Skill UI

A specialized guide for authors aiming to submit to the Conference on Uncertainty in Artificial Intelligence (UAI). It provides expert advice on framing the core contribution—such as probabilistic reasoning, causal inference, and uncertainty modeling—and calibrating the manuscript for highly technical, statistical ML reviewers. Use this skill to refine your submission strategy, identify evidence gaps, and properly position your work relative to other top-tier AI venues like AISTATS and IJCAI.

A rigorous checklist and guide for conducting causal inference in development economics, specifically tailored to the high standards of top-tier journals like The World Bank Economic Review (WBER). It covers advanced econometric designs (RCT, DiD, RD, IV), focusing not just on estimation but on defining the estimand, addressing external validity, general equilibrium effects, and translating local findings into actionable policy recommendations.

This guide outlines the rigorous standards for establishing causal claims in development economics and social sciences. It covers robust quantitative methods (like DID, IV, RDD, RCT) and structured qualitative/mixed-methods approaches. The core principle is that the logical route from evidence to claim must be explicitly defensible and matched to the strength of the assertion, avoiding over-claiming.

This skill provides comprehensive norms for executing and reporting robust, reproducible data analysis in comparative, cross-national, or formal-empirical studies. It guides authors on honestly reporting uncertainty, ensuring statistical robustness, performing rigorous cross-national inference, and integrating qualitative evidence through triangulation to meet the demanding standards of top academic journals.

Statsmodels is Python's premier library for rigorous statistical modeling. It provides comprehensive tools for estimation, inference, and diagnostics across a wide range of statistical methods. Use this skill for advanced analysis, including linear regression (OLS, WLS), generalized linear models (Logistic, Poisson), and complex time series forecasting (ARIMA). Ideal for econometric studies and producing publication-ready results.

Utilize zero-shot NER to extract custom entity types (e.g., Drug, Symptom, Device) from complex clinical or biomedical text without requiring any labeled training data or fine-tuning. OpenMed wraps GLiNER/GLiNER2, allowing users to define labels on the fly. The workflow involves building a model index and then running inference via CLI or Python API, making it ideal for rapid prototyping or unstable schemas.

Provides a hardened FastAPI endpoint for OpenMed's core functionalities: clinical Named Entity Recognition (NER), Personally Identifiable Information (PII) extraction, and de-identification. Designed for self-hosted microservices, it handles inference requests, model lifecycle management, and supports dynamic batching, ensuring secure, on-device processing of sensitive clinical data.

This document outlines the canonical contract for deploying model inference services on Itô compute. It details the secure handoff process of an immutable serving manifest after a compute booking is verified. The process enforces multiple strict gates, including entitlement checks, manifest integrity validation, idempotency key usage, and final health checks, ensuring robust and reliable deployment of advanced AI models.

This tool is a deterministic formatter for generating the final delivery summary for academic papers (meta-paper-write). It accepts JSON inputs including paper contracts, compiled PDFs, and citation maps. It strictly reports only verified fields and consistent citation statistics, ensuring the output is machine-readable and never relies on LLM inference or prose counting.

This skill covers implementing service mesh patterns for AI inference traffic management using Istio or Linkerd. It includes configuring mTLS for security, setting up authorization policies for service accounts, managing egress for model endpoints, and implementing traffic splitting for canary releases and A/B testing. It ensures cross-cluster resilience and protects GPU-backed services from cascading failures without modifying application code.

Learn to orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using tools like Prefect, Airflow, or Dagster. This skill covers scheduling recurring tasks, managing dependencies between data preparation and model serving, and building reliable, observable workflows for production AI systems.

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