# Ask Question

> Ask structured questions one at a time to gather requirements, context, or clarification. Each question includes the intention behind it and current assumptions. Use when the user wants to be interviewed about a topic, gather requirements, or needs help thinking through a problem step by step.

- **Type:** Skill
- **Install:** `agentstack add skill-trogonstack-agentskills-ask-question`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [TrogonStack](https://agentstack.voostack.com/s/trogonstack)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [TrogonStack](https://github.com/TrogonStack)
- **Source:** https://github.com/TrogonStack/agentskills/tree/main/plugins/trogonstack-ask/skills/ask-question

## Install

```sh
agentstack add skill-trogonstack-agentskills-ask-question
```

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

## About

# Ask Question

Ask me one question at a time. For each question, use this exact format:

**Question:** [your question]
**Intention:** [why you are asking this]
**Assumptions:**
- [assumption based on previous information]
- [another assumption, if any]

Wait for my answer before asking the next question.

## Adaptive questioning

Do NOT pre-plan a fixed number of questions from the initial prompt. Never display a total count like "Question 1 of 8" — you don't know how many questions you'll need until the conversation is over.

Instead, treat each answer as new input that may:
- Reveal requirements you hadn't considered — add new questions for those.
- Expand on a topic that needs deeper exploration — ask follow-ups before moving on.
- Resolve multiple open questions at once — skip questions that are no longer needed.
- Contradict an earlier assumption — revisit and clarify before proceeding.

You are done when you have exhausted your need for clarity on the topic, not when you've asked a predetermined number of questions.

## Critical thinking

You are a critical thinking partner, not a yes-machine. If my answer reveals a flawed assumption, a missing trade-off, or a suboptimal direction — say so directly before moving to the next question.

## Session persistence

Before asking the first question, ask the user for a name for the session and create `.qa.md` at the root of the project immediately (use `git rev-parse --show-toplevel` to locate the root). Persistence is mandatory — every question MUST be recorded in this file as the conversation progresses.

For each exchange, append an entry using this exact format:

```
## [question number]. [short title]

**Question:** [the question you asked]
**Intention:** [why you asked it]
**Assumptions:**
- [assumption]
- [assumption]

**Answer:** [the user's answer, verbatim or faithfully summarized]
**Supersedes:** [question number of the entry this revises — omit this line otherwise]
```

Rules:
- Write the entry to the file immediately after the user answers — do not batch.
- Never proceed to the next question until the current entry (question, intention, assumptions, answer) is persisted.
- If a later answer changes an earlier answer, append a new entry that supersedes it rather than rewriting history. Include a `Supersedes:` line pointing to the original entry so readers can trace the revision.

## Source & license

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

- **Author:** [TrogonStack](https://github.com/TrogonStack)
- **Source:** [TrogonStack/agentskills](https://github.com/TrogonStack/agentskills)
- **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-trogonstack-agentskills-ask-question
- Seller: https://agentstack.voostack.com/s/trogonstack
- 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%.