Skip to main content
skill CX Codex

llm-models — Claude Code skill: what it does, how to install

llm-models queries over a hundred LLMs through OpenRouter using the belt command-line tool directly from your agent. Selects cost-effective models automatically.

no license 238 installs ★ 31 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add 101-skills/superpowers --skill llm-models -a claude-code
Open on GitHub

What llm-models does

The skill equips your coding assistant with instructions to query external language models through the belt CLI on inference.sh. It routes prompts to specific targets like openrouter/claude-sonnet-45, openrouter/gemini-3-pro-preview, or openrouter/kimi-k2-thinking. For cost-sensitive tasks, it calls openrouter/any-model to pick a budget-friendly option.

Under the hood, the agent executes belt app run with prompt parameters packaged in JSON. It can also inspect available services via belt app search or generate input scaffolds with belt app sample.

Commands fail immediately unless the belt CLI is installed on your system and authenticated with belt login.

What it helps with

  • trigger alternative LLMs from inside your coding agent
  • delegate multi-step reasoning to Kimi K2
  • route simple questions to budget-friendly models automatically
  • test code generation tasks against Claude Opus 4.5

Example prompts for the agent

  • Run this Python coding task through Claude Opus via belt
  • Plan a web scraping pipeline using Kimi K2 thinking
  • Send this short prompt to openrouter/any-model

How to install llm-models

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill llm-models -a claude-code

2Manually: put the files in place

~/.claude/skills/llm-models/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/llm-models/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about llm-models

How to install llm-models in Claude Code?

Run npx skills add 101-skills/superpowers --skill llm-models -a claude-code in your terminal.

What does llm-models do?

It provides instructions for calling OpenRouter language models using the belt command-line tool, supporting JSON input with custom prompts.

What prerequisites are needed to run queries?

The machine needs the belt CLI installed and authenticated via belt login.

Similar skills

All skills for AI and ML →

From the same set81

The whole set →
qwen-image-2-pro qwen-image-2-pro — a skill for Claude Code and Cursor that generates images via Alibaba Qwen-Image-2.0-Pro. Renders multi-line text in posters and banners. CX Codex +1 239installs linkedin-content linkedin-content — a skill for drafting LinkedIn posts: hook formulas, formatting rules, post types, character limits and the signals the feed rewards. CX Codex +1 239installs widgets-ui widgets-ui — a skill for Claude Code, Cursor, Codex and other agents: builds React/Next.js components from JSON descriptions. The agent outputs a widget structure; the renderer assembles forms, cards and layouts in the project. CX Codex +1 239installs javascript-sdk javascript-sdk teaches the agent to wire the inference.sh JavaScript/TypeScript client into your app: running AI apps, streaming progress and building agents in code. CX Codex +1 239installs press-release-writing press-release-writing is a Claude Code skill that writes AP-style press releases with an inverted pyramid, triggered by product launches, funding rounds, partnerships, and company news. CX Codex +1 238installs customer-persona customer-persona turns market search into a buyer persona: demographics, psychographics, goals, quantified pain points and a generated portrait. For strategy decks and product decisions. CX Codex +1 238installs ai-podcast ai-podcast builds multi-character talking head video podcasts from scratch using inference.sh tools for portrait rendering, speech synthesis, and clip stitching. CX Codex +1 238installs ai-podcast-creation ai-podcast-creation is a Claude Code skill that turns text into spoken podcasts with multiple voices, generated music, and merged audio. It also supports audiobook narration and document-based discussions. CX Codex +1 238installs

Project sponsors

Companies that keep this analytics open