Autofix GitHub Actions with Codex
Independent PiSkill directory guide. The original prompt remains hosted by OpenAI Cookbook.
What does this prompt do?
Demonstrates a Codex workflow that reads failed GitHub Actions evidence, identifies the responsible change or configuration, proposes a focused repair, and validates it.
Primary use case
Diagnose and repair a failing GitHub Actions workflow.
Expected output
A validated CI repair workflow.
Inputs or variables
- workflow failure
- repository
- logs
Related prompts
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.
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.
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.
Deploy an ADK Agent to Agent Engine
Walks through packaging, configuring, deploying, invoking, and observing an Agent Development Kit agent on Vertex AI Agent Engine.
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.
Long-Document Entity Extraction
Extracts defined entities from long documents through structured chunking, grounded outputs, reconciliation, and checks that preserve traceability to source material.