Infsh Cli
技能 已验证 活跃Run 250+ 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
To enable users to easily run a vast ecosystem of AI applications and models from a single, unified command-line interface without needing to manage GPUs or complex API integrations.
功能
- Run 250+ AI apps via CLI
- Support for image, video, LLM, search, 3D, and social automation
- Upload local files as inputs
- Track task status and results
- Comprehensive CLI reference and examples
使用场景
- Generating images and videos using various AI models
- Interacting with LLMs for text generation or analysis
- Performing web searches and data extraction
- Automating tasks on platforms like Twitter/X
- Integrating AI capabilities into scripts or workflows
非目标
- Providing direct access to raw AI model APIs without the CLI abstraction
- Managing local AI model deployments or GPU resources
- Offering a graphical user interface for AI app execution
Compliance
- info:GDPRThe skill facilitates interaction with AI models which may process personal data. While the CLI itself doesn't appear to handle PII directly, the inference.sh platform's GDPR compliance should be considered by the user.
Protocol
- info:Idempotent retry & timeoutsThe underlying inference.sh service likely handles retries and timeouts for app executions. The CLI itself does not expose explicit controls for this. The `belt task get --no-wait` command indicates asynchronous operations are supported.
安装
npx skills add inferen-sh/skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
Project Session Manager
100Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
Github
100Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.
Telegram Crabbox E2e Proof
100Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.
Agent Browser
100AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用，包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。
Openclaw
100使用多提供商路由从文本生成图像和视频 — 支持 GPT Image 2.0（近乎完美的文本渲染）、Nanobanana 2、Seedream 5.0、Midjourney V8.1（统一的逼真+动漫风格）、Flux 2 Klein（经济高效的草稿）、Seedance 2.0 / Happyhorse 1.0 / Veo 3.1 视频，以及本地 ComfyUI 工作流。包含 1,446 个精选提示和风格感知提示增强。当用户想要创建图像/视频、设计素材、制作照片动画、增强提示或管理 AI 艺术工作流时使用。不适用于：通用聊天、代码生成、文档编写、现有素材的视频编辑、音频/TTS，或任何与 AI 图像/视频创建无关的任务。