Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Integrates StepFun AI models (Step-3.5 Flash, Step-3) via OpenRouter API. Free tier available. Features visible reasoning, fast responses, and multimodal capabilities.
Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export, dataset preparation, synthetic data, MLX (Apple Silicon). Use when: train w…
Transform faces across ages using each::sense AI. Create age progressions, de-aging effects, baby-to-adult predictions, and aging simulations for entertainment, forensics, and visual effects.
Generate photorealistic architectural renders and visualizations using each::sense AI. Create exterior views, interior renders, sketch-to-render conversions, and more for architects, designers, and re…
Give your agent the ability to speak to you real-time. Talk to your Claude! Ultra-fast TTS, text-to-speech, voice synthesis, audio output with ~90ms latency. 8 built-in voices for instant voice respon…
Full autonomous engineering workflow using swarm mode for parallel execution
Refine prompts for GPT models (GPT-5, GPT-5.1, Codex) using OpenAI's best practices. Use when preparing complex tasks for GPT.
Generate images and videos with Kling O3 — Kling's most powerful model family. Text-to-image, text-to-video, image-to-video, and video-to-video editing. Use when the user requests "Kling", "Kling O3",…
OCR text and table extraction from images and PDF using SophNet API. Supports local files and URLs; PDFs are converted page-by-page (low resource), results merged, temp images deleted.
Use when animation needs musical flow—dance sequences, action choreography, comedic timing, scene pacing, or any motion that should feel rhythmic and well-composed over time.
Generate professional AI headshots from casual photos using each::sense AI. Create corporate portraits, LinkedIn photos, executive headshots, team photos, and more with consistent, professional qualit…
Generate Discord server graphics using each::sense AI. Create server icons, banners, role icons, welcome graphics, event banners, bot avatars, emojis, and more optimized for Discord's format requireme…
EO Studio financial advisor. Chris persona-based financial advice, AR strategy, cash flow analysis, FX judgment. Used for 'financial advice', 'cash situation', 'AR analysis', 'FX exchange', 'financial…
Retrieve YouTube transcripts without MCP using a Python CLI tool. Use when a user asks for full transcript text or available transcript languages from a YouTube URL or video ID. For summaries, key poi…
Multimodal AI: vision, image/video generation, speech-to-text, text-to-speech, voice synthesis.
Fast video/audio processing via FGP daemon - 5-20x faster than spawning ffmpeg per operation. Use when user needs to convert videos, extract audio, trim clips, resize, add watermarks, or transcode. Tr…
Prompt engineering guidance for Grok (xAI) model. Use when crafting prompts for Grok to leverage its conversational style, real-time knowledge access, and less-constrained responses.
Use when creating cinematic sequences, narrative animations, or when applying animation principles to video storytelling and visual narrative.
Generate App Store and Google Play screenshot assets using each::sense AI. Create device-framed screenshots, feature highlights, localized versions, and promotional visuals optimized for iOS App Store…
Text-to-speech, speech-to-text, voice conversion, and audio processing using EachLabs AI models. Supports ElevenLabs TTS, Whisper transcription with diarization, and RVC voice conversion. Use when the…
Build Retrieval Augmented Generation (RAG) systems with LangChain - includes embeddings, vector stores, retrievers, document loaders, and text splitting
Refine prompts for Claude models (Opus, Sonnet, Haiku) using Anthropic's best practices. Use when preparing complex tasks for Claude.
Generate 3D models from text or images. Use when the user requests "Create 3D model", "Text to 3D", "Image to 3D", "3D generation", "Generate mesh", "3D asset".
Fast audio transcription via FGP daemon - 3-10x faster than spawning whisper per file. Use when user needs to transcribe audio, convert speech to text, generate subtitles, or translate audio. Triggers…