Personal
~/.codex/skills/Project
.codex/skills/One-line install
npx skills add owner/repo/skill --agent codexSkills for Codex CLI
Free agent skills compatible with Codex CLI by OpenAI. Search within them or filter by category, level and popularity.
69 skills
Chat Performance Testing
microsoft
Benchmark and validate chat UI performance in VS Code.
Memory Leak Audit
microsoft
Prevent memory leaks with effective coding patterns.
Claude Monitor
sickn33
Diagnose performance issues with Claude Code and local systems.
Autoresearch Agent
alirezarezvani
Automate your code optimization experiments.
Metrics Analysis
google-gemini
Enhance repository health through data-driven insights.
TensorBoard
davila7
Visualize and debug machine learning models effectively.
Model Pruning
davila7
Compress LLMs and speed up inference with pruning techniques.
GPTQ Quantization
davila7
Efficiently deploy large LLMs on consumer GPUs with minimal loss.
Half-Quadratic Quantization
davila7
Efficient model quantization without calibration data.
GGUF Quantization
davila7
Efficient model deployment for consumer hardware.
Flash Attention Optimization
davila7
Enhance transformer performance with optimized attention.
BitsAndBytes Quantization
davila7
Optimize LLMs with efficient quantization techniques.
AWQ Quantization
davila7
Optimize large models with 4-bit quantization.
Spark Engineer
jeffallan
Optimize and debug your Spark applications effectively.
Debug Optimize LCP
chromedevtools
Optimize Largest Contentful Paint for faster page loads.
Qdrant Memory Optimization
github
Diagnose and reduce Qdrant memory usage effectively.
Qdrant Indexing Optimization
github
Improve Qdrant indexing and ingestion performance effectively.
Qdrant Search Optimization
github
Diagnose and fix slow Qdrant search performance.
Qdrant Performance Optimization
github
Enhance the efficiency of your Qdrant deployment.
Content Hash File Cache Pattern
affaan-m
Efficiently cache file processing results using content hashes.
Flash Attention
nousresearch
Accelerate transformer training and inference significantly.
HuggingFace Accelerate
nousresearch
Simplify distributed PyTorch training with minimal code changes.
V3 MCP Optimization
ruvnet
Enhance your MCP server for faster performance.
GAIA Architecture Comparison
ruvnet
Evaluate and improve GAIA benchmark harnesses effectively.
