Skill UI

This skill scans a specified local directory, extracts essential metadata from the files, and builds a comprehensive, searchable index. It then securely uploads this generated index to a configured remote search service via HTTP, making local files discoverable across remote platforms.

A rigorous framework for making evidence-based estimates and forecasts when precise data is unavailable. It guides users to anchor predictions on base rates, articulate uncertainty using confidence intervals, and systematically update beliefs using likelihood ratios (prior to posterior) as new evidence arrives. Ideal for risk sizing, project timelines, and strategic decision-making.

An expert advisor for implementing, auditing, and achieving certification under ISO/IEC 42001:2023. This skill guides organizations (AI providers and users) through establishing an AI Management System (AIMS). It covers critical areas including AI risk assessment, AI impact assessments, responsible AI principles, governance framework setup, and preparing for formal ISO certification.

A read-only skill designed for deep analysis of Itô baskets and prediction market data. It allows users to index live basket catalogs, perform deterministic gap analysis by comparing a basket against user research or a watchlist, generate source-grounded market intelligence briefs, or draft non-executable planning worksheets. This tool is strictly observational and never advises, orders, or executes trades.

This skill analyzes local Q&A session JSONL files to produce a complete, auditable weekly report in Markdown format. It supports generating routine weekly summaries, comparing performance across consecutive time windows, and identifying key trends and risks. The output is a single, self-contained Markdown file designed to provide sufficient aggregates and structure for downstream documentation rendering (e.g., Feishu or whiteboards), without needing external data sources or APIs.

DataLad manages scientific datasets using Git and git-annex, handling large files efficiently by storing content remotely. It captures computational provenance for reproducible analysis, allowing users to clone, fetch, and publish datasets from repositories like OpenNeuro. Ideal for managing large data files and ensuring analysis reproducibility.

This skill performs pharmacokinetic and pharmacodynamic modelling, including non-compartmental analysis, compartmental fitting, and population PK. It helps derive exposure metrics, evaluate dosing regimens, and predict drug interactions using Python scripts. Suitable for analyzing concentration-time data and supporting clinical pharmacology workflows.

A comprehensive guide to building production-ready Apache Airflow Directed Acyclic Graphs (DAGs). This skill covers best practices for operators, sensors, testing, deployment, and designing robust data pipelines. Use this when orchestrating complex workflows, managing ETL processes, or ensuring reliable batch job execution in a production environment.

Triage Monte Carlo alerts interactively or build an automated workflow. Fetch, score, and troubleshoot alerts using MCP tools, design reusable stages, and move from manual review to scheduled automation.

A comprehensive skill for analyzing AWS spending patterns and identifying areas of waste. It provides actionable strategies to reduce cloud costs by detecting idle resources (like unattached EBS volumes or unused Elastic IPs), recommending Reserved Instances, and generating reports using AWS CLI and Cost Explorer data.

This skill guides the construction of robust, production-grade backtesting systems for financial trading strategies. It helps users systematically validate performance, avoid common biases (like look-ahead bias), and implement advanced techniques such as walk-forward analysis, ensuring reliable performance estimates before live deployment.

bdistill transforms AI interactions into a structured, queryable knowledge base. It extracts, structures, and quality-scores domain knowledge from both closed-source AI models (in-session) and local open-source models (via Ollama). Users can build comprehensive reference datasets, Q&A pairs, or generate structured training data for traditional machine learning, ensuring validated and exportable domain expertise.