Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Build self-hosted speech-to-text APIs using Hugging Face models (Whisper, Wav2Vec2) and create LiveKit voice agent plugins. Use when building STT infrastructure, creating custom LiveKit plugins, deplo…
Reproduce research papers into working code. Use when user wants to implement ML/AI papers, reproduce experiments, extract algorithms from PDFs, or convert research into executable code. Handles multi…
Generate a 16-frame storyboard for AI UGC, and create videos with Kling while maintaining character consistency. Triggered by "Create a storyboard" and "Generate a storyboard".
Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather th…
Autonomous agent-based web search fallback for when WebSearch API fails or hits limits
Analyze TCM constitution data, identify constitution types, evaluate constitution characteristics, and provide personalized health preservation advice. Support the associated analysis with health data…
Financial due diligence and Quality of Earnings (QoE) reporting. Automates trial balance tie-outs, EBITDA adjustment validation, working capital analysis, and debt-like item identification. Detects an…
This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to …
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
Store and recall sequential memory patterns and state transitions.
Parse the product links from Douyin stores, conduct creative analysis, and generate marketing videos, returning a uniform structure. The domain names for the Douyin e-commerce platform are haohuo.jinr…
Look up the latest news for the user from specified news sites. Provides authoritative URLs for politics, finance, society, world, tech, sports, and entertainment. Use browser_use to open each URL and…
Generate charts (line, bar) from data and save as image files.
Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, co…
Multi-agent stock analysis workflow
Unified media generation - images, videos, and audio through fal.ai MCP. It covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audi…
Intelligently truncate text to maintain content integrity. Suitable for novel text preprocessing and ensuring that the text does not exceed a specified length limit.
Read and comprehend the story text, summarize the characters, relationships, and plot, and organize them into a smooth outline. Suitable for quickly understanding the core of the story and providing a…
Remove AI writing patterns from text. Use when editing, reviewing, or rewriting text to sound more natural and human-written. Detects patterns like inflated symbolism, promotional language, em dash ov…
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems think…
Transform user requirements into production-grade technical specifications and AI coding instructions. Suitable for when requirements are unclear, architecture selection, generating complete technical…
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy…
Retrieves scientific papers from PubMed and creates plain-language research summaries. Use when users ask about medical research, scientific studies, clinical trials, disease treatments, or want to un…
End-to-end presentation creation from content to final PPTX, including AI illustration generation and 18 design styles. To be used when users mention 'making a PPT', 'creating slides', 'presentation',…