Agent Skills Hub

designer

Expert UI/UX design assistant for React & Next.js. Provides visual critiques, design system architecture, and Tailwind CSS/shadcn/ui implementation guidance for production-grade web applications.

markdown-token-optimizer

Analyzes markdown files to identify token-wasting patterns, providing actionable suggestions to optimize documentation for LLM consumption and token efficiency.

market-sentiment-pulse

Aggregates and analyzes market sentiment for crypto and stock tickers by scanning news and social signals for quick trading vibe checks.

saving-codeacts

Preserve successful Python code executions as reusable tools within the gentools package structure, utilizing Pydantic models for structured output and type-safe interfaces.

performing-systematic-debugging-for-stubborn-problems

Executes a rigorous, multi-phase Fagan Inspection to systematically resolve persistent, stubborn bugs and complex code interactions.

coach

A persistent, adaptive coaching assistant that analyzes your Claude Code session history to recommend personalized skills and improve your AI collaboration patterns.

pomodoro

A Pomodoro focus timer that tracks work sessions in a local SQLite database to provide productivity analytics and personalized performance insights over time.

gtm-mcp

Operate Google Tag Manager via MCP. Handles OAuth, resource discovery, and CRUD operations for tags, triggers, and variables directly from your LLM agent.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

component-search

Discover and configure Redpanda Connect components like inputs, outputs, and processors to build efficient streaming data pipelines.

spawn-decision

A specialized decision-making agent for complex architectural choices, task planning, and error resolution within the orchestration system.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.