Token导航 LogoToken导航

Agent Skill · 研究检索

assumption-mapping(假设映射)

assumption-mapping 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。

assumption-mapping 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;许可证为 MIT,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 54,843。

总安装 494周安装 21GitHub Stars 4下载 173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
MIT

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:assumption-mapping(假设映射)
来源仓库:https://github.com/abhsin/designskills
仓库路径:skills/assumption-mapping
安装命令:
npx skills add https://github.com/abhsin/designskills --skill assumption-mapping
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/abhsin/designskills --skill assumption-mapping

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。

assumption-mapping 提取项目中的隐藏假设,并按优先级排序验证顺序。适用于新项目启动或不确定性较高的工作场景。使用结构化问卷引导用户列出“必须为真”的前提条件。输出假设地图与测试建议,降低 build-first 风险。特别适合创意阶段的产品或功能探索。

assumption-mapping 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/assumption-mapping

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/abhsin/designskills --skill assumption-mapping;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

assumption-mapping 怎么安装?

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

assumption-mapping 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。

assumption-mapping 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。

assumption-mapping 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

assumption-mapping 用的人多吗?

公开数据是累计安装 494 次,近一周安装 21 次,下载 173 次,GitHub 4 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。

assumption-mapping 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 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

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
assumption-mapping

假设映射 · 本页

4944只读MIT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

Assumption Mapping

Surface hidden assumptions and prioritize which ones to validate before building.

When to Trigger

  • User is starting something new
  • User expresses uncertainty ("I think...", "probably...", "should work...")
  • User is about to invest significant effort
  • User mentions building without mentioning validation
  • User asks "what should I test first?"

Quick Start

Ask the user:

  1. "What are you building and for whom?"
  2. "What needs to be true for this to succeed?"

Then run the assumption extraction workflow below.

Core Workflow

Assumption Mapping Progress:
- [ ] Step 1: Extract assumptions from conversation
- [ ] Step 2: Categorize by type
- [ ] Step 3: Score risk and uncertainty
- [ ] Step 4: Prioritize for validation
- [ ] Step 5: Suggest validation methods

Step 1: Extract Assumptions

Listen for assumption signals in what the user says:

Signal phraseHidden assumption
"Users want..."Desirability assumption
"We can build..."Feasibility assumption
"People will pay..."Viability assumption
"It's easy to..."Complexity assumption
"Everyone knows..."Knowledge assumption
"They'll figure out..."Usability assumption

Extract 5-10 assumptions. Frame each as a testable statement:

Bad: "Users like simple things" Good: "Users will complete onboarding in under 2 minutes without help"

Step 2: Categorize Assumptions

Assign each assumption to one category:

CategoryQuestion it answers
DesirabilityDo people want this?
FeasibilityCan we build this?
ViabilityCan this sustain itself?
UsabilityCan people use this?
EthicalShould we build this?

Step 3: Score Each Assumption

Rate each assumption on two dimensions (1-5 scale):

Impact: If wrong, how badly does it hurt the project?

  • 1 = Minor inconvenience
  • 5 = Project fails completely

Uncertainty: How confident are we this is true?

  • 1 = We have strong evidence
  • 5 = Pure guess

Step 4: Prioritize

Create a 2x2 priority matrix:

                    HIGH IMPACT
                         │
     ┌───────────────────┼───────────────────┐
     │                   │                   │
     │   VALIDATE LATER  │  VALIDATE FIRST   │
     │   (Low risk)      │  (Critical)       │
     │                   │                   │
LOW  ├───────────────────┼───────────────────┤ HIGH
UNCERTAINTY              │              UNCERTAINTY
     │                   │                   │
     │   SKIP            │  MONITOR          │
     │   (Safe)          │  (Watch for       │
     │                   │   signals)        │
     │                   │                   │
     └───────────────────┼───────────────────┘
                         │
                    LOW IMPACT

Top-right quadrant = validate before building

Step 5: Suggest Validation Methods

For each critical assumption, suggest a lightweight validation:

Assumption typeFast validation (hours)Deeper validation (days)
Desirability5 user interviewsLanding page test
FeasibilityTechnical spikePrototype
ViabilityCompetitor pricing researchWillingness-to-pay interviews
Usability3-person hallway testUsability study

See references/validation-methods.md for detailed methods.

Output Template

Automatically save the output to design/03-assumption-mapping.md using the Write tool while presenting findings in this format:

## Assumption Map for [Project Name]

### Critical Assumptions (Validate First)
| # | Assumption | Type | Impact | Uncertainty | Suggested Test |
|---|------------|------|--------|-------------|----------------|
| 1 | [statement] | [type] | [1-5] | [1-5] | [method] |

### Secondary Assumptions (Validate Later)
[Same table format]

### Safe Assumptions (Monitor)
[Bulleted list]

### Recommended Next Steps
1. [First validation to run]
2. [Second validation to run]

Adaptive Behavior

If user is new to assumption mapping:

  • Explain briefly why we do this (1 sentence)
  • Guide them through extraction with examples
  • Keep the output simple

If user is familiar:

  • Skip explanations
  • Jump to extraction
  • Offer the full matrix output

Gauge familiarity by asking: "Have you mapped assumptions before, or should I walk you through it?"

Handoff

Suggest next steps:

"Use this map to prioritize validation tests before full development. Want to proceed with /solution-scoping or test critical assumptions first?"

Note: File is automatically saved to design/03-assumption-mapping.md for context preservation.

Integration Points

This skill works well before:

  • problem-framing — if problem isn't clear yet
  • validation — to test the critical assumptions identified here
  • ideation — to generate solutions once assumptions are validated

References

平台分布

Claude Code

30.06%
按下载量换算52

Gemini CLI

21.5%
按下载量换算37

Antigravity

19.54%
按下载量换算34

Codex

11.18%
按下载量换算19

OpenCode

8.28%
按下载量换算14

windsurf

3.46%
按下载量换算6

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。

继续浏览同类 Skills