AI & LLM Engineering · Python

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

Orchestra-Research/AI-Research-SKILLs

GGUF format and llama.cpp quantization for efficient CPU/GPU inference.

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

Step-by-step playbook for migrating a pytorch/pytorch .github/workflows/.yml from EC2 to OSDC (ARC) runners — covers both dial-up and 100% opt-in patterns, with the inputs that must be plumbed…

pytorch/test-infra

电商客服主调度技能。用于顾客咨询分类、工具选择（订单/物流/退款/图像）、风险分级与回复策略. An agent skill from whichmen/dxl-commerce-agent.

whichmen/dxl-commerce-agent

A skill your agent uses when building applications with Gemini models, Gemini API, working with multimodal content (text, images, audio, video), implementing function calling, using structured…

benjaminasterA/antigravity-awesome-skills

Converts scanned faxes, images, CSV/TSV exports and C-CDA XML into clean text on-device, ready for OpenMed de-identification and named-entity recognition.

maziyarpanahi/openmed

Covers the rules for writing Gradio Spaces on ZeroGPU hardware: the @spaces.GPU decorator, duration and quota tuning, process isolation and CUDA build limits.

huggingface/skills

A skill your agent uses to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF).

timescale/pg-aiguide

Best practices for multi-step Python tasks including data analysis, HuggingFace datasets, token counting, and any task requiring state across multiple python() calls.

A-EVO-Lab/a-evolve

Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)

sgl-project/sglang

将原生 PyTorch 自定义算子库、Torch extension、生态库（TorchCodec/FlashInfer/DeepEP 等）以及 Kernel DSL 生态（Triton/TileLang/TVM FFI 等）以最小修改方式接入 PaddlePaddle。遇到以下场景务必使用：迁移外部算子库到 Paddle；分析 PFCCLab fork 与上游的兼容差异；处理…

PaddlePaddle/Paddle

A skill your agent uses when reviewing a pull request or diff in the quax repository.

nstarman/quax

AI Engineering from Scratch 中四条独立 Claude 认证路线的 AI 原生导师与入门流程。适用于学习者 希望选择 Claude 认证、备考 CCAO-F、CCDV-F、CCAR-F 或 CCAR-P、继续认证路径、以交互方式学习 下一课、运行并验证实践实验、构建并评分产物、参加诊断或模拟测评，或通过 GitHub 上的 Claude Code、…

fancyboi999/ai-engineering-from-scratch-zh

How to reference code from sample repos in Agent Framework docs pages using :::code directives, snippet tags, zone pivots, and highlight attributes.

MicrosoftDocs/semantic-kernel-docs

Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.

microsoft/skills

Verify a Txtify change end-to-end. An agent skill from lkmeta/txtify.

lkmeta/txtify

Write, debug, and optimize Triton and Gluon GPU kernels from local upstream tutorials, production kernels, language definitions, and compiler source.

slowlyC/agent-gpu-skills

Add a new CV-CUDA operator end-to-end per .agents/guidance/MAKEOPGUIDELINES.md, with a deterministically-enforced definition-of-done.

CVCUDA/CV-CUDA

A skill your agent uses when doing operator migration or kernel migration for CUDA, Triton, or custom ops in cache-dit; porting kernels from nunchaku, deepcompressor, or other repos; designing…

vipshop/cache-dit

Deploys or restarts the shared global Experience KB that Hyperloom workspaces push their Experiences to and pull others' from, validates authenticated health, and tells each workspace which .env…

AMD-AGI/Hyperloom

Register, list, get, and manage LLM models in OCI AI Quick Actions (AQUA) using the ADS SDK.

oracle/accelerated-data-science

Watch a video from YouTube, Instagram, X/Twitter, Vimeo, TikTok or any of ~1800 yt-dlp sites (or a local path).

mathiaschu/watch

Speeds up or throttles cognee ingestion: estimate cost with a dry run, tune batching and chunk size, set LLM rate limits and run work in the background.

topoteretes/cognee

Diagnose and tune erm's output quality. An agent skill from dougcalobrisi/erm.

dougcalobrisi/erm

Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on request.

hermes-labs-ai/lintlang

Measure and diagnose AReno rollout, prefill, decode, training, checkpoint, role-switch, communication, or Python scheduling performance.

inclusionAI/AReno

Run EvalView regression checks against golden baselines to detect regressions in AI agent behavior after code, prompt, or model changes.

hidai25/eval-view

Initialize, validate, and troubleshoot Deep Agents projects in Python or JavaScript using the deepagents package.

soba-labs/langchain-agent-skills

Guides causal experiments on PyTorch models with pyvene, such as causal tracing, activation patching and interchange intervention training, to test how a model works.

Orchestra-Research/AI-Research-SKILLs

Loads large language models in 8-bit or 4-bit with bitsandbytes so they fit smaller GPUs, and sets up QLoRA fine-tuning on a 4-bit base model.

Orchestra-Research/AI-Research-SKILLs

Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.

Orchestra-Research/AI-Research-SKILLs

Generates text embeddings locally with the sentence-transformers library for RAG, semantic search, clustering and similarity, with model picks for general, multilingual and legal text.

Orchestra-Research/AI-Research-SKILLs

Trains and uses SentencePiece tokenizers on raw text, with BPE or Unigram models, for multilingual and CJK projects that need a reproducible vocabulary.

Orchestra-Research/AI-Research-SKILLs

Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads.

Orchestra-Research/AI-Research-SKILLs

Explains three ways to speed up LLM inference: draft-model speculative decoding, Medusa heads and lookahead decoding with Jacobi iteration, and when each one fits.

Orchestra-Research/AI-Research-SKILLs

Guides reinforcement-learning research with torchforge, Meta's PyTorch-native library that keeps RL algorithms apart from infrastructure, including GRPO math-reasoning runs.

Orchestra-Research/AI-Research-SKILLs

Trains LLMs with reinforcement learning using verl, from ByteDance's Seed team, with GRPO, PPO and other algorithms and swappable training and rollout backends.

Orchestra-Research/AI-Research-SKILLs

Delegates click-through web tasks, games and quizzes to S1A through its s1a command, or asks a fast decision model to pick one option from a list you provide.

ThinkFlowLab/system1-agents

Read this before writing any RavenDB query, client call or /databases/ request.

ravendb/docs

Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files.

pytorch/executorch

Uses the Deepgram Python SDK's Read API to analyze text for sentiment, summaries, topics and intents with client.read.v1.text.analyze, from raw text or a hosted URL.

deepgram/deepgram-python-sdk

Explains machine learning predictions with SHAP: picking the right explainer, computing Shapley values and drawing waterfall, beeswarm, bar and force plots.

davila7/claude-code-templates

Loads pre-trained Hugging Face Transformers models for text, vision and audio tasks, runs inference with pipelines and fine-tunes on custom datasets.

davila7/claude-code-templates

Enable or disable Unity Gateway subagent model routing for the current smart-routed Claude or Codex session, along with Smart Router Orchestrator when opted in.

databricks/unity-gateway

Kitaru just recipes, CLI structure and structured-output contract, analytics events, and PR-description conventions.

zenml-io/kitaru

Read when naming anything user-facing - GUI text, docs, public Python API names, arguments, docstrings, or error messages.

lightly-ai/lightly-studio

Developer notes for working inside the Opik Python SDK: layered design, async versus blocking calls, integration styles, batching and dependency rules.

comet-ml/opik