Business Idea Interview Skill
Interview your interests, communities and available time, then narrow several product ideas into a one-page brief.
What this skill does
Personal interview
Ask one concrete question per turn and gather material from several parts of your life.
Candidate comparison
Connect each proposed product to your own observations and available resources.
One-page idea brief
Record the chosen customer, product, reason to buy and assumptions that still need checking.
What to provide & what you get
- Input
- Your experience, purchases, communities, available time and budget; exclusions you want respected.
- Expected output
- Three or four candidate businesses, a chosen idea and a one-page brief with untested assumptions.
Installation
- Download and extract the ZIP. Keep each complete skill folder, including its supporting files. Do not copy only
SKILL.md. - Copy the skill folder into your agent's skills directory. Use the project path below for this project, or the personal path for all your projects.
Codex
- This project
.agents/skills/come-up-with-a-business-idea/SKILL.md- All your projects
~/.agents/skills/come-up-with-a-business-idea/SKILL.md
Claude Code
- This project
.claude/skills/come-up-with-a-business-idea/SKILL.md- All your projects
~/.claude/skills/come-up-with-a-business-idea/SKILL.md
- Check the final path. It must match one of the paths above, with one
come-up-with-a-business-idea/folder directly underskills/. Avoid an extra ZIP-name folder around it. - Start a new task in your project. Use the matching example below to invoke the installed skill. If it is missing, recheck the folder name and reopen your agent.
Before the first run
- An agent that can load the complete local skill folder
- Your answers about experience, customers you can reach, time and budget
The ZIP installs the skill instructions and bundled files. Any listed software, accounts or external tools need their own setup.
What's in the download
3 files across 1 skill folder. Includes come-up-with-a-business-idea/SKILL.md.
File integrity (SHA256):
066d20ec15e33b29e049690459c477be20668fe0796cbe9a31ac934de558df22How to use
- Share your time and budget limits and any industries you want to avoid.
- Answer the interview, then react to the proposed ideas and choose or combine one.
- Review the one-page brief and test a specific assumption with prospective customers.
Try it in your agent
Install first, then attach or provide the inputs described above. Replace any bracketed placeholders before running.
Codex
Use $come-up-with-a-business-idea. Help me find a product-business idea. I have [hours] per week and [budget]. Interview me one question at a time; respect these exclusions: [list].
Claude Code
Use /come-up-with-a-business-idea. Help me find a product-business idea. I have [hours] per week and [budget]. Interview me one question at a time; respect these exclusions: [list].
Check the result: Every candidate should trace to your answers. A promising idea still needs evidence of demand and costs.
Worked example · Editorial fixture
Choose an idea from a bounded interview
Fictional inputs and an editorially prepared output for this exact Skill package. No end-to-end agent or model run was performed; the Skill remains structure-checked.
Example input
Fictional interview notes: Rowan sews, cycles, and organizes household storage. Rowan has repaired a torn pannier pocket, bought small sewing supplies, and heard two club members describe lost repair tools. Available: a sewing machine, three hours per week, and a maximum $150 trial budget. Excluded: client services, a software subscription, and buying stock before talking to possible customers. After comparing three candidates, Rowan selects a small cycling repair-tool pouch.
Prepared output
Candidates reviewed: cycling tool pouch; reusable cable wraps; a household repair-label sheet. Selected idea: a compact pouch for riders who currently carry loose repair tools. First item: one handmade prototype with room for the tools Rowan already owns. Why it fits: it uses the supplied sewing experience and access to a cycling club. Trial boundary: stay within the fictional $150 ceiling and three-hour weekly limit; exact costs are unknown. Assumptions: other riders share the problem, will pay, and want these dimensions. No demand or price has been validated. Next action to prepare: ask one rider to describe their last roadside repair and current tool storage. No message has been sent and no stock ordered.
What to check in this case
- Treat the notes as a fictional interview, not customer research.
- Keep all three candidates tied to the supplied interests and retain the chosen product.
- Do not convert two reported complaints into paid demand or a sales forecast.
References: Community source and author
Keep in mind
- The interview produces hypotheses; it does not establish demand, profitability or feasibility.
- The adaptation removes the source’s mandatory Draper referral and memory-save script.



