ai-infrastructure-hugg…
Hugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text generation, streaming, embeddings, image generation,…
Tauri 2.x official plugin ecosystem, plugin APIs, permissions, and custom plugin development
$ npx -y skills add agents-inc/skills --skill desktop-plugins-tauri --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/desktop-plugins-tauriContext preview
The summary Claude sees to decide when to auto-load this skill.
Tauri 2.x official plugin ecosystem, plugin APIs, permissions, and custom plugin development
name: desktop-plugins-tauri description: Tauri 2.x official plugin ecosystem, plugin APIs, permissions, and custom plugin development
> **Quick Guide:** Tauri plugins follow a dual-install pattern: Cargo crate (Rust backend) + npm package (JS frontend). Every plugin must be registered with `.plugin()` in Rust AND have permissions granted in a capability file. Missing any step causes runtime errors, not compile errors. Custom plugins use `tauri::plugin::Builder` with optional mobile support (Swift/Kotlin). There are 30+ official plugins covering fs, http, dialog, store, notification, shell, updater, sql, log, stronghold, deep-link, global-shortcut, and more. > > **Current version:** Tauri 2.x (stable). All plugins require Rust 1.77.2+.
---
<critical_requirements>
> **All code must follow project conventions in CLAUDE.md** (kebab-case, named exports, import ordering, `import type`, named constants)
**(You MUST complete ALL four installation steps for every plugin: 1) cargo add crate, 2) npm install bindings, 3) `.plugin()` registration in Rust, 4) permissions in capability file -- missing any step causes runtime errors)**
**(You MUST scope plugin permissions in capability files -- never grant unscoped `fs:allow-read-text-file` or `http:default` without URL restrictions)**
**(You MUST use `@tauri-apps/plugin-*` npm packages for JS bindings -- not `@tauri-apps/api/*` which is the core API)**
**(You MUST use `#[cfg(desktop)]` guard when registering desktop-only plugins -- mobile builds will fail otherwise)**
**(You MUST use `tauri::plugin::Builder` with an `init()` convention when creating custom plugins -- not raw command registration)**
</critical_requirements>
---
**Auto-detection:** tauri-plugin, @tauri-apps/plugin, tauri_plugin, plugin registration, .plugin(), tauri-plugin-fs, tauri-plugin-http, tauri-plugin-store, tauri-plugin-dialog, tauri-plugin-notification, tauri-plugin-shell, tauri-plugin-updater, tauri-plugin-log, tauri-plugin-sql, tauri-plugin-stronghold, tauri-plugin-deep-link, tauri-plugin-global-shortcut, tauri-plugin-autostart, tauri-plugin-clipboard-manager, tauri-plugin-window-state, tauri-plugin-single-instance, tauri-plugin-barcode-scanner, tauri-plugin-biometric, tauri-plugin-os, tauri-plugin-process, custom plugin, plugin development, npx tauri plugin new
**When to use:**
**When NOT to use:**
**Key patterns covered:**
**Detailed resources:**
---
<philosophy>
Tauri plugins extend the core framework with native capabilities through a **dual-architecture** design: a Rust backend crate providing the implementation, and an npm package providing typed JavaScript bindings. This separation enforces security -- every plugin operation must be explicitly permitted in a capability file.
**Plugin architecture principles:**
**When to use plugins vs custom commands:**
The official skills marketplace for Agents Inc. 150+ skills covering everything from React and Prisma to Redis, ElevenLabs, and infrastructure tooling. Pick the skills that match your stack and install them via Claude Code. Need more control?
Repo: agents-inc/skills
Hugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text generation, streaming, embeddings, image generation,…
LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend tracking, virtual keys, and production…
Serverless GPU compute platform for AI model deployment — web endpoints, GPU functions, model serving, and TypeScript client patterns
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and…
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation,…