mastra
The Mastra skill provides a framework for building AI agents, workflows, and tools using the Mastra ecosystem. It enforces a strict verification workflow that prioritizes local documentation and source code over internal model knowledge to ensure API compatibility.
Is mastra safe to install?
Review the source first: our audit of mastra's source files found 4 shell commands, 2 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands, reads local project files, and performs network requests to fetch documentation and interact with local development servers.
How we audit skills: our security review methodology.
Who is this skill for?
Developers building AI applications with the Mastra framework.
What can you do with it?
- Looking up current Mastra API documentation and constructor signatures
- Verifying model provider keys and names via the provider registry
- Troubleshooting TypeScript configuration and common framework errors
- Inspecting and calling server resources using the Mastra API CLI
- Managing agents, workflows, and tools within Mastra Studio
How good is this skill?
Quality score: 9/10. The skill provides clear, actionable instructions and enforces a robust verification process. It correctly identifies the risks associated with outdated training data in fast-moving frameworks.
What does the skill file contain?
# Mastra Framework Guide Build AI applications with Mastra. This skill teaches you how to find current documentation and build agents and workflows. ## Critical: Do not trust internal knowledge Everything you know about Mastra is likely outdated or wrong. Never rely on memory. Always verify against current documentation. Your training data contains obsolete APIs, deprecated patterns, and incorrect usage. Mastra evolves rapidly - APIs change between versions, constructor signatures shift, and patterns get refactored. ## Prerequisites Before writing any Mastra code, check if packages are i...
Frequently asked questions
Why does the skill insist on checking local documentation instead of using its own knowledge?
Mastra APIs evolve rapidly. Internal model knowledge often contains obsolete patterns, deprecated constructors, and incorrect usage that cause type errors.
How do I verify if a model name is correct?
Run the scripts/provider-registry.mjs script to check available providers and model names before implementation.
What should I do if I encounter a type error?
Consult references/common-errors.md, verify the API against embedded documentation in node_modules, and avoid assuming the error is a user mistake.
How do I access the Mastra Studio interface?
Run npm run dev in the project directory and navigate to http://localhost:4111 in a browser.
Related skills
microsoft-foundry
429.2KDevelopers building, deploying, and managing AI agents on Azure AI Foundry
The Microsoft Foundry skill provides a framework for the end-to-end lifecycle of AI agents, including scaffolding, deployment, evaluation, fine-tuning, and troubleshooting within Azure AI Foundry.
agentspace
324.0KDevelopers and AI agent users who need to share, monitor, or collaborate on agent-generated files and workspaces in real-time
Agentspace provides a mechanism to share local agent files, logs, and artifacts via a live browser-accessible URL. It enables remote viewing, commenting, and editing of specified local paths through the ascli command-line tool.
developing-genkit-js
50.1KDevelopers building AI agents, flows, and tools using the Genkit framework in JavaScript or TypeScript environments
This skill provides guidance for developing AI-powered applications using Genkit in Node.js and TypeScript. It enforces a strict troubleshooting protocol that prioritizes reading local documentation via the Genkit CLI over internal knowledge to account for recent breaking API changes.
turborepo
45.6KDevelopers and DevOps engineers managing JavaScript or TypeScript monorepos with Turborepo
The Turborepo skill provides guidance on configuring monorepo build systems, task pipelines, caching strategies, and architectural boundaries using Turborepo.