AI & LLM Engineering · Python · For data scientists

Forecasts any univariate time series zero-shot with Google's TimesFM model, returning point forecasts and calibrated prediction intervals without training.

google-research/timesfm

Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

Orchestra-Research/AI-Research-SKILLs

Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

Orchestra-Research/AI-Research-SKILLs

Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

Orchestra-Research/AI-Research-SKILLs

Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

Orchestra-Research/AI-Research-SKILLs

A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…

PaddlePaddle/Paddle

Sets up FAISS for fast nearest-neighbor search over large collections of dense vectors, choosing between Flat, IVF, HNSW and product quantization indexes.

Orchestra-Research/AI-Research-SKILLs

Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.

onnx/onnx

Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

R6410418/Jackrong-llm-finetuning-guide

Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.

stas00/the-art-of-debugging

Shows how to load, train and use fast Hugging Face tokenizers, with BPE, WordPiece and Unigram models, padding, truncation and alignment tracking.

Orchestra-Research/AI-Research-SKILLs

Indexes research papers on the Hugging Face Hub from arXiv, links them to models and datasets, claims authorship and generates markdown research articles from templates.

huggingface/skills

Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.

maslennikov-ig/claude-code-orchestrator-kit

Guide to LLaVA for image chat, visual question answering and captioning, with model sizes, CLI and Gradio usage and multi-turn conversation code.

Orchestra-Research/AI-Research-SKILLs

Fills in a model card for an OpenMed clinical NER or de-identification model from its evaluation reports: intended use, metrics, subgroups and limitations.

maziyarpanahi/openmed

Reference for designing and tuning production LLM prompts: few-shot examples, chain-of-thought, structured outputs, templates and system prompts.

wshobson/agents

Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/.

comet-ml/comet-examples

在发布前评估 Agent Skill bundle 的结构完整性、触发质量、产物改进、脚本正确性、安全性、已安装目录树完整性和目标宿主可移植性。

fancyboi999/ai-engineering-from-scratch-zh

Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.

huggingface/skills

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent…

pifferologo/cloud-agents-cli

Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces.

kayba-ai/agentic-context-engine

Interactive click-to-segment using Segment Anything 2 — AI-assisted labeling for Annotation Studio

SharpAI/DeepCamera

Shows how to organize PyTorch training with Lightning's LightningModule and Trainer, covering validation, DDP, callbacks and learning-rate scheduling.

Orchestra-Research/AI-Research-SKILLs

Build multimodal AI apps with Pixeltable. An agent skill from pixeltable/pixeltable.

pixeltable/pixeltable

Shows how to launch distributed Megatron-LM training on a SLURM cluster: sbatch skeleton, torch.distributed.run setup, CUDA_DEVICE_MAX_CONNECTIONS rules and failure diagnosis.

NVIDIA/Megatron-LM

中文 AI Agent 实习冲刺导师。用于生成 8 周 AI Agent 学习路线的每周大纲、每日 6 小时学习内容、基于反馈的后续调整，以及 Obsidian 双链知识点维护。适用于用户提出“生成 Week N 大纲”“生成 Day N”“根据反馈继续”“补全双链/生成知识点笔记”等请求时。输出必须为中文，围绕 AI-Interview 主项目，包含固定 5…

Marcos-wu/ai-agent-daily-mentor

Teaches an agent to build LM pipelines, RAG systems and agents in DSPy using signatures, modules and optimizers instead of hand-tuned prompts.

Orchestra-Research/AI-Research-SKILLs

A skill your agent uses when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.

sgl-project/sglang

Builds reusable command line scripts that fetch, enrich or process data from the Hugging Face API, aimed at chained, repeated or automated tasks.

huggingface/skills

Review and structure auto insurance bodily injury claims, including intake triage, evidence completeness, injury causation, treatment chronology, medical necessity, wage-loss support, negotiation…

samarailly51-pixel/claimpilot-harness

Quick-reference help for fine-tuning language models with Axolotl, covering YAML configs, FSDP, context parallelism, compressed saves and dataset formats.

Orchestra-Research/AI-Research-SKILLs

Guides training and analyzing sparse autoencoders with SAELens to break neural network activations into interpretable features, including superposition and monosemanticity studies.

Orchestra-Research/AI-Research-SKILLs

Shows how to use Pinecone, a managed vector database, for production RAG, semantic search and recommendations: indexes, upserts, queries, filters and namespaces.

Orchestra-Research/AI-Research-SKILLs

Mines local Claude Code session transcripts with a deterministic Python pipeline to show what the agent is actually used for, how often it fails and what it costs.

amd/gaia

Complete CLI reference for the ADS AQUA command-line interface (ads aqua).

oracle/accelerated-data-science

A skill your agent uses when writing or reviewing AI agent configs, system prompts, or tool definitions (JSON/YAML/Python) and you need to catch ambiguous tool descriptions, missing stop conditions…

hermes-labs-ai/lintlang

A skill your agent uses when writing, reviewing, or debugging JAX code that involves quax — custom array-ish objects (physical units, LoRA, sparse, symbolic zero, named axes), quax.quaxify…

nstarman/quax

Logs and visualizes ML training metrics with Trackio, firing alerts for issues like loss spikes, and syncing a live dashboard to a Hugging Face Space.

huggingface/skills

Explains how to run Qdrant, a Rust vector database, for RAG and semantic search, covering collections, points, distance metrics and filtered or batched queries.

Orchestra-Research/AI-Research-SKILLs

Walks through aligning language models with SimPO, a reference-free preference optimization method, using accelerate configs for Mistral 7B, Llama 3 8B and math-focused models.

Orchestra-Research/AI-Research-SKILLs

Checks an LLM judge against human labels using train, dev and test splits, TPR and TNR, and a bias correction applied to production data.

ai-evals-course/evals-skills

Run AlphaGenome-PyTorch to get genomic track predictions — via the agt predict CLI (single locus, BED regions, whole chromosomes, raw FASTA sequences, or per-gene count tables/AnnData), variant…

genomicsxai/alphagenome-pytorch

Adds distributed and mixed-precision training to a PyTorch script with a few Accelerate lines, then launches it on one GPU, many GPUs or DeepSpeed and FSDP setups.

Orchestra-Research/AI-Research-SKILLs

Google Coral Edge TPU — real-time object detection natively via Windows WSL

SharpAI/DeepCamera

Guides building Gradio web UIs and ML demos in Python, covering Interface, Blocks, ChatInterface, event listeners, layouts and chatbots.

huggingface/skills

Execute code in E2B sandboxes and integrate with LLMs for tool calling.

agent-sandbox/agent-sandbox

Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis.

Orchestra-Research/AI-Research-SKILLs

Uses Ray Data to read, transform and write large datasets across a cluster for ML training and batch inference, with streaming execution and optional GPU steps.

Orchestra-Research/AI-Research-SKILLs