Skill UI

An interactive workflow designed to audit and standardize naming conventions within Power BI semantic models stored as TMDL files. It ensures that tables, columns, measures, and display folders adhere to consistent, human-readable, and business-aligned standards. The tool guides users through gathering critical business context before auditing and applying complex, cross-file reference updates to maintain data integrity.

Provides expert guidance for authoring and editing Tabular Model Definition Language (TMDL) files directly within PBIP projects. This skill is useful for making quick text-level fixes (like descriptions, format strings, or adding measures) when specialized tools (like Tabular Editor CLI or Power BI Desktop) are unavailable, especially for Git workflow or manual adjustments.

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.

This tool guides users through the critical process of designing experiments *before* data collection. It helps select appropriate structures—such as factorial, crossover, or blocked designs—to ensure that collected data is interpretable and allows for robust causal inference. Use it when planning scientific studies, assigning subjects, or optimizing responses across multiple factors.

A dedicated tool for querying Lark Meeting Notes (Notes) details and raw verbatim transcripts. It requires an explicit note_id to function, allowing users to determine the display type, access associated document tokens, and retrieve the original unified transcript. It strictly focuses on note-based retrieval and does not handle searching by title, document body, or meeting ID.

This Main Agent acts as a central orchestrator for a specialized squad of AI agents, managing complex software development lifecycles. It guides projects through defined phases—from requirements gathering and planning to architecture, implementation, testing, and deployment. It maintains strict context discipline by summarizing agent outputs and referencing full artifacts, ensuring efficient, structured, and non-overwhelming communication to the user.

This skill implements Autonomous Optimization (AO) using Hypothesis Tree Refinement (HTR). It iteratively improves concrete artifacts (like code, models, or data pipelines) by running structured, long-term experiments against a measurable objective. It maintains a persistent hypothesis tree, coordinating subagents to test hypotheses in isolation while using a held-out test evaluator to prevent overfitting and ensure reliable, cumulative research progress. Ideal for complex benchmark tuning, agent refinement, or optimizing entire workflows.

This guide helps developers audit and clean up Vite + React projects initialized using the Lovable scaffolding tool. It systematically removes all boilerplate artifacts, including placeholder assets, dedicated dependencies (like lovable-tagger), generated documentation, and unnecessary components (e.g., unused Radix deps). The goal is to deliver a clean, fully owned, and production-ready codebase.

A structured, multi-phase skill that systematically audits and provides actionable fixes for all four Lighthouse pillars: Performance, Accessibility, Best Practices, and SEO. It analyzes Core Web Vitals, render-blocking resources, security headers, and ARIA compliance to significantly boost site speed and quality.

A crucial post-hoc review skill designed for AI-generated Markdown prose. It audits content against a comprehensive set of 21 stylistic and structural rules using both deterministic mechanical checks and deep semantic judgment. Users can audit a single file to get a detailed scorecard, or compare two drafts (A/B) for regression testing. Furthermore, it can optionally generate a polished, revised copy in a separate file, ensuring the integrity of the original document while significantly improving linguistic quality and adherence to style guides. Ideal for refining AI-written documentation, ...

A comprehensive guide detailing the selection criteria for core modern system components, including databases (SQL/NoSQL), caching, message queues, and API protocols. It helps architects choose the optimal technology for specific use cases, scalability needs, and architectural patterns.

This skill generates a complete React component structure following the industry-standard Container/Presentation pattern. It automatically scaffolds necessary files, including TypeScript, Storybook, and SCSS styles, ensuring adherence to project conventions. Use this when building new, scalable components, allowing you to properly classify whether the component is UI-focused (Presentation) or logic-heavy (Container).