Skill UI

A guide for creating and maintaining the canonical `AGENTS.md` file. This skill enforces minimal, high-signal documentation, ensuring agents receive concise instructions regarding package management, file-scoped commands, and project conventions, while strictly omitting filler or obvious context.

This model provides an engineering operational framework for teams that leverage AI agents to generate large volumes of code. It shifts the focus from simple syntax to process quality, robust architecture design, rigorous testing, and systematic risk control, ensuring the development of highly stable and reliable systems in AI-assisted environments.

A comprehensive expert for deploying and scaling AI agents using AWS Bedrock AgentCore. This guide covers the full lifecycle of agent management, including service selection (Gateway, Runtime, Memory, Identity, etc.), deployment patterns, credential management, and advanced integration workflows required for enterprise-scale AI solutions.

This comprehensive guide details how to set up and configure AWS Machine Capability Platform (MCP) servers for advanced AI agent use. It provides two options: a Full AWS MCP Server (for API calls and documentation search) and a basic AWS Documentation MCP (for documentation search only). Instructions cover prerequisites, configuration methods (via JSON settings), necessary IAM permissions, and troubleshooting tips for seamless integration of AWS services into AI workflows.

This skill implements the BDI (Belief-Desire-Intention) architecture for advanced cognitive agent modeling. It allows agents to reason about context by transforming external knowledge (like RDF triples) into internal mental states (beliefs, desires, intentions) and vice versa. Key features include goal-directed planning, explainable reasoning chains, and T2B2T (Triples-to-Beliefs-to-Triples) flow, making it ideal for multi-agent systems and augmenting LLMs with formal cognitive structures.

An expert agent focused on enhancing code clarity, consistency, and maintainability. It simplifies complex code structures, eliminates redundant logic, and applies project-specific best practices, all while guaranteeing that the original functionality and behavior remain absolutely unchanged. Ideal for code reviews, cleanup tasks, or improving readability.

This pattern defines a robust, continuous loop structure for autonomous agents. It integrates crucial components like quality gates, evaluation harnesses, and explicit recovery controls. It guides complex workflows by defining decision paths (e.g., PR control, RFC decomposition) and includes strategies to mitigate common failure modes such as infinite loop churn or cost drift, ensuring measurable progress in autonomous systems.

This skill provides comprehensive operational controls for long-lived, cloud-hosted agent workloads. It manages the entire lifecycle—from deployment and scaling to observability and security. Features include detailed monitoring (logs, metrics, traces), safety controls (kill switches, least privilege), and robust change management processes (rollout, rollback, auditing). Ideal for mission-critical microservices and background agents.

This pattern addresses the fundamental limitation of context window size by treating the filesystem as a persistent, external memory. Agents can write large outputs, plans, or findings to files, offloading them from the active context. Instead of carrying all information, agents use targeted search and retrieval tools to load only the necessary context on demand, drastically reducing token bloat and improving performance over long, complex tasks.

This infrastructure provides a robust solution for running powerful AI agents in remote, sandboxed environments. It overcomes the limitations of local execution by ensuring unlimited concurrency, consistent environments, and collaborative features. Use this to build complex background coding agents, multi-client interfaces (e.g., Slack, Web), or scale agent workloads far beyond local machine constraints.

Use this command to set up a structured multi-agent collaboration environment within AgentHub. It allows you to define the core task, specify the required number of agents, and configure detailed evaluation criteria (metrics, directions, and commands) for both quantitative benchmarking and qualitative LLM judging. This is the starting point for any agent competition or complex AI workflow.

Production-grade toolkit that lets Claude Code agents scaffold Playwright configs, generate/review/fix end-to-end tests, migrate suites, sync with TestRail, and run BrowserStack reports.