OpenAI Prompt Optimization
Independent PiSkill directory guide. The original prompt remains hosted by OpenAI Cookbook.
What does this prompt do?
Uses test cases and explicit success criteria to revise a prompt, compare variants, and retain improvements that are supported by evaluation evidence.
Primary use case
Optimize a reusable content or marketing prompt.
Expected output
An improved prompt and evidence from comparison cases.
Inputs or variables
- current prompt
- examples
- success criteria
Related prompts
Autofix GitHub Actions with Codex
Demonstrates a Codex workflow that reads failed GitHub Actions evidence, identifies the responsible change or configuration, proposes a focused repair, and validates it.
Codex Prompting Guide
Provides a source-linked recipe for structuring coding tasks, context, constraints, tool use, iteration, and verification when working with Codex-oriented models.
Deep Research API Workflow
Shows how to frame a research question, provide source access, run a deep-research workflow, and return a cited synthesis with transparent limitations.
Evaluate LLM SQL Generation
Builds an evaluation workflow for generated SQL using representative cases, execution-aware checks, correctness criteria, and reproducible comparison rather than subjective inspection alone.
Gemini Product Marketing Campaign
Uses Gemini to analyze product imagery and supplied product facts, then produce structured campaign positioning, feature language, headings, and taglines for review.
Iterative Repair Loops with Codex
Shows how to structure an iterative coding loop that observes failures, changes a bounded implementation, reruns checks, and stops on success or a defined limit.