Conduct deep adaptive interviews to extract and organize knowledge into structured files and folders. Use when user says "interview me about X", "deep interview", "extract my knowledge", "build knowledge base from interview", "ask me questions about X", or wants to systematically capture expertise on any topic through guided questioning.
Conduct adaptive interviews that progressively extract knowledge and build organized knowledge bases in real-time.
ASK -> LISTEN -> WRITE -> DEEPEN -> REPEAT
Each cycle: ask targeted questions, capture answers into files, identify gaps, go deeper. The knowledge base grows with every answer.
Parse the topic from user input. Determine output path:
--output <path> provided: use that path~/Documents/interviews/<topic>-<date>/Create the output directory and an _interview-index.md file:
# Interview: <Topic>
**Date:** <today>
**Status:** In Progress
**Depth:** <shallow|medium|deep>
## Themes Discovered
(updated as interview progresses)
## Files Created
(updated as files are written)
Use AskUserQuestion to understand the landscape. Ask 2-3 broad questions max per call.
First call - establish scope and the interviewee's relationship to the topic:
IMPORTANT: After EACH AskUserQuestion response, immediately write what was learned to a file before asking more questions. Never accumulate more than one round of answers without writing.
Based on answers, identify themes (3-7 major areas). For each theme:
<theme-slug>.md<theme-slug>/ and split into sub-filesQuestion strategy per depth:
| Depth | Questions per theme | Total rounds | Output size |
|---|---|---|---|
| shallow | 2-3 | 3-5 | 5-10 files |
| medium | 4-6 | 6-10 | 10-20 files |
| deep | 8-12 | 12-20 | 20-40 files |
Default depth: medium.
Vary question types to extract different knowledge layers:
Tip: Use the options field in AskUserQuestion to suggest concrete answers when possible - this makes it easier for the user and surfaces assumptions to validate.
File naming: kebab-case, descriptive. e.g., target-audience.md, pricing-strategy.md, session-1-agenda.md
File format:
# <Theme Title>
> Source: Deep Interview, <date>
## Key Points
- Point extracted from answer
- Another point
## Details
<Expanded content from follow-up questions>
## Open Questions
- Things that still need clarification
Folder creation trigger: When a theme has 3+ sub-themes, create a folder:
output/
├── _interview-index.md
├── overview.md
├── simple-theme.md
└── complex-theme/
├── _index.md
├── sub-topic-1.md
└── sub-topic-2.md
After every 3 rounds of questions, show the user a brief status:
**Interview Progress:**
- Themes covered: X/Y
- Files created: N
- Current focus: <theme>
- Estimated remaining: ~Z more rounds
When all themes are covered (or user signals done):
_interview-index.md with final table of contents_summary.md - a concise synthesis of everything learned_open-questions.mdmultiSelect: true for "which of these apply?" questions