Best AI and LLM engineering skills, page 22

Generate a search quality benchmark for the AI Registry. An agent skill from agentic-community/mcp-gateway-registry.

agentic-community/mcp-gateway-registry

Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills.

amd/skills

Add, fix, or validate Triton Runner support for an exact Triton version.

toyaix/triton-runner

A skill your agent uses to durably record a hard constraint or invariant that the work must respect.

harrylettering/CodeMemory

Deploy LLM models on OCI using AI Quick Actions (AQUA) - single model, multi-model, stacked (LoRA), with GPU shape selection, vLLM configuration, streaming, and tool calling.

oracle/accelerated-data-science

Scaffolds evaluation suites for the Axiom AI SDK: eval files, scorers, flag schemas and axiom.config.ts, generated from plain descriptions of an AI capability.

openclaw/clawhub

Measures the throughput difference between two branches with force-balanced routing.

mlc-ai/pith-train

Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets.

borghei/Claude-Skills

Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch).

amd/ZenDNN

Picks which Venice text model to call for a prompt based on privacy tier, input modality, capabilities and cost, and decides when to escalate from a local agent.

veniceai/skills

Lint AI agent instruction files (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md), tool definitions, system prompts, and agent configs with the deterministic LintLang CLI.

hermes-labs-ai/lintlang

A skill your agent uses for performance profiling and optimization.

ByteDance-Seed/VeOmni

Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling parameters, and prompt upsampling.

NVIDIA/cosmos-framework

AI驱动的自动化循环集合。覆盖软件开发、数据科学、内容创作、产品运营、学习管理等领域。当用户需要自动化工作流、修复问题、生成内容、分析数据或执行质量检查时使用。

jwangkun/loops

Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally.

artokun/comfyui-mcp

Generate beautiful, distinctive HTML/CSS/JS control panels for MATLAB uihtml components.

matlab/agent-skills-playground

Add a new team member to Langfuse's canonical team data and shared team table.

langfuse/langfuse-docs

Run Claude Code (Anthropic) from this host via the claude CLI (Agent SDK) in headless mode (-p) for codebase analysis, refactors, test fixing, and structured output.

win4r/claude-code-clawdbot-skill

Use Kernel Atlas to collect phase-aware hipfire measurements and render ISA Fit View visualizations for AMD GPU kernels, quant formats, and architectures.

warpfront/hipfire

Benchmark validation procedure for one assigned benchmark-related target.

Intelligent-Internet/zenith

Review PRs and local changes for hsliuustc0106/vllm-rlt: Ouro engine and KV correctness, serving behavior, and BF16 accuracy/speed evidence.

ThinkFlowLab/vllm-rlt

Builds a complete agent with multiple Airbyte connectors using PydanticAI or Claude SDK.

airbytehq/airbyte-agent-sdk

Claude Inspector macOS 배포 스킬. An agent skill from kangraemin/claude-inspector.

kangraemin/claude-inspector

Constrains language model output with regex, selections and grammars using the Guidance library, so JSON, XML, code or formatted fields come out valid.

Orchestra-Research/AI-Research-SKILLs

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

Launch a Qualitative Neural Network (QNN) — a layered, multi-epoch brainstorm of agent personas that maps divergent strategies before implementation.

iblameandrew/open-deepthink

Analyze prompt-cache effectiveness for Claude Code usage from the Agent Monitor dashboard — cache hit rate (totalcacheread / (totalcacheread + totalinput)), cachewrite vs cacheread reuse, cache-read…

hoangsonww/Claude-Code-Agent-Monitor

Brain-inspired cognitive architecture. An agent skill from LightHaru/agentbrain.

LightHaru/agentbrain

Reference desk for NVIDIA Nemotron 3 Super — architecture, training data, recipes (pretrain/SFT/RL/eval/quantization), and deployment notes.

NVIDIA-NeMo/Nemotron

Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent.

undefined-ui/second-brain-os

Generate or edit images on the user's own GPU through Guaardvark: single images, instruction edits, background cut-outs, inpaint and outpaint, consistent characters from the Cast Library, and batch…

guaardvark/guaardvark

Core operations for HyperspaceDB — a multi-geometry vector database.

YARlabs/hyperspace-db

Review one specified completed match from a validated RiftCoach summary using attributable knowledge.

123Cx330Yrx/riftcoach-agent

DeePMD-kit and Deep Potential Molecular Dynamics workflows. An agent skill from JCLiuGroup/AI-Computational-Chemist.

JCLiuGroup/AI-Computational-Chemist

Guidance for using the MMSP TypeScript SDK (@prismshadow/mmsp).

Prism-Shadow/model-message-stream-protocol

dstack is an open-source control plane for GPU provisioning and orchestration across GPU clouds, Kubernetes, and on-prem clusters.

dstackai/dstack

Analyzes Android codebases to implement ML Kit GenAI Prompt API.

sreichholf/dreamDroid

A skill your agent uses when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.

sgl-project/sglang

Add or modify an AReno algorithm, trainer, loss, advantage calculation, role model, or algorithm-specific configuration.

inclusionAI/AReno

A skill your agent uses when customizing Deep Researcher Agent behavior through Jinja2 prompt templates or per-agent model selection — editing prompts under src/deepresearcheragent/agents//prompts/…

NVIDIA-AI-Blueprints/deep-researcher-agent

Build and debug cuEquivariance irreps, custom Irrep subclasses, Clebsch-Gordan tensor products, and equivariant or segmented polynomials.

NVIDIA-BioNeMo/bionemo-agent-toolkit

Operate the user's self-hosted AsterMem service. An agent skill from Asterove/AsterMem.

Asterove/AsterMem

查询本机 CrabRAG RAG 知识库，返回证据片段 JSON；当用户问题需要本地知识库资料、法规、制度、流程或业务规则依据时使用。

guoyijia22/CrabRAG

A skill your agent uses when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function…

Ayuilos/Miffan

Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow.

benchflow-ai/benchflow

LlamaIndex 官方用户文档离线知识库，用于检索并回答 LlamaIndex Python 框架的安装、RAG、数据加载、索引、检索与查询、Agent、Workflow、模型、Embedding、向量库、评估、可观测性、部署、LlamaCloud 和 LlamaParse 等问题，也可生成有文档依据的示例代码与排障建议。当用户提到…

chujianyun/skills

Migrate Python LangChain, LangGraph, or Deep Agents applications to Pydantic AI and, when the source uses harness features, Pydantic AI Harness.

pydantic/pydantic-ai

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

SharpAI/DeepCamera