Design and build production RAG (Retrieval-Augmented Generation) pipelines. Use when implementing document ingestion, chunking strategies, embedding selection, vector search, hybrid retrieval, reranking, or generation with grounding.
Use reasoning / thinking models (GPT-6 Astra, Claude Opus 5.5, DeepSeek R1, Gemini Thinking) effectively. Covers when to choose reasoning vs fast models, prompt patterns for reasoners, effort / thinking controls, structured outputs with reasoning, cost/latency trade-offs, and combining reasoners with fast models.
Design robust REST APIs with proper versioning, pagination, error handling, rate limiting, and documentation. Use when creating new API endpoints, designing resource naming conventions, implementing pagination or filtering, adding rate limiting, or documenting APIs with OpenAPI/Swagger.
Apply fundamental coding principles (SOLID, DRY, KISS) and structure projects for maintainability with clean architecture and separation of concerns. Use when refactoring, reviewing patterns, setting up project structure, or organizing modules.
Estimate and attribute cloud running cost for a proposed architecture before it is built. Use when writing an ADR options table, sizing a prototype, comparing managed versus self-hosted services, or answering "what will this cost to leave running". Produces a load-enveloped estimate with an idle-versus-active split…
Design database operations including migrations, indexing strategies, transactions, connection pooling, and ORM best practices. Use when creating database schemas, writing migrations, optimizing slow queries, configuring connection pools, or choosing between ORM frameworks.
Enforce infrastructure invariants at generation time, before any IaC is applied. Use when writing or reviewing Terraform, Bicep, or ARM, when a generated stack disables authentication or encryption, when resource names drift, or when a reviewer needs a mechanical pass over infrastructure code. Provides a rule catalog…
Evaluate and review whether a solution should be built with low-code/no-code platforms (Power Platform, Copilot Studio, Power Apps, Power Automate, Logic Apps, AppSheet, OutSystems, Mendix) or pro-code (custom code on Foundry, Agent Framework, .NET, Python, React, Azure Functions, AKS, etc.). Use when reviewing an…
Optimize application performance and scalability through async patterns, caching strategies, profiling, horizontal scaling, load balancing, and resource management. Use when diagnosing slow endpoints, implementing caching, profiling bottlenecks, planning system capacity, or designing stateless services.
Implement production security practices covering OWASP Top 10, input validation, injection prevention, and secrets management. Use when hardening applications against vulnerabilities, implementing authentication/authorization, managing secrets, configuring HTTPS/TLS, or conducting security audits.
Design, model, and operate Azure Cosmos DB workloads across Gremlin (Graph), NoSQL (SQL), and Mongo APIs. Use when modeling graph data with Gremlin, choosing partition keys, sizing RUs, configuring multi-region writes, securing with RBAC/managed identity, or implementing change feed and TTL. Strong focus on Gremlin…
Analyze structured data across CSV, JSON, SQL, and DataFrame workflows with exploration, transformation, and visualization. Use when exploring datasets with pandas/polars, running SQL queries on files with DuckDB, transforming data pipelines, or generating data visualizations.
Build data engineering, analytics, and ML/AI solutions on the Databricks Lakehouse Platform. Use when creating Delta Lake tables, writing PySpark notebooks, building DLT pipelines, managing Unity Catalog, orchestrating Databricks Workflows, tracking experiments with MLflow, or deploying using Databricks Asset Bundles.
Build data engineering and analytics solutions on Microsoft Fabric - Lakehouse, Warehouse, Spark notebooks, data pipelines, and semantic models. Use when creating Fabric Lakehouses, writing PySpark notebooks, building data pipelines, designing semantic models, or querying OneLake storage.
Build, configure, and validate conversational data agents on Microsoft Fabric Lakehouses using the Data Agent SDK. Use when creating Fabric data agents, configuring few-shot examples, managing Livy sessions, or validating agent responses against Lakehouse data.
Build time-series forecasting pipelines on Microsoft Fabric - data preparation, profiling, clustering, feature engineering, and model training. Use when implementing demand forecasting, training LightGBM/Prophet models, engineering time-series features, or deploying prediction pipelines on Fabric.
Build Power BI reports, semantic models, DAX measures, and data visualizations. Use when designing star schemas, authoring DAX calculations, creating Power Query (M) transformations, optimizing report performance, or deploying Power BI content.
Enforce WCAG 2.1 AA conformance on UX prototypes and shipped UI. Use when reviewing or building any user-facing surface that must pass an a11y audit -- prototypes in docs/ux/prototypes/, production components, or third-party-embedded views. Provides a mechanical checklist split by POUR principle plus reduced-motion…
Identify and prevent AI design slop in generated UI -- forbidden visual tells (purple/teal gradients, generic system emoji, soft pastel everything, fake metrics, hand-drawn cartoon humans, rounded-2xl-everywhere) and enforce honest placeholders. Use after generating any HTML/CSS prototype, marketing surface, or…
Extract and codify a brand specification from user-provided sources (URL, screenshot, PDF, existing app) into a deterministic brand-spec.md artifact. Captures palette, typography, voice, motion, and prohibited patterns so downstream design decisions can be defended against the real brand instead of invented from…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: