local-ai-setup
From the author
The one command that takes someone from nothing to a working local AI setup: scans their machine, asks what they want it for, recommends a model and an app, asks Open WebUI or Odysseus when the pick is browser-based, then installs it with their approval. Use when the user says "set up local AI", "help me run AI on my own computer", "I want to run AI locally", "get me started with local LLMs", "run AI offline", "private AI on my machine", "local AI setup", or asks how to start with local AI without naming a specific tool. Then offers to point Claude Code itself at the installed model, so also use it for "run Claude Code on a local model", "point Claude Code at Ollama" and "use Claude Code offline". Non-technical entry point. Never installs anything before showing download sizes and getting a yes. Requires Claude Code with shell access on the user's own machine; refuses to run in a sandbox.
Install
npx skills add naveedharri/benai-skills --skill local-ai-setup -a claude-code
Installs to .claude/skills/local-ai-setup/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 82
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- install-openwebuinaveedharri/benai-skillsInstalls and wires up Open WebUI end to end, so a non-technical user gets a working local AI chat in the browser instead of setup instructions. Use when the user says "install Open WebUI", "set up Open WebUI", "get Open WebUI running", "connect Open WebUI to Ollama", "Open WebUI shows no models", "localhost:8080 refused to connect", "does not support tools", or asks for help finishing a local AI setup. Installs Ollama if missing, pulls a model that fits, starts the server, connects them, and proves it works with a real reply. Requires Claude Code with shell access on the user's own machine; refuses to run in a sandbox.Browser★ 75
- pick-my-harnessnaveedharri/benai-skillsAsks a few plain questions about the work, then names the one desktop app to run local AI models in, from LM Studio, Goose, Open WebUI, AnythingLLM, OpenWork or Odysseus. Use when the user asks "which app should I use for local AI", "LM Studio or Ollama", "what is the best local AI interface", "do I need Open WebUI", "Open WebUI or Odysseus", "which one supports MCP", "which supports skills", "pick a harness for me", or is comparing local AI desktop apps. Names one tool and states what it cannot do. Never installs anything. Requires Claude Code with shell access on the user's own machine; refuses to run in a sandbox.Design★ 75
- scan-my-machinenaveedharri/benai-skillsScans the user's actual hardware and tells them exactly which local AI models they can run, by name, with expected speed. Use when the user asks "what models can my computer run", "can I run a local LLM", "how much VRAM do I have", "which model should I download", "is my Mac good enough for local AI", "scan my machine", or shares hardware specs and asks what fits. Reads real memory and GPU rather than asking the user to know their own specs. Never installs anything. Requires Claude Code with shell access on the user's own machine; refuses to run in a sandbox.Planning★ 75
- legacy-to-ai-readynicepkg/ai-workflowTransform legacy codebases into AI-ready projects with Claude Code configurations. Use when (1) analyzing old projects to generate AI coding configurations, (2) creating CLAUDE.md, skills, subagents, slash commands, hooks, or rules for existing projects, (3) user wants to enable vibe coding for a codebase, (4) onboarding new team members with AI-assisted development, (5) user mentions "make project AI-ready", "generate Claude config", or "create coding standards for AI".Engineering★ 288
- claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST OfficialEngineering★ 183.9K
- allow-teamnaveedharri/benai-skillsPuts a running Open WebUI or Odysseus on a shareable public URL through an ngrok tunnel, so a teammate can sign in and use the local models without installing anything. Use when the user says "share Open WebUI with my team", "share Odysseus with my team", "let my colleague use my local AI", "expose Open WebUI", "share localhost:8080", "share localhost:7860", "give someone access to my models", "set up an ngrok tunnel", "make my local AI reachable from another machine", or asks how to let someone else try their setup. Checks the harness's own login is on and enforced before it opens anything, installs ngrok if missing, then proves the URL works from outside. Requires Claude Code with shell access on the user's own machine; refuses to run in a sandbox.Engineering★ 75
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in