{"query":"Ollama","count":18,"timings_ms":{"embed":137,"vector":142,"total":279},"embed_cached":true,"results":[{"slug":"Prism-Shadow/ollama","score":0.4341,"name":"ollama","category":"AI & Automation","quality_tier":"featured","quality_score":93,"repo_stars":1923,"repo_full_name":"Prism-Shadow/penguin-harness","description":"Deploy and serve local models with Ollama — pull and run them, then expose the OpenAI-compatible endpoint to apps and agents.","entity_type":"skill","detail_url":"/skills/Prism-Shadow/ollama/"},{"slug":"ArieGoldkin/ollama-local","score":0.4293,"name":"ollama-local","category":"AI & Automation","quality_tier":"listed","quality_score":73,"repo_stars":5,"repo_full_name":"ArieGoldkin/claude-forge","description":"Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.","entity_type":"skill","detail_url":"/skills/ArieGoldkin/ollama-local/"},{"slug":"NNIIKKKKII/grepai-embeddings-ollama","score":0.401,"name":"grepai-embeddings-ollama","category":"AI & Automation","quality_tier":"listed","quality_score":75,"repo_stars":2,"repo_full_name":"NNIIKKKKII/grepai-skills","description":"Configure Ollama as embedding provider for GrepAI. Use this skill for local, private embedding generation.","entity_type":"skill","detail_url":"/skills/NNIIKKKKII/grepai-embeddings-ollama/"},{"slug":"rjvim/rjv-ollama-delegate","score":0.3811,"name":"rjv-ollama-delegate","category":"AI & Automation","quality_tier":"listed","quality_score":63,"repo_stars":null,"repo_full_name":"rjvim/ai-skills","description":"Use when delegating mechanical coding/text work to LOCAL Ollama models (free, private, fast) — implementing a feature from a written spec, writing tests from a spec, classification, extraction, summarization, format conversion. Trigger phrases: \"let qwen do it\", \"use the local model\", \"delegate to ollama\", \"spike this on a local model\". NOT for code review, bug-hunting, or anything unverifiable — local models draft, the main agent reviews.","entity_type":"skill","detail_url":"/skills/rjvim/rjv-ollama-delegate/"},{"slug":"NNIIKKKKII/grepai-ollama-setup","score":0.3715,"name":"grepai-ollama-setup","category":"AI & Automation","quality_tier":"listed","quality_score":75,"repo_stars":2,"repo_full_name":"NNIIKKKKII/grepai-skills","description":"Install and configure Ollama for local embeddings with GrepAI. Use this skill when setting up private, local embedding generation.","entity_type":"skill","detail_url":"/skills/NNIIKKKKII/grepai-ollama-setup/"},{"slug":"tdimino/llama-cpp","score":0.3629,"name":"llama-cpp","category":"AI & Automation","quality_tier":"listed","quality_score":85,"repo_stars":33,"repo_full_name":"tdimino/claude-code-minoan","description":"Secondary local LLM inference engine via llama.cpp. This skill should be used when running GGUF models directly, loading LoRA adapters for Kothar, benchmarking inference speed, or serving models via llama-server. Includes dedicated Qwen 3.5 serve scripts (9B dense with F16 option, 35B MoE) with asymmetric KV cache and thinking mode. Complements Ollama (which remains primary for RLAMA and general use).","entity_type":"skill","detail_url":"/skills/tdimino/llama-cpp/"},{"slug":"agents-inc/ai-infrastructure-ollama","score":0.3627,"name":"ai-infrastructure-ollama","category":"AI & Automation","quality_tier":"listed","quality_score":77,"repo_stars":15,"repo_full_name":"agents-inc/skills","description":"Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint","entity_type":"skill","detail_url":"/skills/agents-inc/ai-infrastructure-ollama/"},{"slug":"jeremylongshore/ollama-setup","score":0.3551,"name":"ollama-setup","category":"AI & Automation","quality_tier":"featured","quality_score":99,"repo_stars":2329,"repo_full_name":"jeremylongshore/claude-code-plugins-plus-skills","description":"Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: \"install ollama\", \"local AI\", \"free LLM\", \"self-hosted AI\", \"replace OpenAI\", \"no API costs\". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.","entity_type":"skill","detail_url":"/skills/jeremylongshore/ollama-setup/"},{"slug":"suxiaoshao/ollama-api","score":0.3463,"name":"ollama-api","category":"AI & Automation","quality_tier":"listed","quality_score":45,"repo_stars":1,"repo_full_name":"suxiaoshao/gpui","description":"Reference skill for Ollama's native `/api/chat` and `/api/show` endpoints. Use when implementing, reviewing, or debugging an Ollama provider that needs chat inference, chat streaming, or full model-information retrieval from Ollama.","entity_type":"skill","detail_url":"/skills/suxiaoshao/ollama-api/"},{"slug":"KerberosClaw/llm-benchmark","score":0.3352,"name":"llm-benchmark","category":"AI & Automation","quality_tier":"solid","quality_score":91,"repo_stars":75,"repo_full_name":"KerberosClaw/kc_ai_skills","description":"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, restores stopped services, and writes a markdown comparison report. NOT for hosted API model evaluation or subjective chat-quality judging without local benchmark commands.","entity_type":"skill","detail_url":"/skills/KerberosClaw/llm-benchmark/"},{"slug":"rjvim/rjv-codex-ollama-subagents","score":0.3282,"name":"rjv-codex-ollama-subagents","category":"AI & Automation","quality_tier":"listed","quality_score":63,"repo_stars":null,"repo_full_name":"rjvim/ai-skills","description":"Use for any local-Ollama delegation: (a) Codex native subagents with repo tools — GPT-5.5 orchestrator, qwen/gemma explorers for read-only exploration, qwen/gemma workers for scoped edits, hybrid-ollama profile, Ollama serve tuning, mixed OpenAI-mini + local routing; and (b) one-shot local text generation (no repo tools) via the bundled ollama-chat.sh runner — draft-from-spec, tests, classify, summarize. Triggers: 'Codex local Ollama subagents', 'hybrid-ollama', 'qwen-explorer', 'gemma-explorer'","entity_type":"skill","detail_url":"/skills/rjvim/rjv-codex-ollama-subagents/"},{"slug":"xuiltul/local-llm-tool","score":0.3261,"name":"local-llm-tool","category":"AI & Automation","quality_tier":"solid","quality_score":89,"repo_stars":224,"repo_full_name":"xuiltul/animaworks","description":"Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.","entity_type":"skill","detail_url":"/skills/xuiltul/local-llm-tool/"},{"slug":"mm-arturo/ollama-qwen-setup","score":0.3171,"name":"ollama-qwen-setup","category":"AI & Automation","quality_tier":"listed","quality_score":72,"repo_stars":null,"repo_full_name":"mm-arturo/claude-code-skills","description":"Install Ollama and run Qwen3.8-27B locally, end to end - measure the machine's VRAM, recommend the quantization that actually fits, download the GGUF plus the vision projector, register the model, verify it runs fully on the GPU, and hand back a one-card summary of how to call it. Use when the user asks to install Ollama, run Qwen locally, set up a local LLM, or pick a GGUF quant for their hardware.","entity_type":"skill","detail_url":"/skills/mm-arturo/ollama-qwen-setup/"},{"slug":"cjw0076/local-llm-agent","score":0.3157,"name":"local-llm-agent","category":"AI & Automation","quality_tier":"listed","quality_score":70,"repo_stars":null,"repo_full_name":"cjw0076/myworld","description":"Use the high-end LOCAL LLMs on this machine as a real agent/coding substrate (not just Claude). Dual RTX 5090 (64GB VRAM) + ollama already installed and serving. Best agentic-coding local model: qwen3-coder:30b. Covers how to pull, run, call (CLI / HTTP / OpenAI-compatible / function-calling), route through the AIOS provider harness, and use as a heterogeneous arm in absorption-probe. Per feedback_use_all_substrates_not_own_head — don't solve from one model.","entity_type":"skill","detail_url":"/skills/cjw0076/local-llm-agent/"},{"slug":"robinbakshi007/rb-ollama","score":0.3034,"name":"rb-ollama","category":"AI & Automation","quality_tier":"listed","quality_score":70,"repo_stars":null,"repo_full_name":"robinbakshi007/ollama-direct-custom-agent","description":"Multi-model AI coding assistant with 51 tools and 13+ providers. Use for code review, refactoring, testing, documentation, and general coding tasks.","entity_type":"skill","detail_url":"/skills/robinbakshi007/rb-ollama/"},{"slug":"espensev/delegate","score":0.3032,"name":"delegate","category":"AI & Automation","quality_tier":"listed","quality_score":72,"repo_stars":null,"repo_full_name":"espensev/ai-skills","description":"Decide whether a narrow, well-scoped sub-task should go to a LOCAL Ollama model vs stay with the controller, and route it if so. Grounded in the ollama-telemetry MCP delegation tools with a static-guidance fallback. Use when offloading a bounded transform (summarize/classify/extract/rewrite/review/draft) on material the controller already fetched.","entity_type":"skill","detail_url":"/skills/espensev/delegate/"},{"slug":"juanre/llmring","score":0.2963,"name":"llmring","category":"AI & Automation","quality_tier":"solid","quality_score":64,"repo_stars":3,"repo_full_name":"juanre/llmring","description":"Unified Python interface for OpenAI, Anthropic, Google, and Ollama LLMs - skills for chat, streaming, structured output, tools, providers, and lockfiles","entity_type":"plugin","detail_url":"/skills/juanre/llmring/"},{"slug":"Prism-Shadow/vllm","score":0.2906,"name":"vllm","category":"AI & Automation","quality_tier":"featured","quality_score":93,"repo_stars":1923,"repo_full_name":"Prism-Shadow/penguin-harness","description":"Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.","entity_type":"skill","detail_url":"/skills/Prism-Shadow/vllm/"}],"source":{"source":"ClaudeAtlas","source_url":"https://claudeatlas.com","license":"MIT (catalog metadata); skills retain upstream licenses","data_recency":"Updated daily ~06:30 UTC","methodology_url":"https://claudeatlas.com/methodology/","citation_url":"https://claudeatlas.com/credits/","recommended_citation":"Source: ClaudeAtlas — https://claudeatlas.com"}}