AI & LLM Engineering

Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.

TalAter/annyang

Add or update type and shape inference for an ONNX operator.

onnx/onnx

Explains why editing CUTLASS fused-MHA headers in ONNX Runtime can leave stale CUDA kernels after an incremental build, and how to force and verify a real rebuild.

microsoft/onnxruntime

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

Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.

voidful/hung-yi-lee-skill

Migrate existing AI agent projects (LangChain, LangGraph, OpenAI Agents SDK, Claude Agent SDK, CrewAI) to EdgeOne Makers platform conventions.

TencentEdgeOne/edgeone-makers-tools

Base skill for the difyctl CLI: discover a Dify server's operations through help output and run them as commands, always with JSON output.

langgenius/dify

Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.

lobehub/lobehub

Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

decolua/9router

Diagnose and optimize vLLM Omni diffusion workloads, especially Wan/Qwen/Flux-style image and video generation.

vllm-project/vllm-omni

逸尘自用的统一音视频转写入口，在 StepFun Step ASR 与火山引擎豆包 ASR 之间按输出需求、安全边界和可用状态路由。用于本地音频或视频的纯文本转写、时间戳、SRT 字幕、口播粗剪，以及转写前体检；用户明确指定服务商时不得静默切换。Use when a local audio or video file needs transcription and the correct…

mcncarl/yichen-skills

Build cross-game mashups and total conversions, the "Minecraft inside Elden Ring" or "skateboarding in MW2" kind.

rehan-remade/universal-modder

Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.

R6410418/Jackrong-llm-finetuning-guide

A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain.

DenisSergeevitch/agents-best-practices

Quizzes you on a completed phase of the AI Engineering from Scratch course, taking a phase number or name and mapping it to that phase's directory.

rohitg00/ai-engineering-from-scratch

A skill your agent uses when the user wants to run a YOLO-Master task (train/val/predict/track/export/benchmark) or use the Agent Skill dispatcher.

Tencent/YOLO-Master

A skill your agent uses when adding a new PyTorch model to Pyrefly's shape-tracking example corpus under tensor-shapes/pyrefly-torch-stubs/examples — i.e.

facebook/pyrefly

A skill your agent uses for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired): DataModel/Field/Input, JSON operators (+ & | ^ ~), synalinks.ops…

SynaLinks/synalinks-skills

A skill your agent uses when the user wants to analyze or distill a blogger/account on Xiaohongshu or Douyin, benchmark a target creator, or diagnose their own content strategy.

otter1101/blogger-distiller

Check Kiln's model list for deprecated or sunset models across all providers.

Kiln-AI/Kiln

Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.

NVIDIA/Megatron-LM

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.

ynulihao/AgentSkillOS

Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models.

different-ai/openwork

Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR…

cclank/news-aggregator-skill

Searches, summarizes, compares and answers questions from an already configured AutoRAG librarian agent over local documents and authorized datasources.

Marker-Inc-Korea/AutoRAG

Stands up the Weave model router in Docker Compose and drives it with claude -p against a real or mocked upstream to reproduce and verify routing and streaming behavior.

weave-os/router

Create and register new patches for tweakcc. An agent skill from Piebald-AI/tweakcc.

Piebald-AI/tweakcc

Guides building on-device multi-agent apps in Swift with the AgentSquad framework: which agent, orchestrator, classifier, storage or voice type fits each situation.

2FastLabs/agent-squad

Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. An agent skill from pytorch/pytorch.

pytorch/pytorch

Create new agents in Paperclip with governance-aware hiring.

paperclipai/paperclip

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns.

pydantic/pydantic-ai

Diagnoses where an agent failed across runs and turns the findings into new skills, system prompt patches and knowledge entries, using the A-Evolve loop.

aiming-lab/AutoResearchClaw

AI 类文章和项目教程的撰写与重构优化。支持新写和重构优化（结合最新源码重写已有文章）两种输入模式，四种风格：安装教程、产品评测、面试八股、深度拆解。覆盖 AI Coding 工具实测、AI 开发框架应用、大模型测评、Agent/Skills/RAG 技术讲解，以及 JobClaw 等实战项目的教程。

itwanger/toBeBetterJavaer

Defines the typia product contract, workspace layout, package boundaries, and canonical commands.

samchon/typia

钉钉 AI 听记。Use when 查询或修改听记摘要、完整逐字稿、关键词、标签、行动项、录音、上传、思维导图、发言人洞察、ASR 热词/识别词配置或分享权限。写文档走 dingtalk-doc；建待办走 dingtalk-todo；日程走 dingtalk-calendar。命令前缀：dws minutes。

DingTalk-Real-AI/dingtalk-workspace-cli

Adds structured long-term memory to OpenClaw agents, built automatically from sessions, with tools the agent calls to recall facts, summaries and decisions.

MemoriLabs/Memori

Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.

lllllllama/RigorPilot-Skills

Finds and deletes specific mem0 memories by search query or ID, always asking for confirmation first, and can undo the most recent memories added this session.

mem0ai/mem0

Defines the shape of cognee's knowledge graph with graph_model: DataPoint node classes, identity and index fields, typed edges and fixes for duplicated nodes.

topoteretes/cognee

Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.

ksimback/looper

A skill your agent uses when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live.

google-gemini/gemini-skills

Implement specialized video understanding capabilities using the z-ai-web-dev-sdk.

jjyaoao/HelloAgents

Interact with IIB (Infinite Image Browsing) service for searching, browsing, tagging, and organizing AI-generated images.

zanllp/infinite-image-browsing

Configures OpenClaw to use free OpenRouter models, setting the best one as primary and adding ranked fallbacks so rate limits do not interrupt work.

Shaivpidadi/FreeRide

Runs the end-to-end vLLM Ascend release process: opens the release checklist and feedback issues, scans for release-blocking bugs and test coverage gaps, and generates release notes and announcements.

vllm-project/vllm-ascend

A skill your agent uses when navigating Paddle eager-mode (dynamic graph) source code, tracing forward/backward execution, debugging autograd issues, understanding PyLayer, or investigating…

PaddlePaddle/Paddle

Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR).

awslabs/agent-plugins

Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

raullenchai/Rapid-MLX