Token导航 LogoToken导航TokenDH.com
前端设计需要联网github未标认证来源可访问许可证需确认审计未展示

clarify%3avague澄清%3 含糊不清

Agent Skill

clarify%3avague 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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

1,449

周安装

61

GitHub Stars

7

下载量

508
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:clarify%3avague(澄清%3 含糊不清)
来源仓库:https://github.com/team-attention/workshop-upstage
仓库路径:skills/clarify%3Avague
安装命令:
npx skills add https://github.com/team-attention/workshop-upstage --skill clarify:vague
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/team-attention/workshop-upstage --skill clarify:vague

简介

将含糊需求转化为精确可执行的规格说明书。

  • 采用假设选项方式呈现多种解释可能,引导用户确认方向。
  • 适用于功能请求、缺陷报告与任务描述不完整的场景。
  • 必须通过 AskUserQuestion 工具交互,不可直接输出疑问句。
  • clarify%3avague 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Vague: Requirement Clarification

Transform vague or ambiguous requirements into precise, actionable specifications through hypothesis-driven questioning. ALWAYS use the AskUserQuestion tool — never ask clarifying questions in plain text.

When to Use

  • Ambiguous feature requests ("add a login feature")
  • Incomplete bug reports ("the export is broken")
  • Underspecified tasks ("make the app faster")

For strategy/planning blind spot analysis, use the unknown skill. For content-vs-form reframing, use the metamedium skill.

Core Principle: Hypotheses as Options

Present plausible interpretations as options instead of asking open questions. Each option is a testable hypothesis about what the user actually means.

BAD:  "What kind of login do you want?"           ← open question, high cognitive load
GOOD: "OAuth / Email+Password / SSO / Magic link" ← pick one, lower load

Protocol

Phase 1: Capture and Diagnose

Record the original requirement verbatim. Identify ambiguities:

  • What is unclear or underspecified?
  • What assumptions would need to be made?
  • What decisions are left to interpretation?

Phase 2: Iterative Clarification

Use AskUserQuestion to resolve ambiguities. Batch up to 4 related questions per call. Each option is a hypothesis about what the user means.

Cap: 5-8 total questions. Stop when all critical ambiguities are resolved, OR user indicates "good enough", OR cap reached.

Example AskUserQuestion call:

questions:
  - question: "Which authentication method should the login use?"
    header: "Auth method"
    options:
      - label: "Email + Password"
        description: "Traditional signup with email verification"
      - label: "OAuth (Google/GitHub)"
        description: "Delegated auth, no password management needed"
      - label: "Magic link"
        description: "Passwordless email-based login"
    multiSelect: false
  - question: "What should happen after registration?"
    header: "Post-signup"
    options:
      - label: "Immediate access"
        description: "User can use the app right away"
      - label: "Email verification first"
        description: "Must confirm email before access"
    multiSelect: false

Phase 3: Before/After Summary

Present the transformation:

## Requirement Clarification Summary

### Before (Original)
"{original request verbatim}"

### After (Clarified)
**Goal**: [precise description]
**Scope**: [included and excluded]
**Constraints**: [limitations, preferences]
**Success Criteria**: [how to know when done]

**Decisions Made**:
| Question | Decision |
|----------|----------|
| [ambiguity 1] | [chosen option] |

Phase 4: Save Option

Ask whether to save the clarified requirement to a file. Default location: requirements/ or project-appropriate directory.

Ambiguity Categories

CategoryExample Hypotheses
ScopeAll users / Admins only / Specific roles
BehaviorFail silently / Show error / Auto-retry
InterfaceREST API / GraphQL / CLI
DataJSON / CSV / Both
Constraints<100ms / <1s / No requirement
PriorityMust-have / Nice-to-have / Future

Rules

  1. Hypotheses, not open questions: Every option is a plausible interpretation
  2. No assumptions: Ask, don't assume
  3. Preserve intent: Refine, don't redirect
  4. 5-8 questions max: Beyond this is fatigue
  5. Batch related questions: Up to 4 per AskUserQuestion call
  6. Track changes: Always show before/after

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

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

34.87%
按下载量换算177

Claude

27.76%
按下载量换算141

Cursor

18.32%
按下载量换算93

Gemini CLI

9.91%
按下载量换算50

安全审计

暂无安全审计结果可展示。

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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