Skill UI

Provides comprehensive, programmatic control over tmux sessions. Users can list, capture output from, send specific keystrokes, and programmatically navigate panes/windows in remote, long-running interactive CLI sessions. Essential for monitoring AI code generation tools (like Claude/Codex) or managing complex multi-terminal workflows via scripting.

This module provides a comprehensive catalog of abstractions and utilities for handling API webhooks within the Webiny framework. It covers essential components such as payload types (IWebhookPayload), domain models (Webhook), delivery mechanisms, and core services like WebhookDispatcher and WebhookFactory. It supports advanced features including event routing, data validation, and secure payload signing, making it ideal for backend integration development.

This workflow systematically analyzes deployed AWS resources and Infrastructure-as-Code (IaC) definitions. It collects usage metrics from CloudWatch and Cost Explorer to identify over-provisioning, unused resources, and inefficient configurations (e.g., right-sizing EC2, S3 lifecycle policies). It generates actionable cost optimization recommendations and creates structured GitHub issues for tracking and implementing savings.

A comprehensive minimal terminal coding harness designed for building, extending, and integrating advanced AI capabilities directly into CLI environments. It supports deep integration via SDK (Node/TypeScript), RPC, and JSON event streams. Developers can create custom skills, providers, TUI components, and utilize advanced features like web search, video understanding, and agent orchestration.

Unship is a local development workflow designed to allow users to compare multiple temporary UI alternatives (variants) generated by AI coding agents directly within a running application's source code. It injects temporary source-level variants and provides a local browser picker for judgment. After the user selects a winner, it cleans up the losing code, ensuring a clean codebase before shipping. This tool is for local iteration, not production A/B testing or analytics.

An interactive skill designed to guide users through the process of generating, auditing, and improving Best Practice Analyzer (BPA) rules for Power BI semantic models. It follows a double-diamond discovery process, first gathering deep organizational context and model details, and then recommending tailored rules for validation, governance, and compliance.

This skill provides expert guidance on writing and executing C# scripts to deeply manipulate Power BI semantic models. It allows users to perform bulk operations, manage security roles (RLS/OLS), format DAX expressions, and query model metadata via the TOM API, supporting both Tabular Editor 2 and 3 environments for advanced data engineering tasks.

This skill provides a comprehensive, step-by-step workflow for generating complete Power BI reports from scratch. It guides the user through model discovery, KPI selection, page layout, visual placement, data binding, and publishing, offering rich control over the entire reporting lifecycle using the pbir command-line interface.

This skill provides expert, developer-level guidance on the Power BI Project (PBIP) file format. PBIP deconstructs the opaque PBIX binary into human-readable, structured text files, enabling robust source control, external editing, and multi-author collaboration. It covers project structure, the difference between thick and thin reports, file conversion (PBIX to PBIP), and critical cross-cutting concerns like rename cascades and data location discrepancies across various report components.

This guide provides a comprehensive workflow for managing the refresh lifecycle of semantic models and datasets in Power BI/Fabric. It details how to use the enhanced REST API and Fabric CLI to trigger specific refresh types (e.g., full, dataOnly, calculate), validate data baselines, monitor status, and handle post-refresh validation, ensuring data integrity and proper pipeline orchestration.

This skill provides a comprehensive reference for the Tabular Editor 2 (TE2) command-line interface. It covers connecting to local files, remote XMLA endpoints (like Power BI/Analysis Services), executing scripts, deploying models, and running Best Practice Analysis (BPA). It is designed for automating data model deployment and managing CI/CD pipelines in Windows environments.

This advanced tool surfaces critical, often unrecorded, evidence of human-AI collaboration during development sessions. It analyzes git diffs and conversational context across multiple layers to classify the signal level (HIGH/MEDIUM/LOW), measure technical complexity, detect decision forks, and quantify the specific contribution of the AI model, providing structured data for post-session retrospectives and accountability.