Explore our collection of Agent Skills to enhance your AI workflow.
Secures and validates agent success criteria through centralized JSON parsing and defensive injection prevention.
Automates modern web testing and browser interactions using Playwright-powered Robot Framework keywords.
Writes dataframe-agnostic Python code that runs seamlessly across pandas, Polars, PyArrow, and other major backends.
Streamlines the creation, testing, and publishing of Nuxt modules using best practices and Kit utilities.
Analyzes and optimizes JavaScript bundle sizes to improve web application performance and load times.
Writes and executes comprehensive API tests for Hono-based backend services using the Vitest framework.
Orchestrates the complete AI agent pipeline from task classification and selection to spawning, execution, and audit logging.
Automates robust web testing using Robot Framework's Playwright-powered Browser Library with advanced selector and assertion support.
Enforces opinionated frontend constraints and accessibility best practices for building polished, high-performance user interfaces.
Automates mobile application testing for iOS and Android native, hybrid, and web apps using Robot Framework.
Streamlines the creation and validation of AI agent templates through automated scaffolding and profile linting.
Accelerates the creation and registration of AILANG builtin functions through a streamlined M-DX1 registry workflow and automated testing tools.
Enhances Claude's decision-making through metacognitive oversight to ensure alignment and strategic focus during complex tasks.
Enables comprehensive audit trails and structured logging for Docker-based Claude Flow Novice (CFN) agent execution.
Monitors and reports real-time memory usage for Dockerized Claude agents to prevent system crashes and optimize resource allocation.
Standardizes Python development workflows using the uv package manager for high-performance environment, dependency, and execution management.
Assists with writing PRDs, analyzing feature requests, and synthesizing user research within your development workflow.
Automates the final stages of a development branch by verifying tests, managing merges or PRs, and cleaning up worktrees.
Generates and validates comprehensive testing strategies and directory-level documentation to establish consistent testing philosophies.
Generates distinctive, production-grade frontend interfaces that avoid generic AI aesthetics through intentional design choices.
Executes complex implementation plans by dispatching specialized subagents for independent tasks with a rigorous two-stage review process.
Enforces a disciplined, four-phase investigation process to identify root causes before attempting code fixes.
Accelerates development by orchestrating multiple Claude agents to solve independent tasks and bug fixes concurrently.
Enforces epistemic quality in documentation to prevent LLM hallucinations in RAG systems.
Visualizes Rust project dependencies and coupling metrics through an interactive web interface to identify architectural hotspots.
Generates detailed, TDD-focused implementation blueprints that break down complex features into actionable, bite-sized tasks.
Provides a comprehensive set of utility methods and helpers for Odoo 18 development via the DTGBase abstract model.
Transforms raw ideas into structured technical specifications through collaborative, incremental dialogue and architectural analysis.
Standardizes the creation of high-quality Claude Code skills using Test-Driven Development (TDD) principles for documentation.
Enforces rigorous code review protocols and evidence-based verification gates to ensure technical accuracy and prevent false completion claims.
Scroll for more results...