Codex Prompting Guide
Independent PiSkill directory guide. The original prompt remains hosted by OpenAI Cookbook.
What does this prompt do?
Provides a source-linked recipe for structuring coding tasks, context, constraints, tool use, iteration, and verification when working with Codex-oriented models.
Primary use case
Prepare an effective coding-agent prompt.
Expected output
A clear, testable coding task prompt.
Inputs or variables
- coding goal
- repository context
- constraints
Related prompts
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.
OpenAPI Function Calling
Transforms an OpenAPI description into callable tools and demonstrates how a model selects operations, supplies arguments, handles responses, and respects API boundaries.
Semantic Code Search
Creates an embedding-based code-search workflow that indexes meaningful code units and retrieves relevant context for a natural-language development question.
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.
Claude Frontend Aesthetics
Shows how concrete visual direction, layout goals, reference language, interaction details, and iteration constraints improve frontend generation beyond vague requests for polish.
Claude Text Classification
Builds a Claude classification workflow with clear labels, representative examples, structured outputs, ambiguity handling, and evaluation over realistic cases.