- Home
- Skills
- Multiversx
- Mx Ai Skills
- Multiversx Clarification Expert
multiversx-clarification-expert_skill
10
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill multiversx/mx-ai-skills --skill multiversx-clarification-expert- SKILL.md4.7 KB
Overview
This skill identifies ambiguous or incomplete requirements for MultiversX development and asks targeted, actionable clarifying questions to unblock work. It prevents wasted implementation or audit effort by surfacing missing constraints, conflicting choices, and security trade-offs. Use it whenever requests lack specifics or multiple valid approaches exist.
How this skill works
The skill inspects user requests, feature descriptions, and bug reports to detect vagueness, missing technical constraints, or conflicting requirements. It batches related clarifications, proposes sensible defaults, and explains trade-offs tied to MultiversX primitives (ESDT types, mapper choices, upgradeability, etc.). It then returns a concise list of concrete questions and a recommended path forward.
When to use it
- Requests like “Make it secure” or “Add a token” without details
- Feature specs missing storage, token type, or access-control choices
- Bug reports that lack reproduction steps or expected behavior
- Security review requests without a threat model or invariants
- When multiple implementation approaches exist and a decision is required
Best practices
- Always offer concrete options rather than open-ended questions
- Group related questions by topic to reduce back-and-forth
- Provide a recommended default and justify it briefly
- Explain trade-offs for choices that affect gas, upgradeability, or attack surface
- If user is unresponsive, list assumed defaults and state risks clearly
Example use cases
- New token feature: ask whether token is Fungible ESDT, SFT, NFT, or Meta-ESDT and propose a default
- Staking module: batch token, min-stake, reward model, and access-control questions
- Storage design: clarify whether per-user, enumerable, ordered, or unique storage is required
- Security audit request: request threat model, invariants, expected behaviors, and high-value targets
- Bug triage: request reproduction steps, current vs expected behavior, and environment (Devnet/Mainnet)
FAQ
I propose sensible defaults and explain the trade-offs. I’ll proceed with the recommended option if you approve or give explicit alternate choices.
How many questions will you ask at once?
I batch related questions by topic to minimize rounds; typically 4–10 concise, concrete items depending on scope.