Authentic Mexican cooking expert covering moles, salsas, tacos, and regional Mexican dishes

Rapidly build and launch micro-SaaS applications with best practices, monetization, and deployment

Interact with MicroPython boards via mpy-repl-tool to push files, execute code, and test MicroPython scripts. Use when working with MicroPython development, testing board functionality, or evaluating MicroPython code on hardware.

提供微服务分布式架构思考框架，涵盖服务拆分、通信机制、基础设施、治理策略、可观测性五大维度。当需要设计微服务系统、评审分布式架构、或需要全局视角审视服务边界与协同时使用。支持 DDD 领域建模、同步/异步通信、API Gateway、服务网格、熔断降级等分布式系统关键决策。

Creates interactive educational MicroSims using the best-matched JavaScript library (p5.js, Chart.js, Plotly, Mermaid, vis-network, vis-timeline, Leaflet, Venn.js). Analyzes user requirements to route to the appropriate visualization type and generates complete MicroSim packages with HTML, JavaScript, CSS, documentation, and metadata.

This skill analyzes diagram, chart, or simulation specifications and returns a ranked list of the most suitable MicroSim generator skills to use. It compares the specification against capabilities of all available microsim generators (p5.js, ChartJS, Plotly, Mermaid, vis-network, timeline, map, Venn, bubble) and provides match scores (0-100) with detailed reasoning for each recommendation. Use this skill when a user has a diagram specification and needs guidance on which MicroSim generator skill to use.

Utility tools for MicroSim management including quality validation, screenshot capture, icon management, and index page generation. Routes to the appropriate utility based on the task needed.

Expert guidance for Microsoft Fabric development using the Fabric MCP Server. Access Fabric public APIs, OpenAPI specs, item schemas, best practices, and OneLake file management. Use when working with Fabric workloads, Lakehouses, pipelines, semantic models, notebooks, or building Fabric integrations.

Generate MJ V7 prompts for all images in a page.

Configure and operate Midnight Network infrastructure including proof servers, indexers, and network endpoints. Use when setting up development environment, troubleshooting connections, or configuring deployments. Triggers on network, proof server, indexer, or testnet questions.

Migrate .env-only configuration to split secrets/config format

Migrate Python modules from SDR_stochastic research code to vrp-toolkit architecture. Use when migrating files from the old codebase structure to the new three-layer architecture (Problem/Algorithm/Data layers), refactoring paper-specific code into generic implementations, or converting research notebooks into educational tutorials.

Complete migration guide from Zod v3 to v4 covering all breaking changes and upgrade patterns

Specialized in database migrations and data seeding. Trigger this when creating tables, modifying schemas, or preparing initial data.

Expert guidance for writing database migrations using golang-migrate for the mediaz SQLite database. Covers migration creation, testing, rollback capability, data preservation, and mediaz-specific patterns. Activates when users mention migrations, schema changes, database alterations, or golang-migrate.

Эксперт по отслеживанию milestones. Используй для трекинга прогресса, critical path, статус-репортов и earned value.

Debug and troubleshoot Mini-Apps when they fail to load, build, or run. Covers build checks, browser console inspection, bridge issues, and asset routing fixes.

>

Setup and configure Minikube for local Kubernetes development

Manages local Kubernetes clusters using Minikube for development and testing. This skill should be used when setting up local K8s environments, enabling addons, configuring networking, and deploying applications locally. Use this skill for Phase IV local Kubernetes deployments before cloud deployment.

Optimal patterns for MiniMax MCP tools (web_search + understand_image)

Mise development environment manager (asdf + direnv + make replacement). Capabilities: tool version management (node, python, go, ruby, rust), environment variables, task runners, project-local configs. Actions: install, manage, configure, run tools/tasks with mise. Keywords: mise, mise.toml, tool version, runtime version, node, python, go, ruby, rust, asdf, direnv, task runner, environment variables, version manager, .tool-versions, mise install, mise use, mise run, mise tasks, project config, global config. Use when: installing runtime versions, managing tool versions, setting up dev environments, creating task runners, replacing asdf/direnv/make, configuring project-local tools.

This skill implements the miso feature-to-code workflow. When feature markdown files change, it automatically propagates those changes through the implementation chain: pseudocode → platform-specific

Execute a single task with Pathfinder/Builder/Inspector crew. Self-fetches work from Beads.

Convert PDFs to Markdown using Mistral OCR API with image extraction. Use when you need to extract structured text and images from PDFs, especially for scanned documents or documents with complex formatting. Outputs Markdown with embedded images.

Build mithril-cache for torch.compile caching. Use when implementing content-addressable storage, cache keys, eviction, or framework hooks.

Build mithril-checkpoint compression for PyTorch models. Use when implementing byte grouping, compression pipeline, or checkpoint I/O.

Build mithril-dedup for ML dataset deduplication. Use when implementing MinHash, LSH, clustering, or document I/O.

Component specifications, design patterns, and UI elements for the mixmi platform including TrackCard, grids, modals, and audio components

MkDocs Material documentation management. This skill should be used when writing, formatting, or validating documentation in docs/. Covers admonitions, Mermaid diagrams, code blocks with annotations, content tabs, navigation setup, and mkdocs testing. Always check project-specific docs at docs/dev/ai/skills/ and docs/dev/ai/agents/ for project-specific Claude skill and Claude agent documentation when available.

Deep expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered features.

ml-deployment-helper

Expert in building scalable ML systems, from data pipelines and model training to production deployment and monitoring.

Serve models with A/B testing, monitoring, retraining.

Automate ML workflows with Airflow, Kubeflow, MLflow. Use for reproducible pipelines, retraining schedules, MLOps, or encountering task failures, dependency errors, experiment tracking issues.

ml-pipeline-orchestrator

Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, or managing experiment tracking systems.

ML research for RAN with reinforcement learning, causal inference, and cognitive consciousness integration. Use when researching ML algorithms for RAN optimization, implementing reinforcement learning agents, developing causal models, or enabling AI-driven RAN innovation.

Domain-specific ML expert for NLP, Computer Vision, and Time Series. Text classification, NER, sentiment (BERT, transformers), image classification, object detection (YOLO, ResNet), and forecasting (ARIMA, Prophet, LSTM). Use for specialized ML domains.

End-to-end ML system design for production. Use when designing ML pipelines, feature stores, model training infrastructure, or serving systems. Covers the complete lifecycle from data ingestion to model deployment and monitoring.

>

Design DAG-based MLOps pipeline architectures with Airflow, Dagster, Kubeflow, or Prefect. Activates for DAG orchestration, workflow automation, pipeline design patterns, CI/CD for ML. Use for platform-agnostic MLOps infrastructure - NOT for SpecWeave increment-based ML (use ml-pipeline-orchestrator instead).

Comprehensive MLOps workflows for the complete ML lifecycle - experiment tracking, model registry, deployment patterns, monitoring, A/B testing, and production best practices with MLflow

Use the MIDI Markdown Compiler (mmdc) CLI for compiling MMD to MIDI, validating syntax, real-time playback with TUI, exporting to different formats (JSON, CSV, table), and managing device libraries. Use when the user wants to compile, validate, play, inspect MMD files, or work with device libraries.

Troubleshoot and debug MIDI Markdown (MMD) files including validation errors, timing issues, value ranges, syntax problems, and compilation failures. Use when the user encounters MMD errors, validation failures, unexpected behavior, or needs help diagnosing MMD issues.

Create custom MIDI device libraries for MIDI Markdown with aliases, parameters, and documentation. Use when the user wants to create device-specific aliases for hardware (guitar processors, synthesizers, effects units), document MIDI implementations, or build reusable command libraries.

Write MIDI Markdown (MMD) files with correct syntax, timing paradigms, MIDI commands, and advanced features like loops, sweeps, random values, and modulation. Use when the user wants to create or edit .mmd files, needs help with MMD syntax, is implementing MIDI automation sequences, or is troubleshooting MMD validation errors.

19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.

**Enterprise SPEC-First TDD Development Orchestration**

>-