bcastelino

Interactive guide for creating, scaffolding, and iterating on Agent Skills. Use when the user wants to build a skill, write a SKILL.md, generate frontmatter, define trigger phrases, validate, package, or distribute a skill.

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances. Use when applying for jobs, customizing resumes for different roles, or optimizing for ATS systems.

Download YouTube videos with customizable quality and format options. Use when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.

AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents. Use when designing or implementing AI agents.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ...

Production-grade AI engineering for LLM applications, RAG systems, and agent architectures. Use when building AI features, designing model integrations, or implementing AI safety and monitoring.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features. Use when building AI or ML systems.

AI product engineering covering LLM integration patterns, RAG architecture, prompt engineering, and production AI systems. Use when building AI-powered product features or shipping LLM applications.

Composes a multi-visual Power BI dashboard from already generated reports in the generated-reports folder. This skill should be used only when the user explicitly requests a dashboard combining visuals from previously generated reports. It copies visual.json files, validates semantic model consistency, excludes card/slicer/kpi visuals, arranges up to 4 visuals per page in a 2x2 grid, and saves the output to the generated-dashboards folder with a "Dash" suffix in the project name.

Source-agnostic adapter that introspects any data storage (SQL databases, cloud warehouses, Excel/CSV files, OData/REST APIs, SharePoint lists) and emits a normalized data-model.json describing tables, columns, types, and relationships. Use this skill at the start of the dashboard pipeline whenever the user has not provided a structured data model. It also emits a clarification question list when schema cannot be auto-discovered, and produces the source-specific M-Code / import block consumed by semantic-mapper.

Top-level entry point that turns a natural-language dashboard request into a complete Power BI Desktop Project (PBIP). This skill should be used whenever a user asks in plain English for a dashboard, report, or set of visuals without providing structured input. It introspects the data source, runs two explicit user-confirmation gates (data-model readiness and scaffold readiness), then orchestrates data-source-connector, query-to-pbip, theme-branding, and bi-dash-creator to produce the final dashboard.

Scaffolds a complete Power BI Desktop Project (PBIP) directory structure, assembles TMDL and report artifacts, validates the project integrity, and creates a distributable zip archive. Use this skill when all semantic model and report files are ready and need to be packaged into a valid PBIP. This is Stage 4 of the query-to-pbip pipeline.

Orchestrates the end-to-end conversion of a Databricks Genie Query into a Power BI Desktop Project (PBIP) with visuals. Use this skill when transforming a Genie SQL query or YAML metric view into a complete, openable Power BI project containing a semantic model (TMDL) and report visuals (PBIR). It coordinates four sub-skills in sequence — semantic-mapper, visual-selector, visual-generator, and project-packager — to produce a zipped PBIP artifact.

Translates a data model description into a Power BI TMDL semantic model. Accepts either (a) a Databricks Genie YAML metric view OR (b) a normalized data-model.json produced by data-source-connector. Use this skill whenever a query or data model needs to be converted into TMDL files (model, database, relationships, tables) for use in a Power BI Desktop Project. This is Stage 1 of the query-to-pbip pipeline.

Applies professional themes and corporate branding to a generated PBIP project. This skill should be used after the report files are written and before the final dashboard is delivered, to swap in a chosen theme JSON, register it in report.json, and optionally inject a logo and corporate color palette. Provides four built-in presets (corporate, modern, minimal, dark) and supports custom theme files.

Builds Power BI report visual JSON files in PBIR format, where each visual is a separate visual.json file inside its own directory. Also generates page.json, pages.json, report.json, version.json, and definition.pbir. Use this skill when generating the report layer of a PBIP project from a selected visual type and field mappings. This is Stage 3 of the query-to-pbip pipeline.