Categories.seoDescriptions.all
Discover the world's most comprehensive directory for AI Agent Skills and community-driven MCP Servers (Model Context Protocol). Seamlessly find and install high-quality developer integrations for your Claude Desktop, Cursor, or custom AI agents. From cloud operations to API integrations, explore verified open-source MCP practices to supercharge your AI workflows.
claude-api is an AI agent skill that helps developers build applications with Claude API and Anthropic SDKs. It automatically detects when code imports anthropic libraries and provides Claude Opus 4.6 integration with adaptive thinking capabilities for LLM-powered applications.
chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.
The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.
The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.
writing-skills is Test-Driven Development applied to AI agent process documentation. It involves creating pressure scenarios with subagents, watching baseline failures, writing documentation skills, verifying agent compliance, and refactoring loopholes for Claude Code and Codex agents.
using-git-worktrees is a skill that creates isolated Git workspaces, allowing for simultaneous work on multiple branches without switching, using systematic directory selection and safety verification.
dispatching-parallel-agents is an AI agent skill for managing concurrent workflows. It operates on the core principle of dispatching one agent per independent problem domain, allowing them to work in parallel on tasks without shared state or sequential dependencies.
subagent-driven-development is an AI agent execution pattern that uses a fresh subagent for each independent task within a session. It is defined by a mandatory two-stage review process conducted after each task: a specification compliance review followed by a code quality review.
systematic-debugging is an AI Agent skill that enforces a strict debugging process. It prohibits proposing fixes until a root cause investigation is complete, ensuring that solutions address underlying issues rather than just symptoms.
Test-driven development is a software development process that relies on the repetitive cycle of writing tests before writing implementation code.
writing-plans is an AI Agent Skill that creates comprehensive, multi-step implementation plans for developers from a given specification. It meticulously documents every required action, from which files to touch and code to write, to testing and documentation, assuming the engineer has zero context.
using-superpowers is an AI agent skill that mandates compulsory Skill tool invocation in Claude Code when any applicable skill is detected. It establishes non-negotiable technical protocols requiring skill loading and direct implementation before generating responses, including clarifying questions.