deep-interview

# Deep Interview

A structured interview process for gathering requirements and making design decisions on complex features.

## When to Use This Skill

- Complex features with multiple valid approaches
- Features affecting multiple layers (backend, frontend, data model)
- When prior investigation exists that needs stakeholder validation
- When "quick win" scope needs definition

## Input

`$ARGUMENTS` can be:

| Format              | Example                            | Description                    |
| ------------------- | ---------------------------------- | ------------------------------ |
| Issue number        | `#531` or `531`                    | GitHub issue to research first |
| PRD path            | `docs/feature-spec.md`             | Existing PRD to validate       |
| Feature description | `"user authentication flow"`       | Free-form description          |
| Nothing             | (empty)                            | Ask what we're planning        |

---

## Interview Process

### Phase 1: Context Gathering (Before Questions)

**Do this silently before asking any questions:**

1. **If issue number provided** (strip `#` prefix if present):

   ```bash
   # User may pass "#531" or "531" - strip the # if present
   gh issue view 531 --comments
   ```

2. **Search for related documentation** using Glob and Grep tools:

   ```
   # Use Glob to find markdown files
   Glob: **/*.md

   # Use Grep to search for keywords in markdown files
   Grep: pattern="<keywords>" glob="**/*.md"
   ```

3. **Explore current implementation:**
   - Use Task tool with `subagent_type: Explore` to find relevant code
   - Identify existing patterns that could be reused
   - Note gaps between documented plans and current state

4. **Summarize findings** to the user before starting questions:
   > "I've reviewed [issue/PRD/code]. Here's what I found:
   >
   > - Current state: [summary]
   > - Planned state: [from docs]
   > - Key gaps: [what's missing]
   >
   > Let me ask some q