Skill UI

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.

AKF is the native metadata format specifically designed for tracking AI-generated or AI-modified content. It allows users to stamp files (including DOCX, PDF, images, and code) with detailed trust scores, source provenance, and compliance metadata. This tool is essential for professional workflows requiring strict auditing, compliance assurance, and verifiable data lineage, especially concerning regulations like the EU AI Act, HIPAA, and SOX.

A governance skill designed to secure AI agent tool calls using advanced authorization policies. It implements Cedar policies to control which tools agents can access and under what conditions. Key features include running in 'Shadow mode' for safe observation, 'Enforce mode' for strict blocking, and generating cryptographically signed Ed25519 receipts to provide an immutable, tamper-evident audit trail for every policy decision.

Run open-source molecular design and structural biology tools on Tamarind Bio's managed cloud GPUs via REST API or MCP. Covers AlphaFold/Boltz/Chai structure prediction, RFdiffusion and ProteinMPNN design, antibody and nanobody engineering, DiffDock docking, binding affinity, MSA generation, and molecular dynamics — no local GPU setup needed.

Mint and verify tamper-evident signed receipts for consequential AI agent actions such as deploy, delete, pay, or grant access. Supports EU AI Act Art. 12 record-keeping with Ed25519 and post-quantum signatures, verifiable offline from the receipt alone.

An advanced system that analyzes coding sessions via hooks to extract atomic, confidence-scored behaviors called "instincts." It tracks patterns, allowing users to evolve these instincts into comprehensive skills, commands, or agents. V2.1 introduces project-scoped learning, preventing knowledge contamination between different codebases and improving development workflow efficiency.

A comprehensive guide for researchers designing and auditing NLP experiments for top-tier conferences. It covers establishing defensible baselines, ensuring evaluation breadth, performing rigorous statistical tests (significance, variance), controlling for data contamination, and structuring detailed functional error analysis. Essential reading for publishing reliable AI research.

A comprehensive guide detailing best practices for designing and auditing empirical evaluations of Large Language Models (LLMs). It addresses critical pitfalls such as data contamination, baseline unfairness, model version drift, and decoding parameter sensitivity, ensuring that published results are robust, reproducible, and scientifically sound for academic publication.

A comprehensive guide for structuring the empirical evidence section of top-tier NLP conference papers (e.g., EACL). It mandates rigorous controls, including fair baselines (tuned models, explicit LLM prompts), statistical significance testing (variance, CI), contamination checks, and detailed human evaluation protocols. Use this to elevate your research from mere assertion to scientifically audited proof.

A specialized downstream skill for analyzing security vulnerabilities in complex agentic systems. This tool is designed for red teaming and penetration testing, focusing on detecting prompt injection, retrieval poisoning, memory contamination, planner drift, and tool boundary abuse within multi-step LLM chains. Use when proving how untrusted inputs compromise system integrity.

Transcribe audio/video files into timestamped Markdown transcripts and optional LLM-generated executive summaries using local Whisper inference.