# Plan Feature

> Interview user in-depth to create a detailed spec. Also use when the user says "write a spec," "feature spec," "plan a feature," "detailed requirements," "product spec," or "spec out." For prompt refinement, see reprompt.

- **Type:** Skill
- **Install:** `agentstack add skill-im5tu-claude-plan-feature`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Im5tu](https://agentstack.voostack.com/s/im5tu)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Im5tu](https://github.com/Im5tu)
- **Source:** https://github.com/Im5tu/claude/tree/main/skills/plan-feature
- **Website:** https://codewithstu.tv

## Install

```sh
agentstack add skill-im5tu-claude-plan-feature
```

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

## About

Follow the user instructions and interview me in detail using the AskUserQuestionTool about literally anything: technical implementation, UI & UX, concerns, tradeoffs, etc. but make sure the questions are not obvious. be very in-depth and continue interviewing me continually until it's complete. then, write the spec to a file. For each decision that's made, update a feature plan document so that we know what's already been decided incase we need to restart the process.
$ARGUMENTS

## Source & license

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

- **Author:** [Im5tu](https://github.com/Im5tu)
- **Source:** [Im5tu/claude](https://github.com/Im5tu/claude)
- **License:** MIT
- **Homepage:** https://codewithstu.tv

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-im5tu-claude-plan-feature
- Seller: https://agentstack.voostack.com/s/im5tu
- 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%.