MCP CheckClaude skills for Ollama
29 public Claude skills touch on Ollama. These 29 are the closest fit, best-known sources first. Each links to its folder; copy it into ~/.claude/skills/ to use it.
add ollama provider
Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run…
nanocoai/nanoclaw★ 31kMITFolder:
add-ollama-provideradd ollama tool
Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.
nanocoai/nanoclaw★ 31kMITFolder:
add-ollama-toolollama stack
Run local LLM workloads with Ollama, Open WebUI, and GPU-aware tuning for private development environments. Use when setting up private inference, local AI dev environments, or air-gapped LLM deployments.
BagelHole/DevOps-Security-Agent-Skills★ 1.2kMITFolder:
ollama-stackai infrastructure ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint
agents-inc/skills★ 26MITFolder:
ai-infrastructure-ollamadspy ollama
Run DSPy with local models via dspy.LM and Ollama — no API key needed. Use when you want to run DSPy locally, use Ollama, set up a local LLM, run offline, or configure local model parameters. Also used for ollama, local model, run LLM locally, llama local,…
lebsral/DSPy-Programming-not-prompting-LMs-skills★ 12No licence statedFolder:
dspy-ollamacognee integrations
Use when the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenRouter), changing databases (Postgres, PGVector, Neo4j, Neptune, Turso), S3 storage, or the MCP server for…
topoteretes/cognee★ 33kApache-2.0Folder:
cognee-integrationstechnology selection
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 Runtime, and OllamaSharp. Covers the full spectrum from…
dotnet/skills★ 5.8kMITFolder:
technology-selectionlocal llm free
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. Use when the user asks about running locally, running for free, offline use, avoiding…
artokun/comfyui-mcp★ 879MITFolder:
local-llm-freeconfiguring vision
The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models. Use this to configure provider-neutral visual understanding…
oxbshw/watch-skill★ 534MITFolder:
configuring-visionmodel serving
LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local), BentoML (ML deployment), Triton (multi-model),…
ancoleman/ai-design-components★ 525MITFolder:
model-servingagentsop llm engine selection
Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a…
agentsope/SkillAlchemy★ 459MITFolder:
agentsop-llm-engine-selectionsetup
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 optional llama.cpp, and writes the optimal-default config so…
glebis/claude-skills★ 402MITFolder:
setuplocal models
Run quick, offline, private LLM tasks on local models via llama.cpp, reusing models already downloaded by Ollama. Use for cheap/bulk text work (summarize, classify, extract JSON, anonymize PII, translate, proofread, keywords), local embeddings, and offline…
glebis/claude-skills★ 402MITFolder:
local-modelssession anonymizer
Three-layer PII anonymization for session transcripts (therapy, coaching, consulting, mentoring). Runs Natasha (Russian NER), OpenAI Privacy Filter, and local LLM (Ollama) in sequence for maximum coverage. Fully local by default. This skill should be used…
glebis/claude-skills★ 402MITFolder:
session-anonymizerhuggingface
Use when running open models or working on the Hugging Face platform — the Inference Providers router or InferenceClient, Hub repos via the hf CLI, a dedicated Inference Endpoint with scale-to-zero, a Gradio Space with ZeroGPU, picking an open model by…
ericrisco/rsc-harness★ 388MITFolder:
huggingfaceglimmer delegation
Delegates tasks to a locally served Muse Glimmer via ollama. Use when delegation-core selects glimmer or the prompt must not leave the machine.
athola/claude-night-market★ 343MITFolder:
glimmer-delegationgemma4 local deploy
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 Q4_K_M、64K/128K 长上下文、QAT Q4_0 @ 256K、左右对比演示之间选择，配置 tmux 后台运行，验证健康检查、问答接口、资源占用和常见故障。当用户说部署 Gemma 4、Gemma 4…
majiayu000/spellbook★ 288MITFolder:
gemma4-local-deployBrowserBash Browser Automation
BrowserBash is a vendor-independent, natural-language browser automation CLI. Drive a real browser from plain-English objectives or committable Markdown tests, run on local Chrome, CDP/Playwright MCP, Browserbase, LambdaTest, or BrowserStack, and stream…
PramodDutta/qaskills★ 244MITFolder:
browserbashsynthetic data finetuning expert
Expert guide for synthetic dataset generation, LLM-as-a-judge filtering, QLoRA fine-tuning (Unsloth), DPO alignment, and GGUF/Ollama export for local SLMs / Panduan ahli generasi data sintetis, fine-tuning QLoRA, DPO, dan ekspor GGUF/Ollama.
roedyrustam/vibes-plug★ 116MITFolder:
synthetic-data-finetuning-experteu business compliance panyeroa1
Check documents for GDPR compliance, analyze data processing agreements, and ensure Belgian business law compliance using Ollama cloud models for intelligent legal analysis.
ThomasMoreAI/legal-skills-open★ 96Apache-2.0Folder:
eu-business-compliance-panyeroa1contract law reviewer panyeroa1
Intelligent contract analysis for EU and Belgian business law. Identifies risks, suggests improvements, and ensures legal compliance using Ollama cloud models.
ThomasMoreAI/legal-skills-open★ 96Apache-2.0Folder:
contract-law-reviewer-panyeroa1eu regulatory updates panyeroa1
Track EU regulations, directives, and compliance changes relevant to Belgian businesses. Monitors EU Official Journal, Commission announcements, and regulatory databases using Ollama cloud models.
ThomasMoreAI/legal-skills-open★ 96Apache-2.0Folder:
eu-regulatory-updates-panyeroa1llm benchmark
Use when the user wants to test, compare, or choose local Ollama models for their machine. Checks Ollama/GPU state, recommends model sizes from available VRAM, preserves existing benchmark records, pulls only approved models, runs repeatable benchmarks,…
KerberosClaw/kc_ai_skills★ 79MITFolder:
llm-benchmarkllama cpp
Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when…
tdimino/claude-code-minoan★ 41MITFolder:
llama-cppopen interpreter
Desktop GUI automation via OpenInterpreter — mouse, keyboard, screenshot, and OCR control for native macOS/Linux applications. Three modes: Library (Claude reasons, OI executes), OS subprocess (full autonomous computer use), and Local agent (Ollama,…
tdimino/claude-code-minoan★ 41MITFolder:
open-interpreterrlama
Build and query fully local RAG knowledge bases from documents (PDF, MD, code, etc.) using RLAMA and Ollama — no cloud, no data leaving the machine. Triggers on 'local knowledge base', 'search documents', 'document Q&A', 'RAG query', 'ingest files',…
tdimino/claude-code-minoan★ 41MITFolder:
rlamagraphrag hybrid
Répond à une question par recherche hybride locale : similarité vectorielle dans Qdrant, puis expansion du voisinage dans Neo4j, puis synthèse par un modèle Ollama — pipeline neo4j-graphrag-python (Apache-2.0), zéro API payante. À utiliser quand…
GeekFamilyCorp/TricorderKit★ 32MITFolder:
graphrag-hybridrun llms
Set up and run local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT,…
av/skills★ 28MITFolder:
run-llmsheretic abliteration
Heretic — fully automatic LLM censorship removal (abliteration) and serving the result via Ollama. Wraps p-e-w/heretic: directional ablation (difference-of-means refusal directions, orthogonalizing attn.o_proj + mlp.down_proj) with an Optuna/TPE search…
broomva/skills★ 5MITFolder:
heretic-abliteration
Claude skills for Ollama: what people ask
Is there a Claude skill for Ollama?
There are 29 of them, spread over 22 repositories on GitHub. Named for it and most starred: add ollama provider (nanocoai/nanoclaw, ★ 31k), add ollama tool (nanocoai/nanoclaw, ★ 31k) and ollama stack (BagelHole/DevOps-Security-Agent-Skills, ★ 1.2k). Stars rate the repository a skill sits in, not the skill.
How do I install a Claude skill for Ollama?
For Ollama, take the add-ollama-provider folder from nanocoai/nanoclaw (the folder that holds SKILL.md) into ~/.claude/skills/ to use it in every Claude Code project, or into .claude/skills/ for one project. In the Claude apps, zip that folder and upload it as a custom skill in settings.
Are all these Ollama skills in English?
No: gemma4 local deploy is written mainly in Chinese, Japanese, Korean or Russian rather than English, though the Ollama task is the same. Claude can follow it either way, but read it before you install.
Should I use a skill or an MCP server for Ollama?
A skill teaches Claude a way of working; an MCP server gives it new tools, like access to Ollama itself. We list 21 MCP servers for Ollama if you need the connection.
What should I check before installing a Ollama skill?
A Ollama skill is instructions Claude follows, and it can bundle scripts Claude runs, so read SKILL.md and every script first: for add ollama provider, that is everything in the add-ollama-provider folder. 1 of the 29 here, heretic abliteration, come from repositories with under 10 stars, so few people have looked at it. Red flags: piping a download into a shell, sending files to a URL, and instructions to hide what it does from you.
Are these Ollama skills maintained?
26 of the 29 Ollama skills sit in repositories that changed in the 30 days before 31 Oct 2026.
More topics: every “Claude skills for…” page.