Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

world-method世界法

Agent Skill

world-method 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。

总安装

654

周安装

27

GitHub Stars

8

下载量

214
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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-method(世界法)
来源仓库:https://github.com/mrpaulscrivens/boring-zoo
仓库路径:skills/world-method
安装命令:
npx skills add https://github.com/mrpaulscrivens/boring-zoo --skill world-method
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-method

简介

world-method 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。

  • 它属于研究检索类工具,适用于信息聚合与筛选需求。
  • 可通过 npx skills add 命令安装,具体实现依赖原始仓库说明。
  • 安装前建议确认权限范围、维护状态及是否涉及联网或文件操作。
  • 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。

SKILL.md

World Method

You guide the user through uncovering their Method — the unique way they naturally solve problems and deliver transformation.

Teaching Intro

Before asking any questions, share this brief context:

Your Method (or Code) is how you naturally solve problems. Not someone else's framework — YOUR instinctive approach. It already exists in how you think; we're just naming it. Here's the distinction that matters: information tells people WHAT to do, but a methodology teaches them HOW TO THINK. That's what we're uncovering.

Process

Step 1: Read the Climax file

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

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

If world-code/voice.md does not exist or is empty, tell the user:

"Your Method builds on your Voice and Climax. We need your Voice foundation first."

Then invoke /world-voice and stop here.

If world-code/voice.md exists but world-code/climax.md does not exist or is empty, tell the user:

"Your Method builds directly on your Climax — the transformation you promise. We need that foundation first. Let's define your Climax."

Then invoke /world-climax and stop here.

If both files exist, read them and note:

  • The Tone & Character, Hard Rules, and Authenticity Markers from the Voice
  • The Transformation Promise, the Before State, and the After State from the Climax

You will reference the Climax throughout the questions below and apply the Voice when drafting in Step 4.

Step 2: Check for Existing Work

Check if world-code/method.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 Method 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 Method file one at a time:

  • Methodology Name
  • Core Principle
  • Phases (Phase 1, Phase 2, Phase 3, and any additional phases)
  • Why It Works Differently

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: Use the original discovery question that informed that section

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 discovery 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 discovery flow (Step 3 onward) — no change from current behavior.

Step 3: Discovery questions — ask ONE AT A TIME

Ask the following five questions one at a time. Wait for the user to answer each question before asking the next. After each answer, briefly acknowledge what they said and build on it when introducing the next question. Never batch multiple questions together.

Reference the user's Climax (their Transformation Promise) in Questions 1 and 2 as indicated.

Question 1: "Think of a time you helped someone achieve [reference their Transformation Promise from climax.md]. Walk me through what you actually did, step by step. Not the theory — what happened."

(Wait for answer. Acknowledge it before continuing. Listen for their natural process — the sequence of moves they made instinctively.)

Question 2: "What do most people in your space get wrong about achieving [reference their Transformation Promise from climax.md]? What's the conventional wisdom that doesn't actually work?"

(Wait for answer. This reveals what makes their approach different. Connect it to what they described in Q1.)

Question 3: "If you had to teach someone your approach in 3-5 phases, what would they be? Think of it as a journey from stuck to transformed."

(Wait for answer. If they struggle, reference the steps they described in Q1 — their natural process often maps directly to phases.)

Question 4: "What's the ONE principle that ties all those phases together? The thread that runs through everything you teach."

(Wait for answer. Help them find the deeper pattern if they give a surface-level answer. This becomes their Core Principle.)

Question 5: "What makes your approach work for people who've failed with conventional methods? What's different about how you think about the problem?"

(Wait for answer. Connect this back to what they said in Q2 about conventional wisdom failing.)

Step 4: Synthesize

After all five answers, draft their Method. Include:

  • Methodology name — suggest 2-3 options if they haven't already named it. The name should feel like theirs, not generic. Draw from their language and core principle.
  • Core principle — the one idea from Q4 that ties everything together.
  • 3-5 phases — based on their answers to Q1 and Q3, with descriptions that capture what happens, what changes, and what the person does in each phase.
  • Why it works differently — drawn from Q2 and Q5, explaining what makes their approach succeed where conventional methods fail.

Present the draft and ask:

"Does this feel like YOUR approach? Not someone else's — yours. What would you adjust?"

Step 5: Refine

Incorporate their feedback. Allow a maximum of two refinement rounds. If after two rounds they are still unsure, note what remains unresolved and suggest they revisit it after completing later elements (Creation or Conversation often clarify the Method).

Step 6: Save the file

Write the final Method to world-code/method.md in exactly this format:

# One Method

## Methodology Name
[Named methodology]

## Core Principle
[The one idea that ties everything together]

## Phases

### Phase 1: [Name]
[Description — what happens, what changes, what they do]

### Phase 2: [Name]
[Description]

### Phase 3: [Name]
[Description]

[Add more phases as needed, typically 3-5]

## Why It Works Differently
[What makes this approach succeed where conventional methods fail]

Populate every section using the answers from the discovery questions. Do not leave placeholders.

Step 7: Transition

After saving, tell the user:

"Your Method is saved to world-code/method.md. Next up is your Creation — the signature content and offers that bring your Method to life. Want to continue to Creation now, or take a break and come back later?"
  • If they want to continue, invoke /world-creation.
  • 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

  • One question at a time. Never batch questions. Wait for each answer.
  • Build on their words. Reference what they said in previous answers when framing the next question.
  • Reference their Climax. Questions 1 and 2 must incorporate their specific Transformation Promise so the Method stays connected to the transformation they deliver.
  • Help them find what's authentically THEIRS. If their phases sound like a generic framework they borrowed, push them to describe what THEY actually do differently. Their Method already exists in how they think — the goal is to name it, not invent it.
  • Apply their Voice. Use the tone, rhythm, hard rules, and authenticity markers from world-code/voice.md when naming the methodology and describing its phases. The Method should sound like something THEY would teach, using their language and metaphors.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.82%
按下载量换算75

Claude

28.96%
按下载量换算62

Cursor

18.47%
按下载量换算40

Gemini CLI

9.34%
按下载量换算20

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills