# Define Project Scope and Approve the Stack

Unclear requirements cause scope creep and premature technology choices. This skill converts requirements and research into prioritized scope, effort estimates, and an approved technology stack.

## Install

```bash
npx skillstore add cubha/scope
```

## Metadata

- Status: approved
- Slug: cubha-scope
- Skillstore revision: r2
- Version status: missing
- Tree hash: 3aea249c7b084e38b8c4008ea62d4bf678b7d93c117cd4f4f7ea41e17ec80f3e
- Author: cubha
- GitHub username: cubha
- License: MIT
- Repository: https://github.com/cubha/claude-workflow-plugins/tree/3172e1a00f7090579f36af20c046828489983c23/plugins/scope/skills/scope
- Ref: c43861a65bb95efcae259cd161c9d6f4dc7eec6f
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 69
- Public page: https://skillstore.pages.dev/skills/cubha-scope
- Manifest: https://skillstore.pages.dev/api/skills/cubha-scope/manifest

## Capabilities

- Loads a selected research document or finds RESEARCH files under docs/research.
- Asks only for missing details that affect scope or technology decisions.
- Breaks requirements into user-value features and assigns MoSCoW priorities.
- Estimates Must and Should features with relative T-shirt sizes.
- Compares relevant technology categories and requires user approval before finalizing choices.
- Creates a dated SCOPE document or returns the same content in the conversation.

## Use Cases

- Prioritize an MVP: Convert product requirements into Must, Should, Could, and Won't features with relative effort.
- Select a Practical Stack: Compare technology options against required features before committing development resources.
- Create an Engineering Handoff: Produce an approved scope document that can guide planning and project scaffolding.

## Prompt Templates

### Scope a Simple Project

```
Define the scope for [project]. The target user is [user], and the main problem is [problem].
```

### Prioritize an MVP

```
Scope an MVP for [project]. Separate features with MoSCoW priorities and estimate Must and Should items with T-shirt sizes.
```

### Use Existing Research

```
Scope [project] using [research file]. Compare only stack categories required by Must features, then ask for approval.
```

### Evaluate Constraints and Risks

```
Create a scope for [project] under [constraints]. Identify uncertain XL items, compare stack tradeoffs, record rejected options, and require approval.
```

## Limitations

- Does not generate application code, configuration, or project scaffolding.
- Provides relative effort estimates, not schedules or contractual delivery dates.
- Does not perform broad market or technology research.
- Produces weaker stack recommendations when no research evidence is available.

## Best Practices

- Provide the target user, core problem, deployment constraints, and excluded technologies.
- Keep Must features limited to the smallest set that delivers the core value.
- Review XL estimates and stack tradeoffs before approving the final document.

## Anti Patterns

- Do not treat every requested feature as a Must requirement.
- Do not accept a technology stack without reviewing its fit and tradeoffs.
- Do not use relative estimates as guaranteed delivery dates.

## Security Audit

- Audited at: 2026-07-23T13:02:54.086\+00:00
- Summary: All 31 external-command alerts are Markdown formatting or benign command documentation, not Ruby or shell backtick execution. The entropy alert reflects Korean and Unicode text, not obfuscation. Two medium semantic risks remain around unrestricted research paths and treating loaded research as trusted instructions.

## Stats

- Views: 0
- Downloads: 4
- Favorites: 1
- Popularity score: 0