Agent Skills Hub

java-coding-standards

Enforce high-quality Java 17+ coding standards, Spring Boot conventions, and maintainable project structures.

code-review

Perform comprehensive code reviews with a focus on security vulnerabilities, performance optimization, maintainability, and code correctness.

mcp-prompts

An intelligent development orchestration skill that provides self-improving code analysis, build error diagnosis, and automated workflow configuration via mcp-prompts integration.

recursive-decomposition

Handles large-scale tasks by automatically breaking them down into manageable, recursive sub-tasks to overcome context window limits and improve reasoning accuracy on large codebases and document sets.

oracle

CLI tool to bundle repository context, files, and prompts into a one-shot request for advanced AI debugging, refactoring, and code review.

claude-ralph

An autonomous AI agent loop that executes Claude Code repeatedly to build features from structured PRDs until completion.

feature-dev

Guided, systematic feature development agent that orchestrates codebase exploration, architectural design, implementation, and automated testing.

prp-manager

Context Engineering agent skill to initialize, generate, and execute comprehensive implementation blueprints (PRPs) for one-pass software development.

sosumi

Retrieves Apple platform documentation, Human Interface Guidelines, and WWDC transcripts as Markdown using the Sosumi service.

context-driven-development

Standardizes project context by managing artifacts (product, tech-stack, workflow, tracks) in a conductor/ directory. Supports project scaffolding, artifact synchronization, and AI alignment for greenfield and brownfield projects.

property-based-testing

Automated guidance for implementing property-based testing (PBT) in software and smart contracts to improve test coverage and edge case detection.

kreuzberg

High-performance document intelligence library for extracting text, tables, code, and metadata from 91+ file formats, with OCR and LLM-ready output.