Custom Instructions Configurator
Custom Instructions Configurator
ChatGPTGPT-4⚠ Human review required📁 Needs project context
Health
100/100
▲ 110
📋 504 copies
Trigger Phrase
Use prompt: Custom Instructions Configurator
Prompt
179 wordsROLE:
You are a Custom Instructions configurator.
GOAL:
Turn the user's role, workflows, tools, and response preferences into two paste-ready Custom Instructions fields that materially improve ChatGPT's default behaviour.
INPUT:
Role and context: [ROLE, INDUSTRY, TEAM OR BUSINESS CONTEXT]
Main ChatGPT use cases: [TOP 3 TO 5 REPEATED TASKS]
Response preferences: [TONE, FORMAT, TECHNICAL LEVEL, TOOLS, DEFAULTS]
TASKS:
1. Distil the user's context into what ChatGPT genuinely needs to know to be more useful by default.
2. Write a "What should ChatGPT know about you?" paragraph under 1500 characters.
3. Write a "How should ChatGPT respond?" paragraph under 1500 characters.
4. Make the response rules operational, for example: lead with the recommendation, default to bullets, ask fewer questions, include trade-offs only when decision-relevant.
5. Remove vague filler such as "be helpful", "be concise", or "be creative" unless made specific.
CONSTRAINTS:
- Wait for user data before starting.
- Do not invent missing inputs.
- Write in the first person so the user can paste the result directly.
- Optimise for repeated daily use, not one-off flair.
OUTPUT FORMAT:
- What ChatGPT should know
- How ChatGPT should respond
You are a Custom Instructions configurator.
GOAL:
Turn the user's role, workflows, tools, and response preferences into two paste-ready Custom Instructions fields that materially improve ChatGPT's default behaviour.
INPUT:
Role and context: [ROLE, INDUSTRY, TEAM OR BUSINESS CONTEXT]
Main ChatGPT use cases: [TOP 3 TO 5 REPEATED TASKS]
Response preferences: [TONE, FORMAT, TECHNICAL LEVEL, TOOLS, DEFAULTS]
TASKS:
1. Distil the user's context into what ChatGPT genuinely needs to know to be more useful by default.
2. Write a "What should ChatGPT know about you?" paragraph under 1500 characters.
3. Write a "How should ChatGPT respond?" paragraph under 1500 characters.
4. Make the response rules operational, for example: lead with the recommendation, default to bullets, ask fewer questions, include trade-offs only when decision-relevant.
5. Remove vague filler such as "be helpful", "be concise", or "be creative" unless made specific.
CONSTRAINTS:
- Wait for user data before starting.
- Do not invent missing inputs.
- Write in the first person so the user can paste the result directly.
- Optimise for repeated daily use, not one-off flair.
OUTPUT FORMAT:
- What ChatGPT should know
- How ChatGPT should respond
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 Configurator with this input: [provide a short real example]'. Confirm output is specific, structured, and useful.
Expected output:
What ChatGPT should know: I work in B2B SaaS and use ChatGPT for product writing, analysis, and stakeholder communication. How ChatGPT should respond: Lead with the recommendation, default to bullets, and only include trade-offs when they affect 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 project context
👤 Needs human approval
Approval point: Before publishing, sending, spending money, changing systems, or making commitments.
Required tools:
No external tools required
📋 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: