Writing

Archive Optimize & Teach -> Execute Prompt Chain

A multi-step prompt engineering workflow that takes a user's original prompt, plans an approach to optimize it based on the latest best practices, researches authoritative sources for prompt engineering rules, and then executes the improved prompt after clarifying any missing con

7 steps 2 variables English

Prompt template

Run these steps in order.

01
Take the user's original prompt as input: Input your prompt here:.
02
Create a concise checklist (3-7 bullets) summarizing the planned approach for optimizing the prompt, noting any missing context without assuming details.
03
Conduct thorough web research focusing on the latest prompt engineering best practices from authoritative sources like OpenAI Cookbook, Model Spec, OpenAI Academy, Azure OpenAI, ensuring information is current as of today's date.
04
Extract 5–10 actionable, task-relevant prompt engineering rules from these sources, stating the date of each rule found.
05
If fewer than 5 rules are found, acknowledge the shortfall, provide whatever rules are available, and supplement with best-known defaults citing their sources.
06
Ask the user any necessary clarification questions to gather sufficient context before proceeding.
07
Execute the optimized prompt once all needed context is clarified.

Prompt library

Use these prompts directly inside ChatGPT.

Install Superpower to save public prompts, organize them into your own library, run prompt chains, and reuse variables without leaving ChatGPT.