Agent Skills Hub

implementation

Structured, template-driven workflow for end-to-end feature development including coding, automated testing, verification, and session-based improvement.

context-compression

Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.

openai-agents-sdk

Build AI agents with the OpenAI Agents SDK for Python. Supports multi-agent handoffs, function tools, stateful sessions, streaming, and Azure OpenAI integration via LiteLLM.

mastra

Official Mastra framework guide. Master AI agent and workflow development with local documentation lookup, API verification, and TypeScript-based project management.

create-skill

Standardizes the process of creating and maintaining reusable Claude Code skills for packaging developer workflows and domain expertise.

claude-code-guide

An advanced development guide for Claude Code, covering REPL environments, MCP integration, development workflows, and best practices for AI-assisted coding.

paper-plan

Generate a structured academic paper outline from research narrative, experiment data, and review conclusions.

test-environment-management

Manage test infrastructure with IaC, Docker, and service virtualization. Optimize testing costs, ensure dev/prod environment parity, and automate environment provisioning for consistent, scalable software testing.

flaky-detect

Identify, categorize, and troubleshoot flaky tests by analyzing CI history, execution patterns, and code structure to improve test suite reliability.

PAI

Physical hardware synthesis bridge for PAI. Generates blueprints, 3D printing code, SVG paths for laser cutting, and G-Code for CNC machining to bring agentic designs into the physical world.

kreuzberg

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

ring:testing-skills-with-subagents

A meta-skill for building robust AI agent skills using a TDD approach: define failure (RED), implement the skill (GREEN), and plug rationalization loopholes (REFACTOR).