Claude Skills

This skill designs acoustic levitation systems using ultrasonic standing waves to trap small objects at pressure nodes. It covers transducer selection, wave formation, node calculation, and phased arrays for multi-axis manipulation. Use it for designing contactless handling in chemistry, biology, or materials science applications.

This skill generates a standards-compliant A2A Agent Card manifest (`agent.json`) to make your agent discoverable and interoperable within multi-agent systems. It defines the agent's capabilities, skills, authentication, and supported content types as a public contract. Use it when building, migrating, or integrating an agent that must work with other A2A-compliant agents and registries.

This skill enables Claude to perform rigorous, step-by-step derivations of formulas or theorems from first principles, explicitly justifying each step. It's designed for use cases like proving mathematical statements, verifying textbook results, or creating self-contained derivations for academic work. Key features include checking special cases and building upon established axioms or theorems with logical deduction.

This skill automates deploying a Next.js application to Vercel, handling project linking, environment variable configuration, and deployment setups. It is designed for initial deployments, setting up preview deployments for pull requests, and configuring custom domains. Use it to streamline the process of managing production and preview environments on Vercel.

This Claude Skill deploys applications to Kubernetes clusters using kubectl manifests and Helm charts for production-ready setups. It handles deployments, services, configs, and implements health checks, resource limits, and rolling updates. Use it for deploying to cloud or self-hosted K8s, migrating from Docker Compose, or setting up multi-environment deployments.

This skill provides a complete guide to deploying ShinyProxy for hosting multiple containerized Shiny applications behind a single entry point. It covers Docker deployment, configuration, authentication, and usage tracking for isolated app containers. Use it when you need per-app access control, scalable multi-app hosting, and usage analytics for Shiny deployments.

This skill deploys Shiny applications to shinyapps.io, Posit Connect, or Docker containers. It handles configuration, manifest generation, Dockerfile creation, and deployment verification. Use it to publish apps for users, move from local development to hosted environments, or containerize apps for deployment pipelines.

This skill deploys a self-hosted SearXNG meta search engine using Docker Compose, covering configuration, engine selection, and Nginx setup. It's designed for developers who want to set up a private, untracked search engine that aggregates results from multiple providers. Use it when creating a shared search instance for teams or reducing reliance on single search providers.

This skill deploys ML models to production using MLflow, BentoML, or Seldon Core, providing REST/gRPC endpoints. It implements autoscaling, monitoring, and A/B testing for high-performance inference at scale. Use it when setting up real-time prediction APIs, managing variable load, or migrating from batch to online inference.

This skill deploys ML models to edge devices using frameworks like TensorFlow Lite and ONNX Runtime, optimizing them via quantization and hardware delegates. It enables on-device inference for scenarios where cloud connectivity is limited by latency, cost, or reliability. Use it for deploying to mobile, IoT, or embedded systems with tools for performance benchmarking and platform-specific deployment.

This Claude Skill helps developers define and implement measurable reliability targets (SLO/SLI/SLA) using Prometheus and tools like Sloth or Pyrra. It enables error budget tracking, burn rate alerts, and automated reporting to balance feature development with system reliability. Use it when establishing data-driven SRE practices for customer-facing services.

This skill provides a framework for implementing collective, layered defense in distributed systems, inspired by immune response patterns. It enables threat detection, alert propagation, and a proportional response that escalates with severity, preventing over- or under-reaction. Use it to design scalable incident response and defense-in-depth strategies where no single component can address all threats.

This skill guides developers through the controlled decommissioning of a validated system, ensuring compliance with data retention regulations. It handles key steps like data migration validation, archival strategy, and access revocation. Use it when replacing or retiring a system due to end-of-life, discontinued support, or regulatory changes.

This skill analyzes minified JavaScript to identify and classify feature flag gate implementations, extracting details like reader variants, default values, and logical conditions. It helps developers understand flag behavior when names are unclear or multiple flagging libraries are used. The analysis supports reverse-engineering by decoding gate mechanics and structured configuration schemas.

This skill provides guidance for cutting gemstones using cabochon or faceting techniques. It covers the entire process from rough stone assessment and orientation through dopping, grinding, and final geometry for brilliant cuts. Use it when planning gemstone cutting projects or setting up lapidary equipment.

This Claude Skill helps developers build and maintain library collections through acquisitions, systematic weeding, and collection assessment. It provides methods like CREW/MUSTIE for weeding and guides for creating collection policies. Use it when creating a new collection, assessing gaps, managing overcrowded shelves, or establishing formal development guidelines.

This Claude Skill provides comprehensive guidance for cultivating bonsai trees, covering technical horticultural tasks like species selection, pruning, wiring, and repotting. It also includes creating seasonal care schedules and integrating contemplative practices. Developers should use it when building applications related to bonsai care, gardening tutorials, or wellness routines involving living plants.

This skill enables two Claude Code instances to conduct structured, reciprocal code reviews via a dedicated MCP broker. It enforces review quality through QSG scaling laws that require minimum evidence thresholds and phase-gated progression. Use it when you need systematic, evidence-backed cross-project analysis between two codebases.

This Claude Skill creates a Work Breakdown Structure (WBS) and WBS Dictionary by decomposing project deliverables into a hierarchical structure of manageable work packages. It handles WBS coding, effort estimation, dependency identification, and critical path analysis for classic or waterfall projects. Use it after project charter approval to establish a basis for detailed planning, estimation, and resource allocation.

This skill creates a new multi-agent team composition file by automating the setup of a coordinated workflow. It handles purpose definition, member selection, coordination patterns, task decomposition, and generates the required configuration and documentation. Use it when defining a multi-agent workflow or composing agents for complex, recurring collaborative tasks.

This skill creates interactive spatial visualizations like maps and elevation profiles from GPX or route data. It supports implementation in R (sf, leaflet) or Observable (D3, deck.gl) for tasks like visualizing tour routes or building trip dashboards. It handles the full workflow from data import and coordinate systems to styled map output in HTML or image formats.

This skill helps developers create standardized SKILL.md files following the Agent Skills open standard (agentskills.io). It provides templates and guidance for structuring skill documentation, including frontmatter schema, procedure writing with Expected/On failure pairs, and validation checklists. Use it to codify repeatable agent procedures or convert existing guides into agent-consumable formats.

This skill scaffolds a complete R package structure following modern best practices. It sets up essential components like DESCRIPTION, testing with testthat, documentation with roxygen2, dependency management with renv, and CI/CD with GitHub Actions. Use it when starting a new package, converting scripts into a package, or creating a collaborative project skeleton.

This Claude Skill generates optimized Dockerfiles for R projects using rocker base images. It handles system dependencies, R package installation, and renv integration with smart layer ordering for faster rebuilds. Use it when containerizing R applications, creating reproducible environments, or deploying R-based services like Shiny or Plumber APIs.