Loading...
Loading...
Found 477 Skills
Analyze images using GPT-4 Vision for detailed description, OCR text extraction, object recognition, and visual Q&A. Use when the user needs to understand image content, extract text from screenshots, identify objects in photos, or ask questions about images via OpenAI GPT-4 Vision API.
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs.
svintl CLI for i18n — translations, locales, pluralization, mounts, building typed dictionaries. Triggers on `npx intl`, YAML locale files, intl directories, or any translation/i18n work in Svelte projects.
List available large language models and send chat completion requests programmatically. Use this skill when you need to call an LLM within a snippet, including model comparison, visual understanding, batch inference, and model performance testing.
Step-by-step guide for adding support for a new LLM in Dust. Use when adding a new model, or updating a previous one.
Design patterns for building AI-powered interfaces like chatbots and intelligent assistants in React.
Configure MeiGen plugin provider and API keys. Use this when the user runs /meigen:setup, asks to "configure meigen", "set up image generation", "add API key", or needs help configuring the plugin.
Vercel AI SDK 5 patterns. Trigger: When building AI chat features - breaking changes from v4.
xAI Grok API authentication and setup. Use when configuring xAI API access, setting up API keys, or troubleshooting authentication issues.
This skill should be used when the user asks for news updates, daily briefings, or what's happening in the world. Fetches news from trusted international RSS feeds and can create voice summaries.
Extracts structured data from LLM responses using JSON schemas, Zod validation, and function calling for reliable parsing. Use when users request "structured output", "JSON extraction", "parse LLM response", "function calling", or "typed responses".
Capture API response test fixture.