Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Real-time and streaming AI image generation — instant results for interactive use. Use when the user requests 'Real-time generation', 'Fast generation', 'Streaming image', 'Instant image', 'Live gener…
Expert guide for Apple's modern Speech framework (macOS 26+, iOS 26+) featuring SpeechAnalyzer and SpeechTranscriber for on-device speech-to-text transcription.
Generate and add images to a Remix game
Fast image processing via FGP daemon - 5-25x faster than spawning convert per operation. Use when user needs to resize images, convert formats, add watermarks, crop, compress, or batch process images.…
Fast video/audio downloading via FGP daemon - 5-15x faster than spawning yt-dlp per operation. Use when user needs to download videos, extract audio, get metadata, or download playlists from YouTube a…
Generate two distinct, AI-powered image variations for advertising campaigns using Google Gemini's image generation capabilities. Use when creating visual assets for ads based on campaign parameters a…
Extract subtitles/transcripts from YouTube videos. Triggers: "youtube transcript", "extract subtitles", "video captions", "视频字幕", "字幕提取", "YouTube转文字", "提取字幕".
vox.ai development best practices. (1) Voice agent system prompt design, authoring, and refactoring (template, {{...}} variable injection, filler options, character normalization, tools/silence action…
Edit existing videos using AI — remix style, edit content, upscale resolution, remove background, or add audio/sound effects. Use when the user requests "Edit video", "Remix video", "Upscale video", "…
Generate CLAUDE.md, CODEMAP.md, and MEMORY.md for any backend project (Node.js, Python, Go, etc.) using prompts and manual analysis. Uses Claude AI to help you document your project constitution, code…
Fast Anthropic Claude API operations via FGP daemon - 15-30x faster than spawning API clients per request. Use when user needs Claude chat completions, streaming responses, token counting, or batch re…
Fast local Ollama model inference via FGP daemon. Use when user needs local LLM chat, text generation, embeddings, or model management. Triggers on "ollama chat", "local llm", "ollama generate", "olla…
Evaluate complex requests from 3 independent perspectives (Creative, Pragmatic, Comprehensive), reach consensus, then produce complete outputs. Use for architecture decisions, creative content, analys…
Generates a chronological timeline of key events, decisions, and flashpoints from a collection of documents. Use when asked to create a timeline, understand sequence of events, see what happened when,…
Synthesize scientific theories from literature corpora using ASTA Theorizer. Use when asked to generate hypotheses, find research gaps, synthesize knowledge across many papers, or create literature-gr…
Use this skill when the user describes a component in natural language, says "create a component with...", "I need a card that has...", "build a form with fields for...", "generate component from desc…
Train custom AI models (LoRA) on fal.ai — personalize image generation for specific people, styles, objects, or video generation. Use when the user requests "Train model", "Train LoRA", "Fine-tune", "…
Build AI-powered Ruby applications with RubyLLM. Full lifecycle - chat, tools, streaming, Rails integration, embeddings, and production deployment. Covers all providers (OpenAI, Anthropic, Gemini, etc…
Fast Hugging Face Inference API via FGP daemon. Use when user needs text generation, embeddings, classification, image captioning, or model inference. Triggers on "huggingface inference", "generate te…
Fast Stability AI image generation via FGP daemon. Use when user needs to generate images, transform images, inpaint, upscale, or remove backgrounds with Stable Diffusion. Triggers on "stability gener…
Vercel AI SDK 5 patterns: useChat, streaming, tool integration, Server Actions. Trigger: When building AI chat interfaces, using Vercel AI SDK, streaming LLM responses, or integrating tools.
-
Hämta väderprognoser från SMHI för de inbyggda orterna Mjölby, Linköping, Norrköping, Motala och Vadstena, samt vädervarningar för Östergötland. Använd när användaren frågar om väder, temperatur, nede…
Exercise tracker for Claude Code. Setup, test, add exercises, tune detection. Launches pose-detection UI when Claude edits files.