How do I install the Mastra skill?

Run npx skillmds@latest add akillness/mastra in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Mastra skill do?

Agent engineering skill for Mastra It is listed under AI & ML on SkillMD.

Is Mastra safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Mastra?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Mastra free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Elastic-2.

Who published Mastra?

akillness (@akillness) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Mastra by akillness — Agent Skill

Name: Mastra
Author: akillness

File contents

mastra

Mastra is a leading agent framework in the 2026 AI agent engineering landscape (25.7k★).

When to use this skill

TypeScript agent framework: Agent class with tools, memory, voice
Workflows: durable graph-based step engine with suspend/resume
RAG pipeline: chunk/embed/store/query across pgvector, Pinecone, Qdrant
Scorers/evals: model-graded and rule-based
Mastra Studio: local playground UI (mastra dev) to build/test/manage agents
Vercel AI SDK interop; deploy via mastra build to serverless (Vercel/CF/Netlify)
Ecosystem overlap: None — catalog is Python-heavy; fills the TS framework gap

Installation

npm create mastra@latest

Core API

npm create mastra@latest   # scaffold project
cd my-app && npm run dev   # Mastra Studio at localhost:4111
# code: new Agent({ name, instructions, model: openai('gpt-5'), tools })

Instructions

Step 1: Initialize the environment

Verify you have TypeScript installed and set up properly. Use the correct package manager (pip, npm, pnpm, uv) as specified in the installation section.

Step 2: Establish the agent flow

Architecture pattern: Agents own tools/memory; workflows provide deterministic graph orchestration around LLM calls; storage/vector adapters pluggable; studio drives dev loop

Step 3: Implement tool integrations and policies

Integrate necessary tools, environment keys, and safety gates according to your architectural needs. Position in the ecosystem: Leading dedicated TypeScript agent framework (Gatsby team, YC W25); alternatives: voltagent (smaller), vercel/ai (lower-level SDK), langgraph-js

Examples

Example 1: Minimal Agent Run

npm create mastra@latest   # scaffold project
cd my-app && npm run dev   # Mastra Studio at localhost:4111
# code: new Agent({ name, instructions, model: openai('gpt-5'), tools })

Best practices

Follow the primary installation commands for Mastra to ensure dependencies are resolved correctly.
Configure model providers and API keys securely before starting the runtime.
Use appropriate sandboxing or permission isolation if executing AI-generated code.

References

---name: mastradescription: Agent engineering skill for Mastralicense: Elastic-2.0 (NOASSERTION on GitHub)---# mastraMastra is a leading agent framework in the 2026 AI agent engineering landscape (25.7k★).## When to use this skill- TypeScript agent framework: Agent class with tools, memory, voice- Workflows: durable graph-based step engine with suspend/resume- RAG pipeline: chunk/embed/store/query across pgvector, Pinecone, Qdrant- Scorers/evals: model-graded and rule-based- Mastra Studio: local playground UI (mastra dev) to build/test/manage agents- Vercel AI SDK interop; deploy via mastra build to serverless (Vercel/CF/Netlify)- Ecosystem overlap: None — catalog is Python-heavy; fills the TS framework gap## Installation```bashnpm create mastra@latest```## Core API```typescriptnpm create mastra@latest # scaffold projectcd my-app && npm run dev # Mastra Studio at localhost:4111# code: new Agent({ name, instructions, model: openai('gpt-5'), tools })```## Instructions### Step 1: Initialize the environmentVerify you have TypeScript installed and set up properly. Use the correct package manager (pip, npm, pnpm, uv) as specified in the installation section.### Step 2: Establish the agent flowArchitecture pattern: Agents own tools/memory; workflows provide deterministic graph orchestration around LLM calls; storage/vector adapters pluggable; studio drives dev loop### Step 3: Implement tool integrations and policiesIntegrate necessary tools, environment keys, and safety gates according to your architectural needs. Position in the ecosystem: Leading dedicated TypeScript agent framework (Gatsby team, YC W25); alternatives: voltagent (smaller), vercel/ai (lower-level SDK), langgraph-js## Examples### Example 1: Minimal Agent Run```typescriptnpm create mastra@latest # scaffold projectcd my-app && npm run dev # Mastra Studio at localhost:4111# code: new Agent({ name, instructions, model: openai('gpt-5'), tools })```## Best practices1. Follow the primary installation commands for Mastra to ensure dependencies are resolved correctly.2. Configure model providers and API keys securely before starting the runtime.3. Use appropriate sandboxing or permission isolation if executing AI-generated code.## References- [https://github.com/mastra-ai/mastra](https://github.com/mastra-ai/mastra)- [https://mastra.ai/docs](https://mastra.ai/docs)

Frequently asked questions

Mastra