Explore our collection of Agent Skills to enhance your AI workflow.
Implements robust TypeScript-first schema validation and parsing using optimized Zod v4 patterns.
Simulates high-performance computational fluid dynamics using pseudospectral methods and optimized Python solvers.
Extracts high-quality frames and thumbnails from video files using the FFmpeg engine.
Optimizes data processing and analysis workflows using the high-performance Polars DataFrame library.
Manages Things 3 tasks, projects, and areas directly within Claude Code using the things3-cli on macOS.
Queries the Google Places API to search for locations, retrieve place details, and fetch reviews directly within the terminal.
Implements sophisticated LLM-as-judge methodologies to evaluate and compare AI model outputs with high reliability and bias mitigation.
Manages Apple Reminders directly from the terminal using the remindctl CLI on macOS.
Implements production-grade LLM-as-a-judge patterns to evaluate model outputs with high reliability and bias mitigation.
Validates Claude Code skill functionality and usability through comprehensive scenario-based testing operations.
Manages AWS Elastic Container Service clusters, task definitions, and services for containerized application deployment and orchestration.
Provides specialized techniques and command patterns for escalating system privileges from low-level access to root or administrator status.
Conducts comprehensive SQL injection vulnerability assessments to identify, exploit, and remediate database security flaws in web applications.
Audits web application code against industry-standard guidelines to ensure high-quality UI, UX, and accessibility compliance.
Provides architectural principles and best practices for designing high-performance tools and MCP interfaces for AI agents.
Extracts high-quality frames and thumbnails from video files using ffmpeg for visual inspection and asset creation.
Conducts comprehensive security assessments of SSH services including enumeration, credential attacks, and vulnerability exploitation.
Provides a comprehensive command reference for penetration testing tools including network scanning, exploitation, and vulnerability assessment.
Streamlines the deployment of Dr. Sophia AI to Railway with environment-aware build systems and automated workflows.
Implements sophisticated, multi-layered memory architectures including knowledge graphs and temporal persistence for autonomous AI agents.
Provides expert guidance and command-line patterns for network discovery, vulnerability assessment, and security auditing across diverse environments.
Builds robust evaluation frameworks and multi-dimensional rubrics to measure AI agent quality, accuracy, and efficiency.
Implements advanced memory architectures for AI agents to maintain session continuity and manage structured entity relationships.
Finds hidden-city flight deals and compares airfare prices to maximize travel savings using Skiplagged's proprietary discovery engine.
Configures and tests core network services like HTTP, HTTPS, SNMP, and SMB for penetration testing labs and security research.
Streamlines the development, deployment, and management of serverless bioinformatics workflows on the LatchBio platform.
Streamlines the process of contributing custom AI skills back to upstream repositories using standardized Git and GitHub CLI workflows.
Generates high-fidelity speech from text using ElevenLabs models with a simple, Mac-style command-line interface.
Builds machine learning models and embeddings for genomic interval data to enable similarity searches, clustering, and single-cell analysis.
Manages multiple Python versions seamlessly using the uv package manager to ensure project consistency and simplified environment setup.
Scroll for more results...