings an idea, need, or problem without defined scope
  • The request is too vague to become an epic or task directly
  • There is uncertainty about size, priority, or approach
  • It is the first contact with a new problem

When NOT to use

  • The problem is already clear and scope is defined — use /agile-epic or /agile-story directly
  • The work has already been decomposed — go to /agile-epic or /agile-story
  • It's a trivial fix — use /agile-story directly

Intake process

1. Listen and record

Ask the user:

  • What is the problem or opportunity?
  • Who is affected and how?
  • Is there urgency or deadline?
  • What constraints are already known?

Don't assume answers. If the user doesn't know, register as an open question.

2. Structure the intake

Fill in the template with collected information:

  • Context: problem, initial objective, value signal, constraints
  • Initial scope: what is included and what is not (even if provisional)
  • Inputs and references: stakeholders, documents, technical context
  • Open questions: everything that doesn't have an answer yet

3. Define next step

Based on trajectory complexity (not duration):

  • Multi-phase trajectory with dependencies (regardless of total duration) → /agile-roadmap → then /agile-epic Indicators — if 2+ apply, use roadmap:

- Multiple initiatives that need sequencing (can't run all in parallel) - Decisions today affect future decisions (local optimization can become tech debt) - Stakeholders need to see the whole journey before approving individual steps - External dependencies (other teams, vendors, deadlines) - Total complexity exceeds what fits in a single epic

  • Single coordinated initiative with broad scope → /agile-epic
  • Medium problem with reasonable scope → /agile-epic (to decompose into stories)
  • Small and clear problem → /agile-story
Important: Roadmap is not defined by time horizon (e.g., "3-12 months"). A 4-week initiative with 5 distinct phases and critical ordering also benefits from a roadmap. The criterion is trajectory complexity, not duration.

Register the recommendation in the intake and confirm with the user.

Flow rule: For large or complex items, decomposition via /agile-epic is mandatory before execution. Only small, localized items can skip directly to /agile-story.

4. Save the intake

  • Ask for the initiative name (e.g., "component-tests", "auth-refactor")
  • Save at planning/<initiative>/intake.md
  • If the user prefers not to save, present inline

5. Chain

After user confirmation, offer to generate the next artifact following the official flow:

  • Multi-phase trajectory → "Do you want me to create the /agile-roadmap?"
  • Single coordinated initiative → "Do you want me to run /agile-epic to decompose into stories?"
  • Small/clear → "Do you want me to create the /agile-story?"

6. Validate

Before closing the intake, confirm:

  • The problem is clear enough for the next step
  • Constraints and premises have been made explicit
  • The next artifact in the flow has been defined

Rules

  • Never jump straight to implementation from an intake. The intake generates the next artifact, not code.
  • If the user insists on starting without clarity, register the risks and ask if they want to proceed anyway.
  • The intake should be short — 10 to 15 minutes of conversation maximum. If it takes longer, the problem probably needs /agile-epic decomposition.
  • Keep the tone of discovery, not detailed planning.

Template

Use ~/.agents/templates/intake.md as base for the artifact.

Relationship with the flow

flowchart LR
    A["/agile-intake"] --> B{next step}
    B --> C["/agile-roadmap"]
    B --> D["/agile-epic"]
    B --> E["/agile-story"]

This skill is the entry point of the flow. It captures the problem and directs to the correct skill. For guidance on which skill to use, you can also use /agile-router.

平台分布

Codex

34.42%
按下载量换算30

Claude

30.83%
按下载量换算27

Cursor

17.35%
按下载量换算15

Gemini CLI

9.2%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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