GitHub
Skills harvested from GitHub repositories
14810 skills availablepresenting-conference-talks
Generate conference presentation slides from a compiled research paper. Produces both Beamer LaTeX PDF (for polished typ...
llamaindex
The leading framework for connecting LLMs with your data. Use LlamaIndex when: Building RAG (retrieval-augmented generat...
llava
Open-source vision-language model for conversational image understanding. Use when: Building vision-language chatbots Vi...
clip
OpenAI's model that understands images from natural language. Use when: Zero-shot image classification (no training data...
skypilot
Comprehensive guide to running ML workloads across clouds with automatic cost optimization using SkyPilot. Use SkyPilot ...
autogpt
Comprehensive platform for building, deploying, and managing continuous AI agents through a visual interface or developm...
guidance
Use Guidance when you need to: Control LLM output syntax with regex or grammars Guarantee valid JSON/XML/code generation...
bitsandbytes
bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss. Installation: pip install bitsandb...
blip-2
Comprehensive guide to using Salesforce's BLIP-2 for vision-language tasks with frozen image encoders and large language...
deepspeed
Comprehensive assistance with deepspeed development, generated from official documentation. This skill should be trigger...
ml-paper-writing
Expert-level guidance for writing publication-ready papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, COLM. This skill co...
pytorch-lightning
PyTorch Lightning organizes PyTorch code to eliminate boilerplate while maintaining flexibility. Installation: pip insta...
bigcode-evaluation-harness
BigCode Evaluation Harness evaluates code generation models across 15+ benchmarks including HumanEval, MBPP, and MultiPL...
swanlab
Use SwanLab when you need to: Track ML experiments with metrics, configs, tags, and descriptions Visualize training with...
litgpt
LitGPT provides 20+ pretrained LLM implementations with clean, readable code and production-ready training workflows. In...
knowledge-distillation
Use Knowledge Distillation when you need to: Compress models from 70B → 7B while retaining 90%+ performance Transfer cap...
model-merging
Use Model Merging when you need to: Combine capabilities from multiple fine-tuned models without retraining Create speci...
gguf
The GGUF (GPT-Generated Unified Format) is the standard file format for llama.cpp, enabling efficient inference on CPUs,...
openrlhf
OpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration. Installation...
model-pruning
Use Model Pruning when you need to: Reduce model size by 40-60% with <1% accuracy loss Accelerate inference using hardwa...
awq
4-bit quantization that preserves salient weights based on activation patterns, achieving 3x speedup with minimal accura...
slime
slime is an LLM post-training framework from Tsinghua's THUDM team, powering GLM-4.5, GLM-4.6, and GLM-4.7. It connects ...
dspy
Use DSPy when you need to: Build complex AI systems with multiple components and workflows Program LMs declaratively ins...
crewai
Build teams of autonomous AI agents that collaborate to solve complex tasks. Use CrewAI when: Building multi-agent syste...