Best LLM inference and serving skills, page 7

Build a Quark Torch LLM PTQ quantization plan from model analysis and user intent.

amd/Quark

Validate Quark quantization output using four lightweight checks: auxiliary file copy alignment, excluded tensor MD5 byte-identity, config.json deep comparison after stripping quantization keys, and…

amd/Quark

Route Quark user goals to the correct atomic skill or workflow.

amd/Quark

Route Quark user goals to the correct atomic skill or workflow.

amd/Quark

Detect upstream Quark changes that affect the skill system and classify required updates.

amd/Quark

Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama.

majiayu000/claude-skill-registry

在本机 Mac 或 Apple Silicon 上部署 Gemma 4 12B。本地安装/升级 llama.cpp，下载 GGUF 量化模型，用 llama-server 暴露 OpenAI-compatible API，或用 Ollama 暴露本地模型服务；按用户需求在默认 Q4KM、64K/128K 长上下文、QAT Q40 @ 256K、左右对比演示之间选择，配置 tmux…

majiayu000/spellbook

Performance optimization patterns covering Core Web Vitals, React render optimization, lazy loading, image optimization, backend profiling, LLM inference, and sustainability UX.

yonatangross/orchestkit

This skill provides guidance for training FastText text classification models with constraints on accuracy and model size.

lazyFrogLOL/Harness_Engineering

Diagnoses Qdrant search quality issues. An agent skill from qdrant/skills.

qdrant/skills

Create and manage Neo4j vector indexes, run vector similarity search (ANN/kNN), store embeddings on nodes or relationships, use SEARCH clause (Neo4j 2026.01+, preferred) or…

neo4j-contrib/neo4j-skills

A skill your agent uses when running the Eval-v1 agent-reliability benchmark (packages/web/eval) — benchmarking a newly released Ollama Cloud model, re-running or adding scenarios, refreshing the…

heypinchy/pinchy

EXECUTE a staged codebase plan (from code-create-staged-plan or an existing notes/<codebase/ plan) one stage at a time, gate-by-gate, while keeping the local clone ground truth and a dated…

open-thoughts/OpenThoughts-Agent

Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks.

AnastasiyaW/codex-claude-code-config

Selects, deploys, and customizes AI models on Amazon SageMaker.

aws/agent-toolkit-for-aws

Installs or verifies AMD Quark and ensures the selected Python environment has an accelerator-matched PyTorch.

amd/Quark

Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request…

amd/Quark

Summarises the delta between a tool's latest release and the last summary the user saw.

sammcj/agentic-coding

Replay an LLM inference request trace (Mooncake / vLLM / SGLang hashids format) against a block-level KV prefix cache and compute hit statistics.

benchflow-ai/skillsbench

How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier, vss-agent), and health checks.

NVIDIA/skills

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).

NVIDIA/skills

Three-layer PII anonymization for session transcripts (therapy, coaching, consulting, mentoring).

glebis/claude-skills

Set up, install, and configure CONFIDE local de-identification — installs Python deps (natasha, scrubadub, phonenumbers, pymorphy2), ensures Ollama + pulls the default qwen2.5:3b model, detects…

glebis/claude-skills

A skill your agent uses when debugging, comparing, or regression-testing LLM / agent calls — when the user wants to capture LLM traffic, see a conversation as a branchable DAG, fork an alternative…

ccplugins/awesome-claude-code-plugins

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs.

jeremylongshore/tons-of-skills-marketplace

End-to-end LLM accuracy evaluation on AMD ROCm (ROCm-only) — container setup, vLLM/SGLang/ATOM serving, lm-eval / lighteval / evalscope benchmarks.

amd/Quark

Add new/custom AI models to opencode.json. An agent skill from IgorWarzocha/Opencode-Workflows.

IgorWarzocha/Opencode-Workflows

Add and manage evaluation results in Hugging Face model cards.

majiayu000/claude-skill-registry

Trending Hugging Face models, datasets, and spaces — filtered by license sanity, dedup vs same-week quantizations, with a "why notable" line per pick (architecture shift, size step, license change…

BankrBot/skills

This skill should be used when the user asks about "local models", "custom models", "fine-tuning", "self-hosting models", "model selection", "which model should I use", "data privacy and models"…

Habitat-Thinking/ai-literacy-superpowers

Routes every prompt to the right hosted Ollama model. An agent skill from mvanhorn/printing-press-library.

mvanhorn/printing-press-library

Rhythm section arranging and MIDI programming (节奏组与打ち込み) - drums, bass and harmony instruments as one unit, and how to make programmed parts sound played.

jtydhr88/music-composition-skills

vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU.

ascend-ai-coding/awesome-ascend-skills

Track daily PRs and Issues from vllm-project/vllm and vllm-project/vllm-ascend, filter by model (DeepSeek/Qwen/GLM/MiniMax/Kimi) and tech topics (PD disaggregation, MTP, quantization, graph mode…

ascend-ai-coding/awesome-ascend-skills

Expert knowledge for Azure Databricks development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations &…

MicrosoftDocs/Agent-Skills

A skill your agent uses when running open-weight LLMs locally with Ollama — pulling and tagging models, calling the local API, picking a quantization or GGUF, writing Modelfiles, and sizing VRAM and…

ericrisco/rsc-harness

A skill your agent uses when building grounded Q&A over your own corpus — chunk, retrieve hybrid, rerank, ground, cite chunk ids, refuse when the sources fall short — or when the right document is…

ericrisco/rsc-harness

A skill your agent uses when calling open-weight LLMs on Together AI or Fireworks AI's OpenAI-compatible endpoints — baseurl plus namespaced model id, the cheapest model that clears the bar…

ericrisco/rsc-harness

A skill your agent uses when operating a vector store as a data layer — choosing or migrating between Pinecone, Qdrant, Weaviate and pgvector; designing a collection or index (distance metric…

ericrisco/rsc-harness

A skill your agent uses when self-hosting an open-weight LLM for high-throughput concurrent serving with vLLM — running an OpenAI-compatible endpoint, splitting a model across GPUs with tensor or…

majiayu000/claude-skill-registry

vLLM is a high-throughput inference and serving engine for large language models that exposes an OpenAI-compatible HTTP API and a Python batch API.

majiayu000/claude-skill-registry

Zed is a fast, GPU-accelerated code editor written in Rust, with built-in AI agent and edit predictions, real-time collaboration, Vim mode and WebAssembly extensions.

majiayu000/claude-skill-registry

Operate, configure, secure, and troubleshoot the LiteLLM AI gateway (proxy) and Python SDK: run the proxy (litellm --config), route to 100+ providers through one OpenAI-compatible API, configure…

magnus919/agent-skills

Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API…

magnus919/agent-skills

Summarizes arbitrarily long text (1k-1M words) using recursive map-reduce with any LLM backend.

swyxio/skills

优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供…

majiayu000/spellbook

Interactive online benchmark orchestrator for vLLM inference services using vllm bench serve.

ascend-ai-coding/awesome-ascend-skills

Intelligent AI model router that automatically switches between two configured models (local for simple tasks, cloud for complex ones).

LeoYeAI/openclaw-master-skills