Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Full-stack AI application generator with Next.js, AI SDK, and ai-elements. Use when creating chatbots, agent dashboards, or custom AI applications. Triggers: chatbot, chat app, agent dashboard, AI app…
Comprehensive voice cloning and text-to-speech (TTS) synthesis. Use this skill when users want to clone a voice, generate speech from text, create voiceovers, or use TTS APIs like ElevenLabs. Triggers…
Blender automation with geometry creation, materials, modifiers, and Mixamo animation retargeting. Core Features: WebSocket-based real-time control, automatic bone mapping with UI review, two-phase co…
Write a short, immersive fictional segment for Act IV of a NEW TEMPS X episode. Use this Skill when you need to create a fictional scene that illustrates the implications of a scientific subject, make…
Game audio principles. Sound design, music integration, adaptive audio systems.
Complete literature retrieval capability combining search and filter skills. LOAD THIS SKILL WHEN: User needs "文獻檢索", "找文獻", "retrieve literature", "系統性搜尋" | starting systematic review | comprehensive…
Expert ML engineer specializing in production model deployment, serving infrastructure, and scalable ML systems. Masters model optimization, real-time inference, and edge deployment with focus on reli…
Generate optimized prompts for Gemini 2.5 Flash Image (Nano Banana). Use for image generation, crafting photo prompts, art styles, or multi-turn editing workflows with best practices.
Implement GraphRAG patterns combining knowledge graphs with retrieval for complex reasoning. Use this skill when building RAG over interconnected data or needing relationship-aware retrieval. Activate…
Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Claude, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Ima…
Automatic decryption and decoding tool using AI. Use when user says "解密", "decrypt", "decode", "crack", "破解密码", or provides encrypted/encoded text that needs to be deciphered. Supports 50+ encryption …
Use when creating storyboards from scripts, generating visual prompts for beat boards or sequence boards, or converting narrative beats into AI-generated images across platforms (Nano Banner, Midjourn…
Patterns for prompting Gemini to generate conceptual images for game development. Use when creating concept art, UI mockups, character designs, environment sketches, or visual references.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.…
Memory systems specialist for hierarchical memory, consolidation, and outcome-based learningUse when "memory system, memory hierarchy, memory consolidation, forgetting strategy, salience learning, out…
Use when extracting structured information from text - named entity recognition, relation extraction, coreference resolution, knowledge graph construction, and information extraction pipelinesUse when
High-precision Optical Character Recognition (OCR) service. Supports text detection and extraction from multi-language, multi-format images, and provides the coordinates of text areas and confidence s…
Implements audio systems including sound management, music systems, positional audio, and audio effects. Use when adding sound effects, music, ambient audio, or any audio features to a game.
Text editing assistant with specialized modes for typos, grammar, flow, headings, citations, and more. Use when editing, proofreading, or improving written content including documentation and markdown…
Extracts hidden data from files and analyzes forensic artifacts. Use when working with images, memory dumps, disk images, steganography, file carving, or when searching for hidden flags in files.
Combined analysis skill to find viral-worthy highlights from videos. Scans transcripts, detects laughter, analyzes sentiment/emotion, and uses scene changes to identify the most engaging moments for T…
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.…
Generate illustrations using Google's Nano Banana (Gemini Image) API. Use when creating images, illustrations, visual content from text prompts, or illustrating documents/stories. Defaults to Pro mode…
Ejecuta flujos RAG en Obsidian para responder, resumir, reorganizar o crear notas nuevas con citas trazables.