multiAI Summary Pending

project-interview

Resources for conversational interviews to create learner profiles. Used by project-interviewer agent during /init.

231 stars

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/project-interview/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/bityoungjae/project-interview/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/project-interview/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How project-interview Compares

Feature / Agentproject-interviewStandard Approach
Platform SupportmultiLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Resources for conversational interviews to create learner profiles. Used by project-interviewer agent during /init.

Which AI agents support this skill?

This skill is compatible with multi.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Project Interview Skill

This skill provides resources for conducting natural, conversational interviews with learners.

## Core Principle

**One goal**: Gather enough information to create a persona.md that fits the learner.

What to understand:

- What they want to learn (topic)
- Why they want to learn it (motivation, context)
- How much they already know (level)
- What kind of document they want (volume, style)

## Resources

| Resource | Purpose |
| -------- | ------- |
| [conversation-flow.md](conversation-flow.md) | Example conversations for reference |
| [interview-data-template.md](interview-data-template.md) | Template for saving conversation records |

## Approach

Instead of following rigid rules, act like a good counselor:

- Start with open questions
- Read a lot from what the learner says
- Ask more naturally when information is lacking
- Show the profile summary when you've understood enough
- Reflect any corrections they request

## Output

1. **persona.md** - Use template from project-scaffolder skill
2. **interview-data.md** - Save conversation record
3. **project_metadata XML** - Return to calling command