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

multiversx-clarification-expertmultiversx 澄清专家

Agent Skill

multiversx-clarification-expert 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

470

周安装

20

GitHub Stars

11

下载量

165
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:multiversx-clarification-expert(multiversx 澄清专家)
来源仓库:https://github.com/multiversx/mx-ai-skills
仓库路径:skills/multiversx-clarification-expert
安装命令:
npx skills add https://github.com/multiversx/mx-ai-skills --skill multiversx-clarification-expert
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/multiversx/mx-ai-skills --skill multiversx-clarification-expert

简介

用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 MultiversX 项目中澄清需求或代码意图。
  • 可帮助解析技术讨论、追踪决策过程或生成说明文档。
  • 安装命令:npx skills add https://github.com/multiversx/mx-ai-skills --skill multiversx-clarification-expert。
  • 使用前应确认是否访问私有仓库或包含商业机密的信息。

SKILL.md

Clarification Expert

Identify ambiguity in user requests and ask targeted questions to unblock MultiversX development or auditing tasks. This skill prevents wasted effort from incorrect assumptions.

When to Use

  • User request is vague (e.g., "Make it secure")
  • Missing technical constraints (e.g., "Add a token" without specifying standard)
  • Conflicting requirements that need resolution
  • Multiple valid implementation approaches exist
  • Security implications require explicit user decisions

Questioning Guidelines

1. Be Specific

Never ask open-ended questions. Always offer concrete choices.

Bad:

"How should the token work?"

Good:

"Should the token be: 1. A standard Fungible ESDT (simple transfers, 18 decimals) 2. A Semi-Fungible Token (SFT) with quantity per nonce 3. A Meta-ESDT with custom attributes If unsure, I recommend option 1 for simplicity."

2. Batch Related Questions

Group questions by topic to minimize back-and-forth.

Example:

Before implementing the staking module, I need to clarify: Token Configuration: 1. Which token can be staked? (specific token ID or any ESDT?) 2. Is there a minimum stake amount? Reward Mechanism: 3. Fixed APY or dynamic based on total staked? 4. Reward distribution: claim-based or auto-compound? Access Control: 5. Can anyone stake, or only whitelisted addresses?

3. Propose Sensible Defaults

Always offer a recommended option when the user may not have strong preferences.

Example:

"For the admin storage, I recommend using SingleValueMapper instead of MapMapper to save gas since you only need one admin. Shall I proceed with that approach?"

4. Explain Trade-offs

When choices have significant implications, explain the consequences.

Example:

"For storing user balances, there are two approaches: Option A: SingleValueMapper with address parameter - More gas efficient for individual lookups - Cannot iterate over all users Option B: MapMapper - Can iterate over all users (useful for airdrops) - Higher gas cost (4N+1 storage slots) Which user enumeration requirement do you have?"

Analysis Categories

1. Scope & Environment

QuestionWhy It Matters
Full audit or specific module?Depth vs breadth
New code or upgrade review?Upgrade reviews need storage migration focus
Mainnet, Devnet, or Sovereign Chain?Different security requirements
Integration with other contracts?Cross-contract interaction risks

2. Risk & Technical Profile

QuestionWhy It Matters
TVL expectations?High value = higher attacker incentive
User base: public or restricted?Public = larger attack surface
Upgradeable or immutable?Affects fix deployment strategy
Custom modules or unsafe blocks?Needs deeper review
External dependencies?Supply chain risk

MultiversX-Specific Clarifications

When user says... ask to clarify:

  • "add a token": Fungible ESDT, NFT, SFT, or Meta-ESDT?
  • "store user data": Per-user (SingleValueMapper + address key), enumerable (MapMapper/SetMapper), ordered (VecMapper/LinkedListMapper), or unique (UnorderedSetMapper)?
  • "admin only": Single owner, stored admin address, multi-sig, role-based, or time-locked?

Question Templates

For New Feature Requests

"To implement [FEATURE], I need to understand: 1. [CRITICAL_DECISION_1] 2. [CRITICAL_DECISION_2] My recommendation is [DEFAULT] because [REASON]. Should I proceed with this approach?"

For Bug Reports

"To fix this issue, I need to clarify: 1. Expected behavior: [WHAT_SHOULD_HAPPEN] 2. Current behavior: [WHAT_HAPPENS_NOW] 3. Reproduction steps: [HOW_TO_TRIGGER] Can you confirm these details?"

For Security Reviews

"Before auditing [CONTRACT], please confirm: 1. Threat model: Who are the trusted parties? 2. Invariants: What properties must always hold? 3. Known risks: Are there accepted trade-offs? This helps me focus on relevant attack vectors."

Anti-Patterns to Avoid

  • Don't assume: If something could go two ways, ask
  • Don't ask obvious questions: "Is security important?" - always yes
  • Don't delay indefinitely: If no response, state assumptions and proceed
  • Don't ask one question at a time: Batch related questions together
  • Don't use jargon without explanation: Clarify technical terms for non-experts

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

35.13%
按下载量换算58

Claude

30.16%
按下载量换算50

Cursor

18.19%
按下载量换算30

Gemini CLI

8.67%
按下载量换算14

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