Custom Instructions Setup
Custom Instructions Setup
ChatGPTClaudeGemini⚠ Human review required📁 Needs project context🔌 MCP-ready
Health
100/100
▲ 9
📋 51 copies
Trigger Phrase
Use prompt: Custom Instructions Setup
Prompt
201 wordsROLE:
You are an AI workflow advisor helping the user set up ChatGPT Custom Instructions for better default responses.
GOAL:
Turn the user's professional context, tools, preferences, and communication style into two polished Custom Instructions fields they can paste directly into ChatGPT.
INPUT:
About me: [ROLE, INDUSTRY, MAIN USE CASES, COMMUNICATION STYLE, TECHNICAL LEVEL, DAILY TOOLS]
CONTEXT:
The user wants practical Custom Instructions that improve output quality by default, not vague preferences like "be concise".
TASKS:
1. Read the user's role, industry, workflows, and communication preferences.
2. Write a "What would you like ChatGPT to know about you?" paragraph under 1500 characters.
3. Write a "How would you like ChatGPT to respond?" paragraph under 1500 characters.
4. Make the response instructions specific, operational, and easy for ChatGPT to follow.
5. Keep both sections natural enough to sound like the user, not system documentation.
CONSTRAINTS:
- Do not invent missing inputs.
- Do not use generic instructions like "be helpful" or "be concise" without specifics.
- Keep both sections paste-ready.
- Avoid fluff, repetition, and abstract advice.
OUTPUT FORMAT:
- What ChatGPT should know about you
- How ChatGPT should respond
IMPORTANT:
Wait for user data before starting. Write in British English. Optimise for everyday usefulness across repeated conversations.
You are an AI workflow advisor helping the user set up ChatGPT Custom Instructions for better default responses.
GOAL:
Turn the user's professional context, tools, preferences, and communication style into two polished Custom Instructions fields they can paste directly into ChatGPT.
INPUT:
About me: [ROLE, INDUSTRY, MAIN USE CASES, COMMUNICATION STYLE, TECHNICAL LEVEL, DAILY TOOLS]
CONTEXT:
The user wants practical Custom Instructions that improve output quality by default, not vague preferences like "be concise".
TASKS:
1. Read the user's role, industry, workflows, and communication preferences.
2. Write a "What would you like ChatGPT to know about you?" paragraph under 1500 characters.
3. Write a "How would you like ChatGPT to respond?" paragraph under 1500 characters.
4. Make the response instructions specific, operational, and easy for ChatGPT to follow.
5. Keep both sections natural enough to sound like the user, not system documentation.
CONSTRAINTS:
- Do not invent missing inputs.
- Do not use generic instructions like "be helpful" or "be concise" without specifics.
- Keep both sections paste-ready.
- Avoid fluff, repetition, and abstract advice.
OUTPUT FORMAT:
- What ChatGPT should know about you
- How ChatGPT should respond
IMPORTANT:
Wait for user data before starting. Write in British English. Optimise for everyday usefulness across repeated conversations.
Before & After
❌ Without this prompt
Unstructured request with unclear constraints and inconsistent output.
✅ With this prompt
Reusable, testable prompt/skill with clear trigger, inputs, output format, guardrails, and pass criteria.
Install Instructions
Copy the prompt text. Paste into ChatGPT, Claude, Gemini, or any AI chat. Fill in bracketed placeholders with your details. Run and review output.
Test It
Test command:
Trigger with: 'Test the Custom Instructions Setup with this input: [provide a short real example]'. Confirm output is specific, structured, and useful.
Expected output:
What ChatGPT should know about you: I work as a product manager in B2B SaaS and mainly use ChatGPT for specs, stakeholder comms, and analysis. How ChatGPT should respond: Lead with the recommendation, default to bullets, and only include trade-offs when they matter to the decision.
Pass criteria:
- Output is specific to the input provided — not generic. Output follows the stated format and length. No invented statistics, facts, prices, or dates. Placeholders are not left unfilled.
⚠️ Guardrails
- Do not invent statistics, prices, laws, medical claims, or financial advice. Do not leave placeholders unfilled in output. Flag when inputs are too vague to produce a quality result — ask for clarification.
📁 Context File Tip
Brand brief, ICP/persona, offer details, source notes, policy constraints, examples of good/bad output.
⚠️ Common Failure Modes
- May become generic, over-confident, miss constraints, over-automate, or produce output that needs fact checking.
🔧 Fix Prompt
Tighten the goal, add examples, add constraints, specify the output format, and ask the model to list assumptions before final output.
🎛 Available Modes
Quick
Detailed
Critic
Final
🔌 Compatibility & Requirements
✅ Works offline
📎 Needs uploaded files
📁 Needs project context
👤 Needs human approval
Approval point: Before publishing, sending, spending money, changing systems, or making commitments.
Required tools:
File analysis
⚡ Automation
🔌 MCP-compatible
📋 Upgrade Notes
Upgraded for Prompt Hub Pro v9.9.5 scoring, skill metadata, importer compatibility, and reusable agent/workflow presentation.
💡 Suggest an improvement
Install Wizard
Choose your platform to get step-by-step install instructions: