Browse all
Advanced financial risk assessment for AI agents
This skill quantifies downside financial exposure using advanced techniques including Monte Carlo simulation, Bayesian inference, and convergence analysis. It allows agents to calculate metrics like Value at Risk (VaR) and Conditional VaR (…
Optimal pathfinding through complex task workflows
This tool implements A* pathfinding to determine optimal task sequences through complex dependency graphs. It supports finding the K-shortest paths while allowing cost, time, or risk to be used as configurable heuristics.
Time Series Forecasting with ARIMA and Holt-Winters
This tool provides robust time series forecasting, utilising both ARIMA and Holt-Winters exponential smoothing methods. It predicts future values, such as revenue or traffic, while providing associated 95% confidence intervals for enhanced …
Decision Intelligence for AI Agents
Enables agents to perform strategic decision analysis using graph-based dependency mapping and convergence scoring. It facilitates identifying critical paths, detecting information conflicts, and optimising choices through bandit and contex…
Genetic Algorithm for Multi-Objective Optimization
This agent uses Genetic Algorithms to find optimal solutions for complex, multi-objective problems, handling nonlinear and discontinuous search spaces where traditional linear solvers fail. It returns the best chromosome and the Pareto fron…
multi-model consensus for agent predictions
This tool generates a mathematically optimal consensus prediction by aggregating outputs from multiple LLMs or models. It automatically weights contributions based on historical accuracy and calculates entropy to measure model disagreement.
State-of-the-art continuous optimization engine
This tool implements CMA-ES, a highly sample-efficient, derivative-free optimizer ideal for tuning continuous parameters or calibrating black-box functions. It excels where traditional gradient-based methods fail, such as hyperparameter tun…
AI-Powered A/B Testing and Feature Optimization
An optimization tool for AI agents that implements Multi-Armed Bandits and Contextual Bandits to automate A/B testing and feature selection. It enables context-aware decision-making by analysing historical rewards and feature vectors withou…
Predicting accuracy and source convergence for agents
This tool assesses the accuracy of past predictions using metrics like the Brier and log scores, and it quantifies multi-source agreement to identify consensus probability and potential outlier sources.
Bayesian Belief Updating for AI Agents
This skill implements Bayesian inference, allowing agents to refine initial beliefs (priors) by systematically incorporating multiple weighted evidence sources. It calculates a posterior probability, enabling robust, multi-factor prediction…
Statistical Anomaly and Outlier Detection Tool
This tool provides robust statistical methods for detecting outliers in data streams or static datasets. It supports both Z-score analysis, ideal for normally distributed metrics, and IQR analysis, which is more robust for skewed data.
Vizro Chart Selection and Configuration
Provides guidelines for selecting appropriate chart types, applying Plotly Express conventions, and configuring colours or KPI cards within Vizro dashboards. It includes instructions for implementing custom charts using the @capture decorat…
Vizro YAML Configuration and Component Reference
Provides comprehensive guidance for constructing and debugging Vizro YAML dashboard configurations. It covers component syntax, data management, custom function wiring, and advanced table setups like AG Grid.
Vizro Dashboard Layout Design Guidelines
Provides comprehensive best practices for structuring Vizro dashboards, covering 12-column grid configuration, optimal component sizing, and strategic placement of filters and selectors. It guides developers on maintaining visual hierarchy …
Vizro Dashboard Design Workflow
A structured three-step workflow for planning Vizro dashboards through requirements gathering, layout design, and visualisation selection. It utilises YAML spec files to document architectural decisions and ensure a consistent transition to…
End-to-end Vizro dashboard development and testing
This skill orchestrates the end-to-end development of Vizro dashboards, accepting design specifications to build, validate, and test complex data applications. It manages code implementation, schema fetching, and critical browser automation…
Design System Component Extraction Skill
This skill enables the extraction of HTML, theme information, and component details from design systems such as Storybook. It facilitates UI assembly by listing, searching, and analysing available components and their variants.
Automated Discovery of Novel Data Patterns
Disco systematically discovers novel, statistically validated patterns and feature interactions within large tabular datasets. It validates findings using FDR-corrected p-values and cross-references results against academic literature, retu…
Deep Codebase and Infrastructure Audit Skill
This skill manages the lifecycle of the OathScore project by loading comprehensive session state and executing a deep, multi-point audit. It cross-references code, configuration, and live APIs to detect critical bugs, stale URLs, and infras…
Persistent, Consensus-Validated Memory for AI Agents
This tool provides a local, persistent knowledge layer for agents, ensuring memories undergo BFT consensus validation and decay over time. It allows agents to recall context, track tasks, and maintain continuity across sessions without rely…
Zero-Trust Session Guardian for Agent Workflows
This skill executes a comprehensive, zero-trust audit at the start and end of every session, ensuring system integrity by cross-referencing environment variables, hardcoded URLs, and scheduler wiring against live API endpoints. It manages s…
Deep forensic audit of codebase integrity
This skill performs an exhaustive, forensic audit of the entire codebase, verifying source integrity, import chains, and configuration alignment. It systematically checks for discrepancies across code, environment variables, and external AP…
Zero-API-Key Web Search and Verification Tool
This comprehensive tool provides a structured workflow for source-backed research, enabling multi-engine search, deep page browsing with anti-blocking features, and evidence-aware claim verification. It outputs citation-ready reports, suppo…
Zero-API-Key Web Search and Evidence Verification
This tool facilitates a comprehensive, source-backed verification workflow, enabling multi-engine search and deep page reading. It supports evidence-aware claim checking and generates citation-ready reports, offering both free and professio…