llm-models
Access Claude, Gemini, Kimi and GLM via inference.sh CLI. Models: Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5, Gemini 4 Argon, Kimi K3, GLM-5.3. One CLI and one input format for every model. Use for: AI assistants, code generation, reasoning, agents, chat, content generation. Triggers: claude api, llm api, claude sonnet, claude opus, gemini api, kimi, glm, language model, gpt alternative, anthropic api, ai model api, llm access, chat api, claude alternative, openai alternative
How do I install this agent skill?
npx skills add https://github.com/skills-shell/superpowers --skill llm-modelsIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill provides an interface to access various LLMs (Claude, Gemini, Kimi, and GLM) through the inference.sh platform using its dedicated CLI tool.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
Install the belt CLI skill:
npx skills add belt-sh/cli
LLM Models
Access leading language models via inference.sh CLI.

Quick Start
Requires inference.sh CLI (
belt). Install instructions
belt login
# Call Claude Sonnet
belt app run anthropic/claude-sonnet-5-5 --input '{"text": "Explain quantum computing"}'
Available Models
| Model | App ID | Best For |
|---|---|---|
| Claude Fable 5.1 | anthropic/claude-fable-5-1 | Anthropic's most capable |
| Claude Opus 5.5 | anthropic/claude-opus-5-5 | Complex reasoning, coding |
| Claude Sonnet 5.5 | anthropic/claude-sonnet-5-5 | Balanced performance |
| Claude Haiku 5.5 | anthropic/claude-haiku-5-5 | Fast, economical |
| Gemini 4 Argon | google/gemini-4-argon | Google's flagship |
| Kimi K3 | melious/kimi-k3 | Multi-step reasoning |
| GLM-5.3 | melious/glm-5-3 | Open-weight, coding |
Every model takes the same input: text, plus optional system_prompt, temperature, max_tokens, images, tools.
Search LLM Apps
belt app search "claude"
belt app search "gemini"
Examples
Claude Opus (Best Quality)
belt app run anthropic/claude-opus-5-5 --input '{
"text": "Write a Python function to detect palindromes with comprehensive tests"
}'
Claude Sonnet (Balanced)
belt app run anthropic/claude-sonnet-5-5 --input '{
"text": "Summarize the key concepts of machine learning"
}'
Claude Haiku (Fast & Cheap)
belt app run anthropic/claude-haiku-5-5 --input '{
"text": "Translate this to French: Hello, how are you?"
}'
Kimi K3 (Reasoning)
belt app run melious/kimi-k3 --input '{
"text": "Plan a step-by-step approach to build a web scraper"
}'
With System Prompt
belt app sample anthropic/claude-sonnet-5-5 --save input.json
# Edit input.json:
# {
# "system_prompt": "You are a helpful coding assistant",
# "text": "How do I read a file in Python?"
# }
belt app run anthropic/claude-sonnet-5-5 --input input.json
Use Cases
- Coding: Generate, review, debug code
- Writing: Content, summaries, translations
- Analysis: Data interpretation, research
- Agents: Build AI-powered workflows
- Chat: Conversational interfaces
Related Skills
# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli
# Web search (combine with LLMs for RAG)
npx skills add inference-sh/skills@web-search
# Image generation
npx skills add inference-sh/skills@ai-image-generation
# Video generation
npx skills add inference-sh/skills@ai-video-generation
Browse all apps: belt app list
Documentation
- Agents Overview - Building AI agents
- Agent SDK - Programmatic agent control
- Building a Research Agent - LLM + search integration guide
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/skills-shell/superpowers/llm-models">View llm-models on skillZs</a>