A practical guide to creating structured, reusable AI prompts that work across tools and contexts.
A superprompt is a structured cognitive interface between human intent and AI reasoning. It translates what you want into how the model should think, then specifies what it should produce. It’s not about length—it’s about architecture.
Think of it as a thinking contract: you define the goal, constraints, reasoning steps, and output format. The model follows that structure to deliver predictable, reusable results.
Most prompts are instructions. Superprompts are systems. They create predictability by controlling three variables:
When you control these, you get consistent results you can reuse, refine, and share.
The SuperPrompt Framework uses CRAFTER—a 7-component structure for building reliable prompts:
| Component | Purpose | Example |
|---|---|---|
| Context | Environment & constraints | “You’re analyzing Q3 sales data for an e-commerce company (50K transactions)” |
| Role | Expertise & perspective | “You are a Data Analyst specializing in e-commerce analytics” |
| Action | Step-by-step tasks | “1. Identify trends 2. Analyze anomalies 3. Generate recommendations” |
| Format | Output structure | “Markdown table: Theme | Evidence | Recommendation” |
| Target & Tone | WHO + HOW to communicate | “Marketing managers (action-oriented) → Direct, scannable, lead with takeaways” |
| Examples | Input→output demonstrations | “Input: ‘reduce costs’ → Output: ‘Cost optimization: vendor consolidation (15% savings)’” |
| Refining | How to iterate | “If ‘more detail’ → expand Analysis with data sources and timeline” |
Key insight: T = Target & Tone (WHO uses this + HOW to communicate) — the most important component for getting the right output style.
Start by exploring complete, copy-ready superprompts in the /examples folder:
Use the canonical template from docs/template.md as your starting point. It includes all CRAFTER components with clear placeholders.
Replace the template placeholders with your specifics:
Paste your completed superprompt into your AI tool (Claude, ChatGPT, Gemini, etc.) and run it. Check the output: Does it match your intent?
If the output isn’t quite right, adjust the weak components and re-run. Use the evaluation rubric to identify which axis needs improvement.
For Content Creation:
For Strategic Thinking:
For Team Facilitation:
For Personal Development:
For Research:
Once you understand the basics, explore these resources:
Superprompts work for any task where you need structured thinking:
This is an open framework. Contributions are welcome!
How to contribute:
git checkout -b feat/your-prompt-name/examples or pattern to /docs/patterns.mdgit commit -m "feat: Add [description]"See the workflow guide for detailed instructions.
This framework is licensed under CC-BY 4.0 (Creative Commons Attribution 4.0 International).
What this means:
Required attribution format:
Framework: CoachSteff's CRAFTER (SuperPrompt Framework v0.1)
License: CC-BY 4.0 — Attribution: Steff Vanhaverbeke (coachsteff.live)
Steff Vanhaverbeke – AI Adoption Coach & Co-founder, The House of Coaching
I help professionals and teams build the uniquely human capabilities that matter most in an AI-driven world. My work focuses on cognitive agility, flexible thinking, and the human side of AI adoption.
The SuperPrompt Framework is an open initiative by Steff Vanhaverbeke to define the emerging discipline of prompt architecture and cognitive design. It’s a living system—use it, adapt it, and contribute back.