Skill UI

This guide provides detailed best practices for ensuring the reproducibility of advanced AI research across various domains, including algorithms, theories, multi-agent systems, and datasets. It outlines the specific evidence required—from pseudocode and seeds to full proofs and public datasets—to elevate a submission's credibility rating from 'irreproducible' to 'convincing' for top-tier AI conferences.

A comprehensive guide for authors targeting the International Conference on Autonomous Agents and Multiagent Systems (AAMAS). This skill helps authors strategically position their work by focusing on core themes like autonomous agents, multiagent learning, game-theoretic interaction, and decentralized decision-making. It covers submission framing, evidence requirements, and risk assessment to ensure manuscripts align with the venue's technical focus.

This guide provides a rigorous framework for developing robust, theory-driven hypotheses in accounting research, especially for high-impact academic journals. It teaches researchers how to transition from observing mere correlations to formulating hypotheses grounded in established economic theories, such as agency theory, information economics, and positive accounting theory. The process emphasizes identifying the core economic friction, naming the acting agents and their incentives, and deriving directional, falsifiable, and a priori predictions.

This guide outlines the rigorous method for developing econometrically testable hypotheses for accounting research, particularly for high-tier journals. Instead of relying on vague constructs, it teaches how to ground predictions in core economic theories like information economics, agency theory, and contracting frictions. It helps researchers build a clear mechanism by specifying the agent's optimization problem, identifying the core friction, and deriving conditional, testable predictions.

A guide for formalizing complex institutional arguments into rigorous, testable economic models, specifically tailored for submission to top journals like JLEO. It covers foundational lineages—such as transaction-cost economics, property rights, and principal-agent problems—teaching researchers how to right-size models, justify assumptions institutionally, and ensure comparative statics are the primary deliverable for empirical testing.

A comprehensive guide to ensure scientific manuscripts meet the highest standards of reproducibility. It mandates documenting the deposition of all necessary data (e.g., GenBank, PDB, GEO), archiving custom analysis code with DOIs (e.g., Zenodo), and detailing sharing plans for unique reagents and materials. Crucial for primary data underlying research conclusions.

webmcpify is a specialized pipeline designed to make existing web applications agent-ready. It extracts user-facing functionality and exposes it as WebMCP tools, allowing AI agents to interact with the application via structured, reliable tool calls rather than fragile DOM scraping. The tool guides developers through detection, inventory, integration, verification, and healing phases to ensure robust AI interoperability.

A comprehensive guide for building AI agents in Dart with Genkit, covering flows, tools, plugins, schemas, and the Genkit CLI for local development. Ideal for integrating LLMs into Dart or Flutter applications.

Performs comprehensive, two-layer validation on generated plans. Layer 1 executes instant structural checks (format, dependencies, compliance) while Layer 2 triggers specialist agents (e.g., security, DB, performance) based on plan content. The system forces resolution of all identified issues before allowing execution, supporting auto-fixes and guided human input.

An interactive wizard designed to help developers identify the optimal architectural pattern (Agent, Command, Skill, Hook, or Rule) for a new automation or feature. By asking a series of guided questions regarding trigger, complexity, and scope, it diagnoses the best fit and generates a complete, ready-to-use template (scaffold) for immediate development.

This skill manages the complex, multi-step workflow for updating the company's threat intelligence database. It delegates the core research and content updates to the dedicated AgentSec system. The process involves reading AgentSec's source material, executing rigorous testing in an isolated workspace, synchronizing the validated security feed, and finally ensuring data integrity by validating the updates across the guide and landing mirrors.

This guide outlines the full workflow for integrating Microsoft Copilot Studio agents into a Power Apps code application. It covers checking the memory bank, adding the connector via CLI, configuring the agent setup, and executing the agent asynchronously using the reliable API endpoint.