Token导航 LogoToken导航

Agent Skill · 研究检索

world-crown(世界皇冠)

world-crown 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。

world-crown 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 50,488。

总安装 612周安装 26GitHub Stars 8下载 214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:world-crown(世界皇冠)
来源仓库:https://github.com/mrpaulscrivens/boring-zoo
仓库路径:skills/world-crown
安装命令:
npx skills add https://github.com/mrpaulscrivens/boring-zoo --skill world-crown
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/mrpaulscrivens/boring-zoo --skill world-crown

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。

world-crown 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。它服务于研究检索场景,帮助 Agent 高效定位所需信息。

使用 npx skills add 命令安装,实际能力需结合原始 README 确认。安装前应检查权限、维护状态及是否触发联网或文件读写。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/world-crown

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/mrpaulscrivens/boring-zoo --skill world-crown;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

world-crown 怎么安装?

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

world-crown 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。

world-crown 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。

world-crown 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。

world-crown 用的人多吗?

公开数据是累计安装 612 次,近一周安装 26 次,下载 214 次,GitHub 8 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。

world-crown 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
world-crown

世界皇冠 · 本页

6128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

World Crown

You guide the user through discovering their Crown — the positioning declaration that claims their territory in the marketplace.

Teaching Intro

Before asking any questions, share this brief context:

Your Crown is the single statement that declares what territory you rule. Not a tagline. Not a mission statement. Your positioning declaration that makes everything else obvious. A king doesn't list every village — he says "I rule the Northern Territories" and everyone understands. We're going to build yours from the work you've already done.

Process

Step 1: Read all prerequisite files

Use the Bash tool to check if world-code/voice.md, world-code/climax.md, world-code/method.md, and world-code/creation.md exist in the current working directory and read them:

cat world-code/voice.md
cat world-code/climax.md
cat world-code/method.md
cat world-code/creation.md

If any file does not exist or is empty, tell the user:

"Your Crown is built from your Voice, your Climax (the transformation), your Method (how you deliver it), and your Creation (the offer that packages it). We need all four foundations first."
  • If world-code/voice.md is missing, say "Let's start with your Voice." and invoke /world-voice.
  • If world-code/voice.md exists but world-code/climax.md is missing, say "Let's start with your Climax." and invoke /world-climax.
  • If both exist but world-code/method.md is missing, say "Let's define your Method first." and invoke /world-method.
  • If those three exist but world-code/creation.md is missing, say "Let's design your Creation first." and invoke /world-creation.

Stop here in any of those cases.

If all four files exist, read them and note:

  • From Voice: Tone & Character, Hard Rules, Authenticity Markers
  • From Climax: Transformation Promise, Who This Is For, Before State, After State
  • From Method: Methodology Name, Core Principle, Why It Works Differently
  • From Creation: Offer Name, BONES Breakdown (especially Obvious and New)

You will use these to auto-generate the Crown draft in Step 3 and apply the Voice throughout.

Step 2: Check for Existing Work

Check if world-code/crown.md already exists and is not empty.

If the file exists and is not empty:

  1. Read it
  2. Present a summary of what's already there
  3. Ask: "You already have a Crown built. Do you want to: a) Refine it — I'll show you each section and you tell me what to keep, change, or rethink b) Start fresh — We'll go through the full discovery process again c) Keep it — Move on to the next element"

If they choose REFINE: Walk through each section of the existing Crown file one at a time:

  • Crown Statement
  • Layer 1 (What You Do)
  • Layer 2 (How You Think)
  • Layer 3 (Who You Fight For)
  • Territory Claim

For each section, show what's there and ask: "Keep this, tweak it, or rethink it?"

  • Keep: Move to the next section
  • Tweak: Ask focused follow-up questions about what to change, then update
  • Rethink: Re-synthesize that layer from the prerequisite files and present a new draft

After walking through all sections, save the updated file (same format, same path) and skip to the Transition step.

If they choose START FRESH: Proceed with the normal flow (Step 3 onward). Overwrite the existing file at the end.

If they choose KEEP: Skip to the Transition step.

If the file does not exist or is empty: Proceed with the normal flow (Step 3 onward).

Step 3: Auto-generate Crown draft

Synthesize a Crown draft from the existing files. Map:

  • Layer 1 (What You Do): Pull from Climax's Transformation Promise + Creation's BONES "Obvious". The specific, concrete outcome.
  • Layer 2 (How You Think): Pull from Method's Core Principle + Creation's BONES "New". The belief/worldview that drives the approach.
  • Layer 3 (Who You Fight For): Pull from Climax's Who This Is For + Before State. The identity + emotional state — not demographics but gut-level recognition.

Combine the three layers into a Crown Statement — a single powerful declaration. Write it in their Voice.

Present the draft:

"I built this from everything you've already defined — your transformation, your method, your offer. Here's your Crown:" Crown Statement: [The combined declaration] Layer 1 — What You Do: [specific outcome] Layer 2 — How You Think: [driving principle] Layer 3 — Who You Fight For: [identity + emotion] "Now let's stress-test it."

Step 4: Validation questions — ask ONE AT A TIME

4 validation questions. These aren't discovery — they're testing the auto-generated draft. Ask each one, wait for the answer, and adjust if needed before moving to the next.

Question 1: The Gut Punch Test "Read your Crown out loud. Does your ideal person feel something visceral — not 'that sounds nice' but 'holy shit, finally someone who gets it'? What's your gut reaction?"

(Wait. If weak, ask what's missing — which layer doesn't land? Adjust that layer.)

Question 2: The Hell No Test "Who should immediately think 'that's definitely not for me' when they hear this? List 3-5 types of people this should repel. If everyone could see themselves in it, it's not a Crown."

(Wait. If they can't list repelled people, the Crown is too broad — tighten Layer 3.)

Question 3: The Territory Test "Could you defend this territory? Do you actually deliver this outcome (Layer 1), genuinely believe this principle (Layer 2), and truly understand these people (Layer 3)? Or are you claiming territory you don't rule?"

(Wait. If any layer feels inauthentic, rework that layer using their feedback.)

Question 4: The Competitor Territory Check "Who else serves a similar audience? How does your Crown create territory that's YOURS — not just 'better' but 'different'? Where are you the ONLY option, not the BEST option?"

(Wait. If their Crown overlaps too much with competitors, sharpen Layer 2 — the belief layer is usually what differentiates.)

Step 5: Refine

Incorporate feedback from the 4 tests. Max two refinement rounds. If the Crown still doesn't feel right, suggest they revisit after Conversation — real-world content often reveals positioning that abstract exercises miss.

Step 6: Save the file

Write the final Crown to world-code/crown.md in exactly this format:

# One Crown

## Crown Statement
[The complete positioning declaration]

## Layer 1: What You Do
[The specific outcome you deliver]

## Layer 2: How You Think
[The principle/belief that drives your approach]

## Layer 3: Who You Fight For
[Your audience's identity + emotional state]

## Territory Claim
[What specific territory this Crown stakes — and what it excludes]

Populate every section using the synthesized draft and validation feedback. Do not leave placeholders.

Step 7: Transition

After saving, tell the user:

"Your Crown is saved to world-code/crown.md. This is your positioning declaration — use it when someone asks what you do. Next up is your Conversation — how you create content that defends this territory and attracts the right people. Want to continue to Conversation now, or take a break?"
  • If they want to continue, invoke /world-conversation.
  • If they want a break, tell them they can return anytime with /world-code-start and it will pick up where they left off.

Key Principles

  • Auto-generate, don't interrogate. The user already answered 15+ questions across Voice, Climax, Method, and Creation. Crown synthesizes — it doesn't re-ask.
  • Test, don't discover. The 4 questions are validation tests, not open-ended discovery. The draft should be close; the questions refine it.
  • Three layers, one statement. The Crown Statement combines all three layers into something someone could say in conversation. The layers exist for clarity, but the statement is what matters.
  • Exclude to include. A Crown that includes everyone includes no one. The Hell No Test is as important as the Gut Punch Test.
  • Apply their Voice. The Crown Statement must sound like something THEY would say. Use their tone, vocabulary, and hard rules from voice.md.

平台分布

Codex

33.61%
按下载量换算72

Claude

30.59%
按下载量换算65

Cursor

19.21%
按下载量换算41

Gemini CLI

10.26%
按下载量换算22

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