Skill-Hub

In the author's own words, from each skill's SKILL.md — showing the first 29 of 368 files.

• huggingface-accelerate

  Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

  skill-main/career/ai-engineering/accelerate/SKILL.md on GitHub (opens in a new tab)

• audiocraft-audio-generation

  PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

  skill-main/career/ai-engineering/audiocraft/SKILL.md on GitHub (opens in a new tab)

• autogpt-agents

  Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

  skill-main/career/ai-engineering/autogpt/SKILL.md on GitHub (opens in a new tab)

• awq-quantization

  Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

  skill-main/career/ai-engineering/awq/SKILL.md on GitHub (opens in a new tab)

• axolotl

  Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

  skill-main/career/ai-engineering/axolotl/SKILL.md on GitHub (opens in a new tab)

• evaluating-code-models

  Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

  skill-main/career/ai-engineering/bigcode-evaluation-harness/SKILL.md on GitHub (opens in a new tab)

• quantizing-models-bitsandbytes

  Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

  skill-main/career/ai-engineering/bitsandbytes/SKILL.md on GitHub (opens in a new tab)

• blip-2-vision-language

  Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

  skill-main/career/ai-engineering/blip-2/SKILL.md on GitHub (opens in a new tab)

• chroma

  Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

  skill-main/career/ai-engineering/chroma/SKILL.md on GitHub (opens in a new tab)

• clip

  OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

  skill-main/career/ai-engineering/clip/SKILL.md on GitHub (opens in a new tab)

• constitutional-ai

  Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

  skill-main/career/ai-engineering/constitutional-ai/SKILL.md on GitHub (opens in a new tab)

• crewai-multi-agent

  Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

  skill-main/career/ai-engineering/crewai/SKILL.md on GitHub (opens in a new tab)

• deepspeed

  Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

  skill-main/career/ai-engineering/deepspeed/SKILL.md on GitHub (opens in a new tab)

• dspy

  Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

  skill-main/career/ai-engineering/dspy/SKILL.md on GitHub (opens in a new tab)

• faiss

  Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

  skill-main/career/ai-engineering/faiss/SKILL.md on GitHub (opens in a new tab)

• optimizing-attention-flash

  Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

  skill-main/career/ai-engineering/flash-attention/SKILL.md on GitHub (opens in a new tab)

• gguf-quantization

  GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

  skill-main/career/ai-engineering/gguf/SKILL.md on GitHub (opens in a new tab)

• gptq

  Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

  skill-main/career/ai-engineering/gptq/SKILL.md on GitHub (opens in a new tab)

• grpo-rl-training

  Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

  skill-main/career/ai-engineering/grpo-rl-training/SKILL.md on GitHub (opens in a new tab)

• guidance

  Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

  skill-main/career/ai-engineering/guidance/SKILL.md on GitHub (opens in a new tab)

• hqq-quantization

  Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

  skill-main/career/ai-engineering/hqq/SKILL.md on GitHub (opens in a new tab)

• huggingface-tokenizers

  Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

  skill-main/career/ai-engineering/huggingface-tokenizers/SKILL.md on GitHub (opens in a new tab)

• instructor

  Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

  skill-main/career/ai-engineering/instructor/SKILL.md on GitHub (opens in a new tab)

• knowledge-distillation

  Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

  skill-main/career/ai-engineering/knowledge-distillation/SKILL.md on GitHub (opens in a new tab)

• lambda-labs-gpu-cloud

  Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

  skill-main/career/ai-engineering/lambda-labs/SKILL.md on GitHub (opens in a new tab)

• langchain

  Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

  skill-main/career/ai-engineering/langchain/SKILL.md on GitHub (opens in a new tab)

• langsmith-observability

  LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

  skill-main/career/ai-engineering/langsmith/SKILL.md on GitHub (opens in a new tab)

• implementing-llms-litgpt

  Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

  skill-main/career/ai-engineering/litgpt/SKILL.md on GitHub (opens in a new tab)

• llama-cpp

  Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

  skill-main/career/ai-engineering/llama-cpp/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 127k stars · 1 skill
• agent-skillsby addyosmani Production-grade engineering skills for AI coding agents. 107k stars · 25 skills
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 103k stars · 30 skills