Llama 3 by Meta — run Llama 3.3, Llama 3.2, and Llama 3.1 across your local device fleet. The most popular open-source LLM family routed to the best availabl...

llama.cpp local GGUF inference + HF Hub model discovery.

Complete methodology for local LLM performance optimization. Core principle: maximize context while fully covering GPU memory — find the sweet spot where GPU...

Virtual pets for Llama agents. And yes, you can adopt exotic animals at animalhouse.ai with your Llama-powered agent. 73+ species. The pet is real. The llama...

Local text-to-speech using llama-tts (llama.cpp) and OuteTTS-1.0-0.6B model.

Query DeFi yield opportunities across chains using the yieldsllama CLI (powered by DeFi Llama API). Use when the user asks about DeFi yields, APY, best staki...

Run llama.cpp benchmarks on GGUF models to measure prompt processing (pp) and token generation (tg) performance. Use when the user wants to benchmark LLM mod...

LlamaIndex：把任意文档变 LLM 可查询知识的 Python 框架。4 大支柱（Index/Retriever/QueryEngine/Synthesizer）+ 52 条 anti-pattern 约束（5 fatal）。 LlamaIndex: a Python framework that tur...

Image OCR, text recognition, extract text from image, scan document, read image text, invoice OCR, receipt OCR, contract recognition, table extraction, busin...

Manage local Ollama models autonomously with health monitoring, automatic fallback, self-healing, and offline operation without internet dependency.

Indexed by skills.sh from orchestra-research/ai-research-skills

Indexed by skills.sh from davila7/claude-code-templates

Ollama multimodal model router for Llama, Qwen, DeepSeek, Phi, and Mistral — plus mflux image generation, speech-to-text, and embeddings. Self-hosted Ollama...

Ollama load balancer for Llama, Qwen, DeepSeek, and Mistral inference across multiple machines. Load balancing with auto-discovery via mDNS, health checks, q...

Ollama Ollama Herd — multimodal Ollama model router that herds your Ollama LLMs into one smart Ollama endpoint. Route Ollama Llama, Qwen, DeepSeek, Phi, Mist...

Ollama fleet router — herd your Ollama LLMs into one smart endpoint. Route Llama, Qwen, DeepSeek, Phi, Mistral, and Gemma across multiple devices with 7-sign...

Manage Ollama models across your machines — see what's loaded, what's eating disk, what's never used, and what you should pull next. Get AI-powered recommend...

Distributed inference for Llama, Qwen, DeepSeek across heterogeneous hardware. Self-hosted distributed inference — scatter requests across macOS, Linux, Wind...

Linux Ollama — run Ollama on Linux with fleet routing across multiple Linux machines. Linux Ollama setup for Llama, Qwen, DeepSeek, Phi, Mistral. Route Ollam...

Local LLM model router for Llama, Qwen, DeepSeek, Phi, Mistral, and Gemma across multiple devices. Self-hosted local LLM inference routing on macOS, Linux, a...

Configure OpenClaw memory search to use Ollama as the embeddings server (OpenAI-compatible /v1/embeddings) instead of the built-in node-llama-cpp local GGUF loading. Includes interactive model selection and optional import of an existing local embedding GGUF into Ollama.

Windows Ollama — run Ollama on Windows with fleet routing across multiple Windows PCs. Windows Ollama setup for Llama, Qwen, DeepSeek, Phi, Mistral. Route Ol...

Indexed by skills.sh from run-llama/llamaparse-agent-skills

CUDA Ollama — route Ollama LLM inference across NVIDIA GPUs with automatic CUDA load balancing. CUDA Ollama cluster for RTX 4090, RTX 4080, A100, L40S, H100....

使用 DefiLlama API/SDK 获取 TVL、stablecoins、coins 价格、yields、volumes、fees、perps、unlocks、bridges、ETFs、narratives、token liquidity、main page、DAT、meta 等数据的 CLI 技能；当需要...

Install and configure the DefiLlama MCP server for DeFi analytics. Provides 23 tools for TVL, token prices, yields, protocol metrics, stablecoins, bridges, E...

Operate DefiLlama public analytics APIs through UXC with a curated OpenAPI schema and read-first guardrails.

Operate DefiLlama public price APIs through UXC with a curated OpenAPI schema and read-first guardrails.

Operate DefiLlama Pro analytics APIs through UXC with a curated OpenAPI schema, path-templated API-key auth, and read-first guardrails.

Operate DefiLlama public yield APIs through UXC with a curated OpenAPI schema and read-first guardrails.

Professional DeFi data aggregator that provides unified access to TVL, protocols, chains, and yields data from DefiLlama. Supports multiple output formats (J...

Turn your spare GPUs into one inference endpoint. Auto-discovers machines on your network, routes requests to the best available device, learns when your mac...

Switch OpenClaw heartbeat model to local Ollama and deploy a guard to prevent unauthorized changes, avoiding paid cloud token usage.

Génère une image en local via Ollama x/z-image-turbo sur macOS et l'envoie sur WhatsApp selon le prompt donné.

Local Ollama daemons + optional LYGO stack queue roles when LYGO_STACK_ROOT is set. Read references/SECURITY.md and SECURITY_AUDIT.md before install. Not for...

Parse, extract, and analyze documents using the LlamaParse API (LlamaCloud). Use when the user asks to parse PDFs, images, spreadsheets, or other documents i...

Run, tune, and troubleshoot local Ollama models with reliable API patterns, Modelfiles, embeddings, and hardware-aware deployment workflows.

Local AI image generation using OllamaDiffuser. Use this skill when Claude needs to generate, edit (img2img/inpaint), or control (ControlNet) images locally...

Integrate and run local Ollama AI models with custom prompts for AI assistance and automatic model management.

Manage and use local Ollama models. Use for model management (list/pull/remove), chat/completions, embeddings, and tool-use with local LLMs. Covers OpenClaw sub-agent integration and model selection guidance.

Set up, diagnose, repair, and quality-test private local OpenClaw semantic memory search using Ollama embeddings. Use when memory_search is disabled, node-ll...

Use this skill when the user wants to test, compare, promote, replace, or clean up local Ollama models with a repeatable two-round real-task benchmark, no-th...

Route tasks to the optimal cloud or local model based on task characteristics — coding, analysis, reasoning, creative, or general.

Locally fine-tune Ollama models, prompts, and LoRAs using custom datasets and evaluation metrics without requiring cloud resources.

Use Ollama's vision/OCR models to recognize text from images. Supports glm-ocr, llava, moondream, and llama3.2-vision models. Ideal when you need local offli...

Ollama proxy — one endpoint that routes to multiple Ollama instances. Drop-in Ollama proxy replacement for localhost:11434. Same Ollama API, same model names...

Conducts local SEO audits analyzing keywords, meta tags, headings, image alt text, site speed, and structure, providing scores and optimization recommendations.

Ollama Updater installs or updates Ollama with curl-based breakpoint resume, auto-retry, progress display, old version cleanup, and GPU driver detection.

Web search via Ollama API. Returns relevant results from Ollama web search for AI agents.

Complete Windows setup guide for Ollama: installation, CORS header fix for web apps, custom model creation with Modelfiles, and integration with desktop AI t...

Set up local semantic memory search in OpenClaw using Ollama + nomic-embed-text. Free, private, offline-capable. Replaces cloud embedding APIs (OpenAI, Gemin...

Gradio-based chat interface for Ollama with multi-session management. Use when working with pywayne.llm.chat_ollama_gradio module to create a web-based chat...

Create and verify no-thinking variants of local Qwen/Qwen3-series Ollama models. Use when a user asks to disable thinking, hide or remove think-tag output, m...

Intelligent task routing between local and cloud Ollama LLM instances. Use when the user wants cost-efficient AI responses by routing simple tasks to a local...

Ubuntu Ollama — run Ollama on Ubuntu with fleet routing across multiple Ubuntu machines. Ubuntu Ollama setup with apt, systemd, and NVIDIA CUDA. Route Ollama...

Use when user wants to integrate Ollama into coding agents, IDEs, or agent harnesses. Supports local/on-prem/Docker deployment, Ollama Cloud, OpenAI/Anthropi...

Manage and execute Ollama tasks via SSH on a remote worker, providing queue status, exclusive task locking, and code generation commands.

Set up local semantic memory search in OpenClaw using Ollama + nomic-embed-text. Free, private, offline-capable. Replaces cloud embedding APIs (OpenAI, Gemin...

This skill should be used when the user asks to "provision GPU instance",

Pretrain LLMs at scale with PyTorch 4D parallelism.

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

Indexed by skills.sh from hkuds/cli-anything

Indexed by skills.sh from starchild-ai-agent/official-skills

Indexed by skills.sh from yoanbernabeu/grepai-skills

Indexed by skills.sh from yoanbernabeu/grepai-skills

Indexed by skills.sh from davila7/claude-code-templates

Indexed by skills.sh from orchestra-research/ai-research-skills

Indexed by skills.sh from mindrally/skills

Use this skill whenever the user needs to observe or govern on-endpoint local LLMs running on Ollama, llama.cpp (llama-server), LM Studio, or a local single-...

Deploy AI models as PAI-EAS inference services. Supports LLMs (Qwen, Llama), image gen (SD, SDXL), speech synthesis, and more. When to use: deploy models, cr...

Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits.

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact G...

Call a local llama.cpp server with the LLaVA model to analyze images.

Automate construction data processing using LLM (ChatGPT, Claude, LLaMA). Generate Python/Pandas scripts, extract data from documents, and create automated p...

Context management for self-hosted LLM backends (llama.cpp, Ollama). Prevents mid-task 503 errors and context overflows caused by VRAM-limited KV caches. Use...

Help users with [Feature Request] Support for Remote llama.cpp Server via URL Endpoint. Use when a user asks for work-productivity, feature, request, support...

Invoke various LLMs (GLM-5, Kimi-k2.5, Llama 3.1, etc.) via NVIDIA NIM API to save main agent tokens and leverage specialized model capabilities.

Deploy 1-bit quantized AI models on cheap VPS for Agent-as-a-Service. Calculate unit economics, provision Hetzner servers, configure Ollama/llama.cpp inferen...

Initialize and configure OpenClaw local embedding mode on CPU-only machines. Handles network probe, proxy fallback, GGUF model download, cmake/llama.cpp comp...

RTX Local AI — turn your gaming PC into a local AI server. RTX 4090, RTX 4080, RTX 4070, RTX 3090 run Llama, Qwen, DeepSeek, Phi, Mistral locally. Gaming PC...

Offline local semantic code search using embeddings to find and index code by meaning with llama.cpp, ONNX, or Ollama backends.

Workspace token consumption analyzer for OpenClaw agents. Scans workspace files, estimates token counts across 6 major models (GPT-4, Claude, Gemini, Llama,...

TurboQuant+ compresses llama.cpp KV caches on Apple Silicon up to 6.4x with minimal quality loss, enabling larger models and longer contexts efficiently.

Windows AI — run local AI on Windows with LLM inference, image generation, and embeddings. Windows AI server for Llama, Qwen, DeepSeek, Phi, Mistral. Turn Wi...

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Fine-tune any HuggingFace instruction-tuned model (Gemma 4, Qwen 3, Llama, Phi, Mistral, and more) on persona data from anyone-skill. Produces a self-contain...

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Crawl a docs site (default docs.stagehand.dev), discover its linked GitHub repo, and flag drift between documented signatures/flags/examples and the actual source — citing both doc and code by file and line. Uses Cerebras Cloud (Qwen3-Coder-480B / Llama-3.3-70B) for fast struc…

Indexed by skills.sh from run-llama/llamaparse-agent-skills