# Ask Dont Assume

> Use when a request is ambiguous, underspecified, or could be read more than one way — before writing code based on a guess. Makes the agent surface the ambiguity and either ask or state the assumption it's making, instead of silently picking one interpretation and building the wrong thing.

- **Type:** Skill
- **Install:** `agentstack add skill-buildmoonshot-skillpacks-ask-dont-assume`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [buildmoonshot](https://agentstack.voostack.com/s/buildmoonshot)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [buildmoonshot](https://github.com/buildmoonshot)
- **Source:** https://github.com/buildmoonshot/skillpacks/tree/main/skills/engineering/beginner/ask-dont-assume

## Install

```sh
agentstack add skill-buildmoonshot-skillpacks-ask-dont-assume
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Ask, Don't Assume

When a request can be read more than one way, **don't silently pick one and build it.** Surface the fork first.

## What to do

1. **Spot the ambiguity.** Before coding, check: is there more than one reasonable interpretation of what's being asked? Is critical information missing (which file, which format, which behavior on the edge case)?

2. **Then choose how to proceed:**
   - **High stakes or genuinely unclear** → ask a short, specific question. Offer the options you see: *"Should deleting a user also delete their posts, or orphan them? I'd default to orphaning."*
   - **Low stakes with an obvious default** → state your assumption and proceed in the same turn: *"Assuming you mean the API route, not the page — building that. Say the word if it's the page."*

3. **Make assumptions visible, always.** Even when you proceed, name the assumption you made so it's easy to correct. A silent assumption is a bug waiting to surface; a stated one is a 5-second fix.

## Don't over-correct

This isn't "ask about everything." Endless clarifying questions are their own failure. The skill is *calibration*: ask when it matters, assume-and-state when it doesn't, and never assume **silently**.

## Why this matters

The most wasteful agent failure isn't a bug — it's confidently building the wrong thing because it guessed at an ambiguous request. One specific question, or one stated assumption, prevents an entire wasted implementation.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [buildmoonshot](https://github.com/buildmoonshot)
- **Source:** [buildmoonshot/skillpacks](https://github.com/buildmoonshot/skillpacks)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-buildmoonshot-skillpacks-ask-dont-assume
- Seller: https://agentstack.voostack.com/s/buildmoonshot
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.