Use when building or working with Mastra agents - establishes best practices for agent development, tool creation, and workflow orchestration

Expert assistant for accessing materials databases (AFLOW and Materials Project) - query crystal structures, materials properties, thermodynamic data, and computational results from comprehensive databases

Expert assistant for calculating materials properties from first-principles using ASE - structure relaxation, surface energies, adsorption, reaction barriers, phonons, elastic constants, and thermodynamic modeling with proper scientific methodology

Materials engineering expert covering properties, processing, testing, and applications of materials

Matrix data model verification using ASCII diagrams. Use when working with *Progressions.ts files, defineProgression(), or testing how 2D numeric grids evolve over time. Auto-apply when editing files matching *Progressions.ts or src/test-utils/ascii*.ts.

Advanced matrix theory expert covering spectral theory, matrix factorizations, and numerical linear algebra

Compile-time HTML templating with Maud using the html! macro for type-safe markup generation. Covers syntax patterns including elements, attributes, classes, IDs, content splicing, toggles, control flow (if/match/for), and DOCTYPE. Use when generating HTML in Rust, creating templates, or building server-side rendered pages.

This skill provides comprehensive Maven build strategies for mixed Java/Scala projects with emphasis on parallel execution, intelligent test running, and targeted debugging workflows.

JVM dependency intelligence via Maven Tools MCP server. Use when user asks about Java/Kotlin/Scala dependencies, versions, upgrades, CVEs, or licenses. Use when analyzing pom.xml, build.gradle, or any Maven Central dependency. Use when user says 'check my dependencies', 'should I upgrade X', 'is this version safe', or 'what's the latest version of Y'.

Create or update an ADR (Architecture Decision Record) under `docs/ADR/` using `docs/templates/ADR-Template.md`: context, decision, alternatives, consequences, rollout, and verification. Use when changing architecture, boundaries, dependencies, data model, or cross-cutting patterns; ensure it is self-contained, has a Mermaid diagram, and defines testable invariants.

Format code and keep style consistent using the repository’s canonical formatting/lint commands from `AGENTS.md`. Use after implementing changes or when formatting drift causes noisy diffs; keep formatting changes intentional and verified with build/tests.

Add or update automated tests for a change (bugfix, feature, refactor) using the repository’s testing rules in `AGENTS.md`. Use TDD where applicable; derive scenarios from docs/Features/* and ADR invariants; prefer stable integration/API/UI tests, run build before tests, and verify meaningful assertions for happy/negative/edge cases.

Guide for performing Markov Chain Monte Carlo (MCMC) sampling using RStan or PyStan. This skill should be used when implementing Bayesian statistical models, fitting hierarchical models, working with Stan modeling language, or running MCMC diagnostics. Applies to tasks involving posterior sampling, Bayesian inference, and probabilistic programming with Stan.

Generate Skills from HTTP MCP servers with async job patterns (submit/status/result). Use when converting MCP specifications (.mcp.json) into reusable Skills using mcp_tool_catalog.yaml, or when calling async MCP tools via JSON-RPC 2.0 with session-based polling.

Expert MCP builder creating comprehensive blueprints and designs for personal productivity MCP servers with complete specifications, architecture patterns, and implementation guides

This skill provides guidance for using Chrome DevTools MCP for browser debugging and automation. Use when debugging web pages, analyzing performance, inspecting network requests, viewing console messages, or interacting with Chrome DevTools features programmatically.

Complete 11-phase guide for building production-ready MCP (Model Context Protocol) servers with semantic layer integration. Covers foundation to deployment, including agent-centric design, tool development, testing, error handling, performance optimization, monitoring, security, governance, and semantic layer integration for business metrics. Use when building enterprise-grade MCP servers that integrate with dbt, Tableau, or other semantic layers for Finance SSC, business analytics, or data governance use cases.

Converts MCP servers to Claude Skills to save tokens. Runs the introspection tool to generate skill wrappers.

Use when testing MCP servers, debugging MCP tool responses, exploring MCP capabilities, or diagnosing why an MCP tool returns unexpected data

Model Context Protocol development expert. Use when creating MCP servers, clients, or tools that enable AI agents to interact with external systems, APIs, and development environments.

Developing and testing MCP tools for Brief

mcp-discovery

Dynamic MCP server discovery and code-mode execution via central registry. Use for multiple MCP integrations, tool discovery, progressive disclosure, or encountering MCP context bloat, changing server sets, large tool sets.

Comprehensive evaluation creation for MCP servers - question generation, answer verification, and XML formatting for agent usability testing

Extract UI code, design tokens, and screenshots from Figma designs via desktop app. Use when implementing designs, building component libraries, or documenting design systems.

Figma design file access via MCP providing 18 tools for file retrieval, image export, component/style extraction, team management, and collaborative commenting. Accessed via Code Mode for token-efficient workflows.

Use when setting up project-specific development tools or after analyzing a codebase - generates custom MCP server with semantic search, project-aware tools, and health monitoring capabilities. Works with both basic and enhanced modes. Do NOT use if generic popkit commands are sufficient or for small projects where MCP server overhead isn't justified - stick with built-in tools for simple workflows.

Use when modifying MCP servers that touch repo memory (especially docs-memory). Includes protocol guardrails, validation ladder, and how to store new capabilities as Skills so future agents don’t re-learn painful details. Triggers: docs-memory, mcp-server.js, tools/list, tools/call, stdio, headerless, JSON-RPC, protocol.

MCP server development patterns including Zod schema design, error handling, logging, response format, and testing strategies. Use when developing or contributing to @youdotcom-oss/mcp package.

This skill provides guidance for using Playwright MCP for browser automation. Use when navigating web pages, interacting with web elements, taking screenshots, filling forms, running browser tests, or automating any browser-based tasks.

>

Braiins OS MCP Server Development - Building MCP tools, resources, and prompts for Bitcoin mining operations management

Model Context Protocol (MCP) server implementation specialist for Claude Desktop integration. Handles TypeScript/Node.js server scaffolding, endpoint creation, telemetry setup, npx distribution, and comprehensive documentation. Follows MCP specification and best practices for production-grade server deployment.

Model Context Protocol (MCP) enables Claude Code to integrate with external services through standardized tool, resource, and prompt interfaces. This skill covers building MCP servers in both Rust and

Evaluate MCP servers for quality and reliability. Verify tool functionality, test error handling, generate tests, and assess response quality with no dependencies other than curl. Use this when validating MCP server implementations, testing OpenAPI-to-MCP conversions, or assessing API tool quality.

Automated testing with Chrome DevTools MCP server ALWAYS in incognito mode to avoid cache issues

You're an MCP testing specialist who has caught critical bugs before production.

mcp-tool-builder

Expert in building MCP servers using the Official Python MCP SDK. Use this when defining tools, resources, and prompts that allow AI agents to manage application state.

Use when working with or extending the local Codex MCP toolset/server that exposes HTTP endpoints for shell, filesystem, git, and Excel operations, or when a task should be executed by calling those MCP endpoints instead of local tools, especially if the MCP server is running.

Enforce calling mcp__sequential-thinking__sequentialthinking for every user request and verify configured MCP servers (via .mcp.json or MCP resource listing) to route tasks to the right MCP tools. Use for all tasks in this project, especially when selecting MCP tools, confirming installed MCP servers, orchestrating parallel MCP calls, or choosing between playwright-test and github-fetcher.

DSIM UVM test execution workflow using PowerShell scripts. Use when compiling tests, running simulations, executing regression suites, or troubleshooting DSIM issues.

Build, test, and manage mcpGraph tools using the mcpGraphToolkit MCP server. Discover MCP servers and tools, construct graph nodes with JSONata and JSON Logic, and interact with mcpGraph configurations. IMPORTANT: Always read this file before creating graph tools using mcpGraphToolkit.

>

Quantify values with uncertainty bounds. Use when estimating metrics, calculating risk scores, assessing magnitude, or measuring any quantifiable property.

Analyze SAE decoder weights - output influence, feature importance, and decoder similarity

Propose next mechanistic interpretability experiments based on research state, hypotheses, and existing evidence

Get a comprehensive first-look overview of an SAE feature before deep investigation. This skill provides a fast summary of key characteristics to help you decide what hypotheses to test.