MethodAI Setup & ProductivityAI setupIntermediate

Build a custom GPT, Gem or Claude Skill

A custom assistant spec: purpose, instructions, knowledge files, conversation starters and test cases.

This is a practical, copy-paste process for a task repeats often enough to deserve its own assistant.. Use it when you want a clear structure, then add your own details and the linked evidence.

Published by Deepstory Research. Reviewed Sep 2026.

How to use this method

1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.

The prompt

Paste it as-is. The AI will ask for anything still in [BRACKETS].

Download .md

# Build a custom GPT, Gem or Claude Skill
Method by Deepstory Research: deepstoryresearch.com/method/build-custom-gpt-or-skill

You are an AI product builder. Follow the method below step by step. Goal: A custom assistant spec: purpose, instructions, knowledge files, conversation starters and test cases.

## My inputs
- Task the assistant does: [TASK_THE_ASSISTANT_DOES]  (example: turn meeting notes into proposals)
- Users: [USERS]  (example: my sales team)
- Platform: [PLATFORM]  (example: ChatGPT GPT, Gemini Gem, Claude Skill)
- Knowledge files: [KNOWLEDGE_FILES]  (example: templates, pricing)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. Define scope and out-of-scope.
2. Write the instruction set (role, process, output format, rules).
3. List knowledge files and how to use them.
4. Write conversation starters.
5. Write 5 test cases with expected behaviour.
6. Give platform-specific setup steps.

## Deliver the output in this structure
- Scope
- Instructions
- Knowledge plan
- Starters
- Test cases
- Setup steps

## Quality rules
- Instructions must include what to do when inputs are missing.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

What you need to give the AI

Input	Placeholder	Example
Task the assistant does	[TASK_THE_ASSISTANT_DOES]	turn meeting notes into proposals
Users	[USERS]	my sales team
Platform	[PLATFORM]	ChatGPT GPT, Gemini Gem, Claude Skill
Knowledge files	[KNOWLEDGE_FILES]	templates, pricing

Use it when

A task repeats often enough to deserve its own assistant.

What you get

Scope
Instructions
Knowledge plan
Starters
Test cases
Setup steps

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

1
Define scope and out-of-scope.
2
Write the instruction set (role, process, output format, rules).
3
List knowledge files and how to use them.
4
Write conversation starters.
5
Write 5 test cases with expected behaviour.
6
Give platform-specific setup steps.

Quality checks built into the prompt

• Instructions must include what to do when inputs are missing.
• Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence for this method

This method runs on your own material: your files, brief or code. If your task needs market or economic numbers, attach a sourced context file from the evidence library alongside the prompt.

Browse evidence

Run next

Methods that chain well after this one.

AI Setup & ProductivityImprove any promptA rewritten prompt with role, context, task, format and constraints, plus why it is better.AI Setup & ProductivitySet up your AI workspace (projects, instructions, memory)A configured AI workspace: project structure, custom instructions, reference files and working rules.AI Setup & ProductivityWrite an instruction file for AI agents (CLAUDE.md / AGENTS.md)A project instruction file telling coding or research agents what the project is, how to work and what not to do.AI Setup & ProductivityBuild an AI context file for any topicA reusable markdown context file with facts, definitions, sources and rules the AI must follow.

Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment decisions need a qualified professional.