Explore our collection of Agent Skills to enhance your AI workflow.
Implements an eval-driven development framework to define, track, and measure the reliability of AI-generated code.
Implements scalable backend architecture, optimized API design, and robust server-side patterns for Node.js and Next.js applications.
Automates complex multimedia tasks including video encoding, audio extraction, and stream processing using the industry-standard FFmpeg framework.
Integrates Google Gemini models into Claude Code for advanced reasoning, multimodal analysis, and high-speed text generation using the google-genai SDK.
Architects user-centered interfaces, comprehensive design systems, and accessible digital experiences using modern design methodologies and token-based systems.
Guides the development, refactoring, and testing of MoonBit projects using idiomatic patterns and the moon toolchain.
Implements cross-platform file I/O and system calls using the Bun runtime's internal Zig utilities.
Protects codebase integrity by enforcing security standards, performance benchmarks, and offline-first architectural compliance.
Optimizes Claude Code sessions by suggesting manual context compaction at logical task boundaries to prevent information loss.
Extracts and saves reusable coding patterns, error resolutions, and project-specific workflows automatically from your Claude sessions.
Implements high-performance React and Next.js architectural patterns, component design systems, and state management best practices.
Verifies code implementation immediately through automated execution or logic review to ensure functional correctness without formal overhead.
Applies behavioral science and over 70 psychological mental models to optimize marketing strategies and consumer influence.
Provides optimized ClickHouse database patterns, high-performance query strategies, and data engineering best practices for large-scale analytical workloads.
Automates a multi-phase quality assurance cycle to ensure code reliability and security before deployment.
Evaluates AI agent workflows and performance using a comprehensive framework based on Anthropic's best practices.
Enforces rigorous test-driven development practices to ensure high code quality and comprehensive test coverage across unit, integration, and E2E layers.
Implements scalable, production-ready Node.js backend architectures using Express, Fastify, and industry-standard design patterns.
Implements high-performance ClickHouse database patterns, query optimizations, and efficient data engineering workflows for analytical workloads.
Validates that code implementations align perfectly with specified requirements, design documents, and task lists before archiving changes.
Implements a formal eval-driven development framework to measure, test, and improve AI coding reliability through structured evaluations.
Optimizes AI coding sessions by suggesting manual context compaction at logical task boundaries instead of arbitrary automated triggers.
Analyzes compiled binaries, identifies assembly patterns, and reconstructs program logic across multiple architectures.
Standardizes internationalization and localization workflows for software extensions across 22 supported languages.
Audits source code for vulnerabilities and enforces industry-standard security patterns across authentication, data handling, and API development.
Implements modern Next.js 14+ architectures using Server Components, streaming, and advanced routing patterns.
Automates npm package installations in non-interactive environments by handling confirmation prompts automatically.
Defines and implements Service Level Indicators (SLIs) and Service Level Objectives (SLOs) to measure and maintain system reliability.
Identifies and resolves performance bottlenecks in Python applications using advanced profiling tools and optimization patterns.
Provides a comprehensive template for project architecture, coding patterns, and testing requirements to ensure AI-driven development consistency.
Scroll for more results...