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).
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
173 skills found
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).
Implement a full Model Context Protocol (MCP) stack in Rails. Connect to external servers, expose your Rails app as an MCP server, or manage subprocess MCP containers via Docker with OAuth 2.1 PKCE support.
Install and manage Codex agent skills from curated lists or GitHub repositories.
A testing skill designed to verify the functionality of the Skillet CLI by performing basic tasks and confirming completion.
Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.
A perspective engineering engine that researches, extracts mental models, and generates runnable persona skills based on deep expression DNA analysis.
Expert guide for MoonBit development, including project scaffolding, modular layout, build tooling, and testing best practices.
Automates the creation of Betty Framework skills by scaffolding directory structures, generating YAML manifests, and handling registry registration.
Build stateful AI agents on Cloudflare Workers using the Agents SDK. Features real-time WebSockets, persistent state management, scheduled background tasks, and native tool integration for production-ready deployments.
Guided, systematic feature development agent that orchestrates codebase exploration, architectural design, implementation, and automated testing.
A standardized template for creating and documenting modular Agent Skills to ensure consistent, efficient context engineering across AI agent systems.
Sends debugging data, logs, and visual output to the Ray desktop application via its local API for real-time developer feedback.