codex
Delegates coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and automated issue fixing within Git repositories.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
522 skills found
Delegates coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and automated issue fixing within Git repositories.
A unified document processing gateway for PDF parsing, text extraction, conversion, and document manipulation across multiple local and cloud providers.
A guide for building high-quality MCP (Model Context Protocol) servers in Python or TypeScript to integrate external APIs and services into LLM workflows.
CLI tool that automatically renames academic PDF files using AI-extracted metadata, supporting multiple providers like Claude, OpenAI, Gemini, and Ollama.
Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.
Execute implementation plans in separate sessions with review checkpoints, ensuring task-by-task verification and robust code quality.
Generate and process 16-bit pixel art office assets for the Claude Office Visualizer using Nano Banana MCP and multi-pass ImageMagick workflows.
Automated guidance for implementing property-based testing (PBT) in software and smart contracts to improve test coverage and edge case detection.
A comprehensive framework for creating, structuring, and managing reusable AI Agent Skills to standardize instruction-driven workflows.
Maintain and synchronize Unified Impact Diagrams using the Diagram Driven Development (DDD) methodology to connect technical architecture with user value.
Expert advisor for implementing Anthropic's structured outputs. Choose between JSON mode and strict tool use for guaranteed schema compliance and validated agentic workflows.
Finds recipes via web search and provides a systematic workflow for scaling ingredient portions, handling fractional measurements, and formatting final outputs.