A time-boxed diligence sprint (3-7 days) with daily deliverables and decision gates. Burns down top 4 risks and produces IC-ready evidence. Use when a deal is live and you need speed without losing rigor.

Master Directus backend internals: API extensions, hooks, flows, services, and database operations

**Purpose:** Marketing attribution and promo code ROI tracking

>

Distributed systems tools including NATS messaging, libp2p networking, and Temporal workflows

Use when planning channel distribution and measuring video performance.

Guide for Direct Memory Access (DMA) attack techniques using FPGA hardware. Use this skill when researching PCIe DMA attacks, pcileech, FPGA firmware development, or hardware-based memory access for game security research.

DNS load balancer with DoS protection, multi-protocol support (DoH, DoT, DoQ), and dynamic traffic management

>

>

Create optimized Dockerfiles with multi-stage builds, security hardening, layer caching, and health checks. Includes docker-compose patterns for development and production environments.

Auto-activates when user mentions Docker, containerize, Dockerfile, docker-compose, or container setup. Creates optimized Docker configurations for applications.

Comprehensive Docker containerization for Python/FastAPI applications from development to production deployments. Use when Claude needs to containerize Python/FastAPI applications with proper multi-stage builds, production-ready configurations, security best practices, and optimized Docker images for deployment to cloud platforms or container orchestration systems.

Initialize Docker environment with Dockerfile, compose config, and .dockerignore

Expert guidance for Docker containerization and Kubernetes orchestration. Use when containerizing applications, managing multi-container setups with Docker Compose, or deploying to Kubernetes clusters.

Secure Docker containers and images with hardening, scanning, and secrets management

Learn Dockerfile fundamentals and best practices for building production-ready container images

Build optimized, secure, and cache-efficient Docker images following production best practices.

Documentation usage analytics and insights. Integrate with Google Analytics, Algolia analytics, and custom tracking to measure documentation effectiveness, identify content gaps, and optimize user journeys.

Navigate hierarchical ai-docs indexes to find documentation. Check local docs FIRST for speed and curated context before web searching. Covers Claude Code, BAML, MCP, and other tracked libraries.

slurp-ai scrapes documentation websites and compiles them into a single markdown file optimized for AI agent context. It is lightweight, fast, and deterministic - it does NOT use AI to scrape, it is F

Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理

Oxford Nanopore basecalling with Dorado on University of Michigan HPC clusters (ARMIS2 and Great Lakes). Use when running dorado basecalling, generating SLURM jobs for basecalling, benchmarking models, optimizing GPU resources, or processing POD5 data. Captures model paths, GPU allocations, and job metadata. Integrates with ont-experiments for provenance tracking. Supports fast/hac/sup models, methylation calling, and automatic resource calculation.

Find denial of service vulnerabilities through resource exhaustion, algorithmic complexity, memory exhaustion, and file/network resource abuse. Use when auditing code for availability issues.

Creates hybrid Native AOT + CoreCLR .NET 10 tool packages using ToolPackageRuntimeIdentifiers. Use for building high-performance CLI tools with Native AOT on supported platforms and CoreCLR fallback for universal compatibility.

dpo

Implement fluid drag-and-drop interactions with physics-based animations.

You are an expert in oil and gas drilling logistics and upstream supply chain management. Your goal is to help optimize the complex logistics of drilling operations, from rig mobilization to well comp

Drizzle ORM configuration and patterns. Use as a lightweight alternative to Prisma.

REQUIRED Phase 2 of /ds workflow. Profiles data and creates analysis task breakdown.

Compose complex DSPy programs using the Ensemble optimizer, MultiChainComparison for reasoning synthesis, and sequential module patterns.

Systematically evaluate DSPy programs using built-in and custom metrics with parallel execution.

Distill a DSPy program into fine-tuned model weights for efficient production deployment.

Optimize complex agentic systems using LLM reflection on full execution traces with Pareto-based evolutionary search.

Jointly optimize instructions and few-shot demonstrations using Bayesian Optimization for maximum performance.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

Build retrieval-augmented generation pipelines with ColBERTv2 that can be systematically optimized.

Optimize DSPy programs using mini-batch Bayesian optimization with statistical analysis of feedback signals.

Analyze AWS Application Load Balancer (ALB) logs stored in S3 using DuckDB. Use when users request ALB log analysis, error investigation, performance analysis, traffic analysis, or need to query ALB access logs. Supports analyzing response times, status codes, error patterns, and traffic trends from S3-stored logs.

Fast in-process analytical database for SQL queries on DataFrames, CSV, Parquet, JSON files, and more. Use when user wants to perform SQL analytics on data files or Python DataFrames (pandas, Polars), run complex aggregations, joins, or window functions, or query external data sources without loading into memory. Best for analytical workloads, OLAP queries, and data exploration.

Dynamically scale model token budgets using resource telemetry, prompt size, and profile presets. Use when token limits must adapt to hardware constraints, per-request size, or safe/fast/quality modes.

You are an expert in dynamic lot-sizing models for non-stationary inventory systems with time-varying parameters. Your goal is to help optimize inventory replenishment decisions when demand, costs, or

Implement dynamic resolution scaling for React Three Fiber / Three.js by adjusting DPR based on measured FPS. Use when asked to add adaptive performance scaling, automatic DPR tuning, or a DynamicResScaler-style component in a R3F scene.

AWS DynamoDB NoSQL database for scalable data storage. Use when designing table schemas, writing queries, configuring indexes, managing capacity, implementing single-table design, or troubleshooting performance issues.

Control Dyson air purifiers, fans, and heaters via local MQTT. Use when asked to control Dyson devices, adjust fan speed, set temperature/heat, enable oscillation, or check room temperature/humidity. Requires being on the same WiFi network as the device.

EAS Build configuration for iOS and Android. Use when setting up cloud builds.

Expert on EAS Build cloud service for building iOS and Android apps. Covers build configuration, credentials management, custom builds, CI/CD integration, and troubleshooting. Invoke when user mentions EAS Build, cloud builds, app compilation, build workflows, or iOS/Android binary creation.

Create and use iOS simulator development builds with EAS for Expo/React Native apps. Use when setting up simulator-only profiles, building, installing, and running dev clients on iOS simulators.

You are an expert in e-commerce fulfillment operations and direct-to-consumer logistics. Your goal is to help online retailers optimize order processing, warehouse operations, shipping strategies, and