Zapier MCP provides over 8,000 individual tools with no memory of your preferences. This skill gives Claude persistent memory for your workflows so it remembers which tools to use and when. It also triggers your pre-built multi-step Zaps via webhooks with simple conversational requests.

This skill provides tools for creating, editing, and analyzing Excel spreadsheets. It handles formulas, formatting, data analysis, and formula recalculation using LibreOffice. Perfect for financial modeling, data processing, and spreadsheet automation tasks.

Skills fail when not tested under pressure. This skill applies test-driven development to skill authoring, teaching you to verify skills work before deployment and close rationalization loopholes before users encounter them.

Writing comprehensive implementation plans prevents context switching and ensures no steps are missed during complex software development. This skill breaks down multi-step tasks into bite-sized, test-driven steps with exact file paths and commands.

Creating rich HTML artifacts for Claude conversations requires significant frontend expertise. This skill provides a complete React development environment with shadcn/ui components so you can build professional interactive artifacts quickly.

Testing local web applications requires setting up servers, navigating pages, and verifying frontend behavior. This toolkit provides Playwright automation scripts and server lifecycle management for efficient testing.

Users struggle to save online videos for offline access. This skill downloads YouTube videos and other platform content in multiple formats and quality options for offline viewing, editing, or archival.

AI agents often claim work is complete without running verification commands. This skill enforces a strict gate that requires running actual verification commands and reading output evidence before making any completion claims or expressing satisfaction.

Working with large datasets that exceed RAM causes memory errors and slow performance. Vaex uses lazy evaluation and memory-mapping to process billions of rows instantly without loading data into memory.

An AI skill for Claude, Codex, and Claude Code

Creating user personas from raw research data is time-consuming and often inconsistent. This toolkit analyzes user behavior patterns, demographics, and interview insights to automatically generate research-backed personas with confidence scoring and design implications.

Finding patent and trademark information requires navigating multiple USPTO systems. This skill provides unified access to PatentSearch, PEDS, TSDR, and assignment databases for comprehensive IP research.

AI assistants often skip skill checks, leading to inconsistent workflows. This skill establishes mandatory skill invocation rules, ensuring the right tools are used for every task. It creates disciplined, predictable behavior across all conversations.

Managing multiple features in the same repository requires constant branch switching and context loss. This skill creates isolated git worktrees that let you work on separate features simultaneously with automatic directory selection, safety verification, and clean baseline testing.

Need to find protein sequences and annotations from UniProt? Query protein databases by name, gene, accession, or organism. Retrieve sequences, map identifiers, and access functional annotations via REST API.

High-dimensional data is difficult to visualize and analyze. UMAP provides fast nonlinear dimensionality reduction that preserves both local and global structure for clear 2D/3D visualizations and effective clustering preprocessing.

Creating consistent design systems manually takes significant time and often results in inconsistent implementations. This toolkit automates design token generation for colors, typography, and spacing, ensuring visual harmony across all components and exports developer-ready code.

Medical professionals need structured, compliant treatment plans for patient care documentation. This skill provides professional LaTeX templates, validation scripts, and clinical frameworks for generating treatment plans across all medical specialties in minutes.

Working with transformer models requires understanding pipelines, tokenization, and fine-tuning workflows. This skill provides comprehensive guidance for using the Hugging Face Transformers library across NLP, computer vision, and audio tasks with best practices and code examples.

Predict molecular properties, generate new compounds, and analyze proteins using TorchDrug ML library. Train graph neural networks on molecules, proteins, and biomedical knowledge graphs for drug discovery and computational chemistry tasks.