Configure environment variables and project settings using mise [env] as the single source of truth. Use whenever the user needs to set up mise.toml, centralize environment…
Choose, review, or refactor project profiles that map mise tools to ecosystem-specific reference sets.
Author, review, or refactor a project's mise `[tools]` section, tool selectors, backends, and lock strategy.
Use when designing the exhibits for a MIS Quarterly manuscript — measurement/correlation and structural-model tables for behavioral IS, regression and robustness tables for…
Route 3D visual-regression and render-diff work through Mission Control with explicit evidence targets and scene-aware validation.
Use when CUDA Tile or tile-shaped GPU refactors need Mission Control planning, validation, and benchmark discipline.
Generate an operational runbook through Mission Control. Use when the user wants RUNBOOK.md or a chat-native runbook covering startup, tests, build, debugging, local reset, logs,…
Switch Mission Control toward local-first behavior. Use when the user wants local files, local models, no cloud deployment, and no external APIs unless explicitly approved.
Run a safe Mission Control refactor workflow. Use when the user wants non-trivial refactors that need codebase understanding, snapshots, path locks, contracts, validation…
Review Mission Control testing coverage and status. Use when the user wants to know what tests exist, what ran, what failed, what was skipped, or where validation coverage is…
Request a Mission Control snapshot or restore point before risky work. Use when the user wants rollback safety before refactors, broad edits, or uncertain changes, preferably…
Use Mission Control to design or repair tf.data pipelines with explicit throughput, caching, and validation evidence.
Route TensorFlow Lite export and edge-readiness checks through Mission Control with explicit artifact and constraint validation.
Ask questions against Mission Control's codebase understanding. Use for architecture questions, where-is-this-handled, why-does-this-exist, and codebase Q&A grounded in the…
Plan or run web application testing through Mission Control. Use for local browser smoke tests, console errors, accessibility checks, screenshots, and regression validation.
Use when designing space missions, computing launch windows, optimizing trajectories, analyzing payload constraints, or planning mission phases and contingencies.
Log, analyze, and prevent recurring mistakes. Use when: (1) a mistake or near-miss occurs (self-detected or user-detected), (2) session start/end review of recent patterns, (3)…
List past mistakes engram has learned in this project — failures, regressions, broken assumptions. Use before starting a non-trivial change to surface relevant prior failures, or…
Configure Mistral AI CI/CD integration with GitHub Actions and prompt testing. Use when setting up automated testing, prompt regression suites, or integrating Mistral AI quality…
Diagnose and fix Mistral AI common errors and exceptions. Use when encountering Mistral errors, debugging failed requests, or troubleshooting integration issues.
Collect Mistral AI debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information…
Deploy Mistral AI integrations to Vercel, Docker, and Cloud Run platforms. Use when deploying Mistral AI-powered applications to production, configuring platform-specific secrets,…
Create a minimal working Mistral AI chat completion example. Use when starting a new Mistral integration, testing your setup, or learning basic Mistral API patterns.
Configure Mistral AI local development with hot reload, testing, and mocking. Use when setting up a development environment, configuring test workflows, or establishing a fast…
Execute migration to Mistral AI from OpenAI, Anthropic, or other providers. Use when migrating to Mistral AI from another provider, performing major refactoring, or re-platforming…
Configure Mistral AI across development, staging, and production environments. Use when setting up multi-environment deployments, configuring per-environment secrets, or…
Optimize Mistral AI performance with caching, batching, and latency reduction. Use when experiencing slow API responses, implementing caching strategies, or optimizing request…
Execute Mistral AI production deployment checklist and rollback procedures. Use when deploying Mistral AI integrations to production, preparing for launch, or implementing go-live…
Implement Mistral AI rate limiting, backoff, and request management. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for…
Implement Mistral AI reference architecture with best-practice project layout. Use when designing new Mistral AI integrations, reviewing project structure, or establishing…
使用 MistTrack OpenAPI 进行加密货币地址风险分析、AML 合规检测和交易追踪。MistTrack 是由 SlowMist 开发的反洗钱追踪工具，支持 BTC、ETH、TRX、BNB 等主流链上地址与交易的风险评分、标签查询、交易调查等功能。
Mitosis lets you write UI components once and compile them to React, Vue, Angular, Svelte, Solid, Qwik, and more.
Vovk.ts OpenAPI mixins — importing third-party OpenAPI 3.x schemas as typed client modules that share the same call signature as native Vovk RPC modules.
MixSeek Agent Skills collection for AI coding assistants. Provides workspace management, team configuration, evaluation setup, and debugging tools for MixSeek-Core.
MixSeek Agent Skills collection for AI coding assistants. Provides workspace management, team configuration, evaluation setup, and debugging tools for MixSeek-Core.
Run a Mixture of Experts (MoE) audit on any topic, plan, codebase, evidence archive, or process. Dynamically spawns specialized subagents with different critical lenses to…
MkDocs with Material theme expertise for Python-centric documentation. Configure navigation, plugins, multi-language support, PDF export, and advanced Material theme features.
Voeg een MkDocs Material documentatiesite toe aan een cedanl Python project en configureer GitHub Pages.
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
Prevents 30+ critical AI/ML mistakes including data leakage, evaluation errors, training pitfalls, and deployment issues.
Deep expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered…
Patterns for efficient ML data pipelines using Polars, Arrow, and ClickHouse. TRIGGERS - data pipeline, polars vs pandas, arrow format, clickhouse ml, efficient loading,…
Use when a model won't learn, loss is NaN, metrics look too good/bad, or training is unstable. Provides a systematic decision tree for diagnosing data, optimization, and…
Prepares ML models for production deployment with containerization, API creation, monitoring setup, and A/B testing.
Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.
Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.
Expert in building scalable ML systems, from data pipelines and model training to production deployment and monitoring.
Déploiement de modèles ML en production (MLOps). Se déclenche avec "déployer un modèle", "ML deployment", "MLOps", "model serving", "inference", "model registry", "ML pip — from…
Expert MLOps engineering covering model deployment, ML pipelines, model monitoring, feature stores, and infrastructure automation.
Build end-to-end ML pipelines with automated data processing, training, validation, and deployment using Airflow, Kubeflow, and Jenkins
Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment.
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment.
Use when the user wants an implementation plan, architecture design, or multi-step ML pipeline — "build X", "implement X", "design X", "set up X
Coaches end-to-end ML system design interviews covering inference pipelines, recommendation systems, RAG, feature stores, and monitoring.
A Principal ML Engineer interviewer that simulates a FAANG-style ML system design interview covering the full lifecycle from data to production.
Use when the user wants to verify code, config, or math before running — or proactively before any expensive training job or deployment
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback.
MLflow experiment tracking via Python API. TRIGGERS - MLflow metrics, log backtest, experiment tracking, search runs.
Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples. — from NVIDIA/skills
Design and implement ML operations — model registry, serving patterns, deployment strategies (shadow/canary/blue-green), drift detection, feature stores, retraining triggers, and…