skilld
All skills
inference-shell avatar

/agent-tools

@8381375
by inference-shellinference-shell/skills757 stars
104

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

Ask your Agent

Use this Skill: https://skilld.dev/gh/inference-shell/skills/agent-tools

This session only. Nothing lands on disk.

referencescli-reference.md

≈851 tokens on demand. Your agent reads this file only when SKILL.md points to it.

CLI Reference

Installation

curl -fsSL https://cli.inference.sh | sh

Global Commands

Command Description
belt help Show help
belt version Show CLI version
belt update Update CLI to latest
belt login Authenticate
belt me Show current user

App Commands

Your Apps

Command Description
belt app list List your deployed apps
belt app list --search <query> Search your apps
belt app search <query> Search your apps (shortcut)
belt app list -l Detailed table view

Store (Public Apps)

Command Description
belt app list Browse the public app store
belt app list --category <cat> Filter by category (image, video, audio, text, other)
belt app search <query> Search the store
belt app list --featured Show featured apps
belt app list --new Sort by newest
belt app list --page <n> Pagination
belt app list -l Detailed table view
belt app list --save <file> Save to JSON file
belt app get <app> Get app details
belt app get <app> --json Get app details as JSON

Execution

Command Description
belt app run <app> --input <file> Run app with input file
belt app run <app> --input '<json>' Run with inline JSON
belt app run <app> --input <file> --no-wait Run without waiting for completion
belt app sample <app> Show sample input
belt app sample <app> --save <file> Save sample to file

Task Commands

Command Description
belt task get <task-id> Get task status and result
belt task get <task-id> --json Get task as JSON
belt task get <task-id> --save <file> Save task result to file

Development

Command Description
belt app init Create new app (interactive)
belt app init <name> Create new app with name
belt app test --input <file> Test app locally
belt app deploy Deploy app
belt app deploy --dry-run Validate without deploying
belt app pull <id> Pull app source
belt app pull --all Pull all your apps

Environment Variables

Variable Description
INFSH_API_KEY API key (overrides config)

Shell Completions

# Bash
belt completion bash > /etc/bash_completion.d/infsh

# Zsh
belt completion zsh > "${fpath[1]}/_infsh"

# Fish
belt completion fish > ~/.config/fish/completions/infsh.fish

App Name Format

Apps use the format namespace/app-name:

  • falai/flux-dev-lora - fal.ai's FLUX 2 Dev
  • google/veo-3-1 - Google's Veo 3
  • infsh/sdxl - inference.sh's SDXL
  • bytedance/seedance-2-0 - ByteDance's Seedance 2.0
  • bytedance/seedance-2-0-fast - ByteDance's Seedance 2.0 Fast
  • xai/grok-imagine-image - xAI's Grok

Version pinning: namespace/app-name@version

Documentation

Source: SKILL.md on GitHub

Third-party checks

2 alerts13d5 checks · Risk HIGH
  • Gen Agent Trust Hub13d

    The skill provides instructions for installing and using the inference.sh CLI ('belt'). It uses a remote script execution pattern (curl piped to shell) for installation and provides capabilities for uploading local files to an external cloud platform. While these are documented features of the platform, they represent significant security surfaces that should be reviewed.

  • Socket13d

    1 alert: gptAnomaly

  • Snyk13d

    Risk: MEDIUM · 1 issue

  • Runlayer6mo

    2/5 files flagged

  • ZeroLeaks5mo

    1 finding · Score: 82/100

Provenance

Signed by skilld at 8381375. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 2 weeks ago

Capability

What it can do
Runs commands
All 1 allowed tools
Bash(belt *)

Topics

  • CLI
  • API
  • inference
  • image-generation
  • video-generation
  • llm
  • web-search
  • twitter
  • 3d
  • ai-apps

README badge

README badge for inference-shell/skills/agent-tools

What it does

Runs 250+ cloud-hosted AI apps via the inference.sh CLI, including image generation (FLUX, Gemini, Grok), video creation (Veo, Seedance), LLM calls (Claude, Gemini via OpenRouter), web search (Tavily, Exa), 3D generation, and Twitter automation. No GPU or local setup required.

Generated from the current SKILL.md.

Frequently asked

Does this skill work with Claude or other AI agents?
Yes. The skill provides CLI commands that any AI agent can execute. It's designed to be called by Claude and other coding agents via Bash.
What models and services does inference.sh support?
250+ AI apps including FLUX and Gemini for images, Veo and Seedance for video, Claude/Gemini/Grok for LLMs, Tavily and Exa for search, Rodin for 3D generation, and Twitter/X automation tools.
Do I need a GPU to run these models?
No. All models run in the cloud via inference.sh. The CLI handles execution remotely, and results are returned to your local environment.
How do I authenticate with inference.sh?
After installing the CLI with `curl -fsSL https://cli.inference.sh | sh`, run `belt login` to authenticate. The installer includes SHA-256 and optional Sigstore signature verification.
Can I upload local files to these AI apps?
Yes. The CLI automatically uploads local files when you provide a path instead of a URL, enabling workflows like image upscaling, image-to-video, or posting media to Twitter.

Generated from the current SKILL.md. These answers refresh after source changes.