productivity▌

Craft precise prompts for Jimeng Seedance 2.0 multimodal AI video generation using text, images, videos, and audio. \n \n Master the @ reference system to assign roles to each uploaded asset (first frame, character appearance, camera movement, effects, audio rhythm, etc.) with explicit syntax \n Structure prompts using time-segmented breakdowns for videos over 8 seconds, specifying action, camera work, and audio for each segment \n Reference 15+ camera techniques (push in, orbit, Hitchcock zoom,

Only validate fields with cardinality starting with "1" as required.

This skill fetches OHLCV data from Yahoo Finance via yfinance and computes technical indicators locally (no API key required).

Text extraction from images using six OCR engines with preprocessing, cloud APIs, and structured output. \n \n Supports six OCR tools with decision tree: Tesseract and EasyOCR for local processing, PaddleOCR for CJK and tables, Google Vision and AWS Textract for cloud accuracy, Claude Vision for semantic understanding \n Includes full preprocessing pipeline (grayscale, deskew, denoise, binarization, morphological cleanup) to maximize accuracy on real-world images \n Provides Python and Node.js i

Implement comprehensive security hardening with defense-in-depth strategy through coordinated multi-agent orchestration:

This skill transforms a user's scattered multimodal assets (images, videos, audio) and ambiguous creative intent into a structured, executable prompt for the Seedance 2.0 video generation model. It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.

NeuroKit2 is a comprehensive Python toolkit for processing and analyzing physiological signals (biosignals). Use this skill to process cardiovascular, neural, autonomic, respiratory, and muscular signals for psychophysiology research, clinical applications, and human-computer interaction studies.

This skill guides you through implementing Metal kernels for PyTorch operators on Apple Silicon.

AI-generated music composition from text prompts with optional fine-grained control via composition plans. \n \n Supports prompt-based generation for instrumental tracks, songs with lyrics, background music, and jingles with configurable length in milliseconds \n Composition plans enable structured control over styles and sections; generate a plan, modify it, then compose for granular customization \n Includes compose_detailed method for retrieving audio alongside composition plan and metadata i

58 community-maintained best practices for shadcn/ui component development, organized by priority and impact. \n \n Covers 10 rule categories spanning CLI setup, component architecture, accessibility, styling, forms, data display, layout, composition, performance, and state management \n Each rule includes specific guidance on Radix primitives, Tailwind styling, React Hook Form integration, and accessibility compliance \n Prioritized by impact: CRITICAL rules for setup and architecture, HIGH for