AI & LLM Engineering

arkcli +deploy：普通创建推理接入点（Endpoint）的统一首选入口。用户说『创建/新建/create 一个 endpoint/接入点』或『部署/上线/deploy 某模型』时优先走这里；但脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是唯一例外，必须改走 arkcli-infer-endpoint，不能由本 skill…

volcengine/ark-cli

Hold / release GPUs by running a standard SGLang inference server on them (lab convention — occupy a card with a real serving job that fills ~all of its memory AND is driven at stable near-full…

cua-lite/cua-lite

Triage recent changes, CI failures, issues, and conversations.

cobusgreyling/loop-engineering

Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI.

pydantic/pydantic-ai

Media intelligence layer for the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.

samuelgursky/davinci-resolve-mcp

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems.

davila7/claude-code-templates

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems.

davila7/claude-code-templates

Bidirectional Home Assistant integration — HA cameras in, detection results out

SharpAI/DeepCamera

Review the Huabu operate agent's three steering artifacts at their fixed repo locations — system prompt, tool descriptions, and skills.

microsoft/Huabu

A skill your agent uses when implementing select colors with visual feedback.

thedaviddias/ux-patterns-for-developers

Run the ComfyUI agent locally for FREE with no subscription, no API key, and fully offline, using our gemma4 models fine-tuned on the comfyui-mcp tool suite via Ollama.

artokun/comfyui-mcp

Builds or modifies ComfyUI workflow JSON templates in MooshieUI's Rust backend (src-tauri/src/templates).

Mooshieblob1/MooshieUI

Guides an interactive error analysis of LLM outputs: studies the dataset, builds a review interface, picks diverse samples and organizes the failure modes you annotate.

ai-evals-course/evals-skills

Create a new agent persona under .agents/agents/. An agent skill from Apocrathia/home-assistant-config.

Apocrathia/home-assistant-config

Prepares many-file, single-turn transforms such as translating or rewriting as a plan, then submits it to the asynchronous, half-price DashScope Batch API through the qwen batch CLI.

QwenLM/qwen-code

Knowledge base assistant that retrieves and cites documents from a curated index.

Atmosphere/atmosphere

Build or change anything under app/webui with Kiln's house controls and styles only.

Kiln-AI/Kiln

Run local evaluations for Hugging Face Hub models with inspect-ai or lighteval.

henryalouf/ruflow

Build an end-to-end UAV object detection and telemetry overlay application on Intel hardware using DL Streamer Pipeline Server with MAVLink telemetry.

open-edge-platform/edge-ai-suites

Build, launch, and drive the LLM Gateway stack in an isolated worktree environment to verify API, gateway, dashboard, playground, or screenshot changes.

theopenco/llmgateway

Improve and rewrite user prompts to reduce ambiguity and improve LLM output quality.

proflead/codex-skills-library

A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…

kid-sid/claude-spellbook

Manage knowledge domains (e.g., Medical, Finance). An agent skill from FabioYanezRomero/Knowledge-Graph-Builder.

FabioYanezRomero/Knowledge-Graph-Builder

Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling.

Orchestra-Research/AI-Research-SKILLs

Guidance for using A-Evolve to improve an AI agent automatically, evolving its prompts, skills and memory against a benchmark through solve, observe and evolve cycles.

Orchestra-Research/AI-Research-SKILLs

Shows how to log ML runs, configs, metrics and media with SwanLab and view them in cloud, local or self-hosted dashboards.

Orchestra-Research/AI-Research-SKILLs

Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups.

Orchestra-Research/AI-Research-SKILLs

Fine-tunes and serves Physical Intelligence's pi0, pi0-fast and pi0.5 robot policies with JAX or PyTorch, including checkpoint conversion and policy servers.

Orchestra-Research/AI-Research-SKILLs

Testing mastracode TUI features interactively in Konsole. An agent skill from mastra-ai/mastra.

mastra-ai/mastra

Choose bounded implementation scope and existing owning modules before Guardrails runtime, configuration, client, resource, streaming, Agents, or SDK compatibility changes and feedback fixes.

openai/openai-guardrails-js

Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX…

dotnet/skills

投资专家顾问团总控。成员：段永平、查理·芒格、霍华德·马克斯（专家视角）+ 《聪明的投资者》《穷查理宝典》《投资最重要的事》（方法论）。

SpaceZephyr/career.skill

Memory recall guide. An agent skill from kevin-hs-sohn/hipocampus.

kevin-hs-sohn/hipocampus

Generative design for construction: text-to-BIM concepts, option generation, and AI-assisted design iteration with cost and carbon feedback.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Add or modify microphone noise-reduction providers in assistant-api with denoiser factory wiring, packet safety, and option/UI compatibility.

rapidaai/voice-ai

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang.kernels JIT infrastructure and public operator groups

sgl-project/sglang

EdgeOne Makers platform development router — the single entry point for building, storing data, and deploying on Tencent EdgeOne Makers.

TencentEdgeOne/edgeone-makers-tools

LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存. An agent skill from affaan-m/ECC.

affaan-m/ECC

A skill your agent uses when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, or maintained framework integrations, or when explaining Hermes Agent's…

NVIDIA/NeMo-Relay

Guides embedding model migration in Qdrant without downtime.

qdrant/skills

A skill your agent uses when running quantization of a BF16/FP16 GGUF repo and Skippy layer-package creation as one local or Hugging Face Jobs workflow, publishing both artifacts to Hugging Face.

Mesh-LLM/mesh-llm

Estimate peak GPU memory for a DualPipeV training run. An agent skill from mlc-ai/pith-train.

mlc-ai/pith-train

Guide for integrating Agentica SDK with Claude Code CLI proxy

parcadei/Continuous-Claude-v3

MANDATORY: When a user asks to install, find, search, or add ANY skill (e.g.

AgentTeam-TaichuAI/ScienceClaw

모의면접 시뮬레이션 스킬. An agent skill from thesun4sky/jobstack.

thesun4sky/jobstack

Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.

glebis/claude-skills

A skill your agent uses to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration).

NVIDIA-AI-Blueprints/video-search-and-summarization

Open-source, client-side code playground supporting 90+ languages/frameworks.

live-codes/livecodes