Agent Building Agent Skills

Create new skills, modify existing ones, and measure their performance through iterative evaluation and benchmarking.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Create a new AgentHub collaboration session with task, agent count, and evaluation criteria for multi-agent competitions.

Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.

Merge the winning agent's branch into the base branch, archive losing branches via git tags, and clean up worktrees after an AgentHub competition session.

Design multi-agent system architectures, generate tool schemas for Anthropic and OpenAI formats, and evaluate execution logs for cost, latency, and failure bottlenecks.

Display DAG state, agent progress, and branch status for an AgentHub session.

Spawns multiple parallel AI agents that compete on the same task using isolated git worktrees, evaluates results, and merges the best solution.

Defines an inter-agent communication protocol for C-suite agent teams, including invocation syntax, loop prevention, isolation rules, and response formats to coordinate cross-functional analysis and board meetings.

Optimizes agent context setup by structuring rules, specs, source files, error output, and conversation history to improve output quality.

Guides usage of the Gemini API on Agent Platform with the Google Gen AI SDK, covering SDK usage (Python, JS/TS, Go, Java, C#), capabilities like multimodal inputs, tools, media generation, caching, batch prediction, and Live API.

Manage custom Agent resources on the Gemini Enterprise Agent Platform via REST API, including creation, configuration, listing, updating, and deletion with support for files, skills, and tools.

Authenticate, initialize, and use the stateful Gemini Interactions API for multi-turn conversations, streaming, structured output, and function calling on the Gemini Enterprise Agent Platform.

Authenticates and connects to Google Cloud Agent Platform for inference with Gemini and third-party OpenMaaS models (Llama, DeepSeek, Qwen). Generates code for multiple SDKs, configures endpoints, and troubleshoots common errors.

Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology, including dataset creation, metric selection, failure analysis, and iterative improvement.

Sets up Google's agents-cli toolkit and guides through the full agent development lifecycle: scaffold, build, evaluate, deploy, publish, and monitor on Gemini Enterprise Agent Platform.

Configures dynamic threshold alerting policies for Google Cloud Vertex AI Agent Platform agents, monitoring latency, error rates, and quality metrics using Terraform and PromQL.

Manages Agent Platform serving endpoints: create, list, describe, update, delete, and troubleshoot permission, quota, and resource busy errors.

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK.

Search models, datasets, Spaces, and papers on the Hugging Face Hub, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools via the Hugging Face MCP server.

Run state-of-the-art machine learning models directly in JavaScript/TypeScript across browsers and server-side runtimes using Transformers.js.

Track and visualize ML training experiments with Trackio, including logging metrics, firing alerts, and retrieving data via CLI. Supports real-time dashboards, webhook alerts, and HF Space syncing.

Build ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.

Creates reusable command-line scripts and utilities for the Hugging Face API, enabling chaining, piping, and intermediate data processing.

Publish and manage research papers on Hugging Face Hub, including creating paper pages, linking papers to models and datasets, claiming authorship, and generating professional markdown-based research articles.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.

Watch, audit, and fix another agent's work by reconstructing the original request, inspecting evidence, and reporting gaps.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Orchestrate expensive frontier models as reviewers and cheaper subagents for bounded, token-heavy work to optimize cost and quality.

Build applications that programmatically interact with GitHub Copilot using the Copilot SDK, supporting session management, custom tools, streaming, hooks, MCP servers, and deployment across Node.js, Python, Go, and .NET.

Guides the creation of high-quality MCP servers that enable LLMs to interact with external services through well-designed tools, covering planning, implementation, testing, and evaluation across multiple programming languages.

Implements a continual learning loop for AI coding agents using hooks, two-tier memory (global and local), and automatic pattern detection to persist and apply learnings across sessions.

Configure Azure API Management as an AI Gateway to govern AI models, MCP tools, and agents with policies for caching, rate limiting, content safety, and cost control.

Deploy, evaluate, fine-tune, and manage Microsoft Foundry agents end-to-end using Azure Developer CLI and MCP tools.

Manage Azure AI Foundry projects, connections, datasets, indexes, and evaluations using the Java SDK.

Build AI applications on Microsoft Foundry using the Azure AI Projects Python SDK, including agent creation, tool integration, thread management, and evaluation.