Skill UI

A comprehensive framework for rigorously testing and benchmarking LLM agents. It moves beyond simple pass/fail checks to assess complex behaviors, reliability metrics, and capability consistency across multiple runs. Ideal for production monitoring and identifying subtle failure modes in advanced AI agents.

This SDK provides comprehensive content moderation capabilities for Python applications using Azure AI. It allows developers to analyze text and images to detect harmful content across multiple categories, including hate speech, violence, sexual content, and self-harm. Key features include multi-severity classification, managing custom blocklists, and analyzing content from local files or URLs. Ideal for pre-moderating user-generated content (UGC) or AI outputs to ensure platform safety.

This SDK provides comprehensive content moderation capabilities for Python applications using Azure AI. It allows developers to analyze text and images to detect harmful content across multiple categories, including hate speech, violence, sexual content, and self-harm. Key features include multi-severity classification, managing custom blocklists, and analyzing content from local files or URLs. Ideal for pre-moderating user-generated content (UGC) or AI outputs to ensure platform safety.

This SDK provides a comprehensive Python client library for interacting with Azure AI Speech-to-Text services. It supports both real-time streaming transcription and robust batch processing of audio files. Users can leverage advanced features such as speaker diarization (identifying multiple speakers) and capturing precise timestamps, making it invaluable for automated meeting minute generation, podcast content processing, and live captioning solutions.

This SDK provides a comprehensive Python client library for interacting with Azure AI Speech-to-Text services. It supports both real-time streaming transcription and robust batch processing of audio files. Users can leverage advanced features such as speaker diarization (identifying multiple speakers) and capturing precise timestamps, making it invaluable for automated meeting minute generation, podcast content processing, and live captioning solutions.

A comprehensive toolkit for building production-grade AI agents focused on crypto business development. This skill guides users through the entire token listing lifecycle: autonomously discovering promising assets across multiple chains, applying a weighted 100-point scoring model, verifying safety via advanced wallet forensics, and managing outreach pipelines with necessary human oversight and LLM cascade patterns.

A sophisticated AI system that coordinates multiple specialized agents (e.g., Security Auditors, Performance Analysts, Architecture Specialists) to perform comprehensive, multi-perspective code assessments. It analyzes code context, manages state, and synthesizes conflicting insights to provide deep, holistic reviews for complex software projects.

A comprehensive toolkit for evaluating the performance of code generation models. It supports benchmarking against industry standards like HumanEval, MBPP, and MultiPL-E across multiple languages. Use this tool to quantitatively compare different LLM coding abilities and measure code synthesis quality using pass@k metrics.

Provides comprehensive guidance on building robust evaluation frameworks for complex agent systems. It addresses the inherent challenges of non-determinism and multiple valid paths, enabling systematic performance testing, validating context engineering choices, and measuring continuous improvements across multiple quality dimensions (e.g., factual accuracy, tool efficiency).

FAISS (Facebook AI Similarity Search) is a library designed for efficient similarity search and clustering of dense vectors. It supports indexing and searching on billions of vectors at scale, featuring GPU acceleration and multiple index types (Flat, IVF, HNSW, PQ) to balance speed and accuracy. It is essential for building high-performance, large-scale applications requiring fast k-NN retrieval or pure vector similarity matching, especially in fields like RAG and recommendation systems.

Gastown is a robust multi-agent orchestration system designed for Claude Code. It enables the simultaneous execution of multiple AI agents on complex projects. It manages the entire development lifecycle, from setting up workspaces and tracking work items (beads) to managing agent lifecycles (polecats/crew) and merging final code (Refinery). Use it when coordinating complex, parallel AI tasks.

Provides calibration-free weight quantization for LLMs down to 1-bit precision with multiple optimized backends, ideal for fast deployments with vLLM/HuggingFace and LoRA/PEFT fine-tuning without collecting calibration data.