mastra

bởi mastra-ai

Hướng dẫn tham khảo để xây dựng agent và quy trình làm việc với các API Mastra hiện tại. Luôn xác minh với tài liệu nhúng trong node_modules/@mastra/*/dist/docs/ (phiên bản đã cài đặt) hoặc tài liệu từ xa tại https://mastra.ai/llms.txt trước khi viết mã; dữ liệu huấn luyện đã lỗi thời. Các khối xây dựng cốt lõi: Agent (tự động, ra quyết định), Quy trình làm việc (chuỗi có cấu trúc), Công cụ (mở rộng khả năng), Bộ nhớ (duy trì ngữ cảnh) và RAG (kiến thức bên ngoài). Yêu cầu mô-đun ES2022 trong cấu hình Type

npx skills add https://github.com/mastra-ai/skills --skill mastra

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Everything you know about Mastra is likely outdated or wrong.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 installed:

ls node_modules/@mastra/
  • If packages exist: Use embedded docs first (most reliable)
  • If no packages: Install first or use remote docs

Resources

References

User QuestionFirst CheckHow To
Create/install Mastra projectreferences/create-mastra.mdSetup guide with CLI and manual steps
Choose Agent/Workflow/Tool/Memory/Storagereferences/core-concepts.mdCore concepts and when to use each primitive
How do I use Agent/Workflow/Tool?references/embedded-docs.mdLook up in node_modules/@mastra/*/dist/docs/
How do I use X? (no packages)references/remote-docs.mdFetch from https://mastra.ai/llms.txt
Choose or validate a modelreferences/model-selection.mdModel format and provider registry lookup
I'm getting an error...references/common-errors.mdCommon errors and solutions
Upgrade from v0.x to v1.xreferences/migration-guide.mdVersion upgrade workflows
Inspect/call server resources via CLIreferences/mastra-api.mdmastra api CLI for local, Mastra platform, or remote servers
Investigate agent health, recurring failures, or improvement opportunitiesreferences/trace-intelligence.mdStart with aggregate Trace Intelligence themes, then inspect trace/log evidence

Scripts

  • scripts/provider-registry.mjs: Look up current providers and models available in the model router. Always run this before using a model to verify provider keys and model names.

Priority order for writing code

Never write code without checking current docs first.

  1. Embedded docs first (if packages installed)

    Look up current docs in node_modules for a package. This matches the exact installed version and is the most reliable source of truth. See references/embedded-docs.md.

  2. Source code second (if packages installed)

    If embedded docs don't cover the question, inspect the installed source and type definitions. This is the source of truth when docs are missing or unclear. See references/embedded-docs.md.

  3. Remote docs third (if packages not installed)

    Use the latest published docs when packages are not installed or when exploring new features. Remote docs may be ahead of the user's installed version. See references/remote-docs.md.

Core concepts

Use references/core-concepts.md when choosing between agents, workflows, tools, memory, and storage.

  • Agent: Use for open-ended tasks that make decisions and use tools.
  • Workflow: Use for defined multi-step processes.

Mastra Studio

Studio is the interactive UI for building, testing, and managing agents, workflows, and tools. Use Studio when advising a human to inspect or debug visually.

Inside a Mastra project, run:

npm run dev

Then open http://localhost:4111 in a browser to show Mastra Studio to your human user.

Mastra API CLI

Use mastra api to inspect or call resources on local dev servers, Mastra platform deployments, or remote Mastra endpoints. It is useful for agent-readable state, execution, traces, logs, scores, threads, and workflow operations. See references/mastra-api.md for usage patterns.

Trace Intelligence

Trace Intelligence (private beta on the Mastra platform) clusters completed agent traces into recurring themes across four trace signals: goal, outcome, behavior, and sentiment. Use it first for aggregate agent-health questions: what users ask for, where outcomes fail or get blocked, which behaviors recur, how sentiment shifts, and where the agent can improve. Then use mastra api trace, log, metric, and score commands for concrete execution evidence from specific traces. Query Trace Intelligence with mastra api learning CLI commands, or over HTTP via the local dev server proxy or the platform endpoint. See references/trace-intelligence.md for the investigation workflow, CLI commands, and route reference.

Critical requirements

TypeScript config

Mastra requires ES2022 modules. CommonJS will fail. See references/create-mastra.md for setup and references/common-errors.md for troubleshooting.

Model format

Always use "provider/model-name" when defining models using Mastra's model router.

When the user asks to use a model or provider, always run scripts/provider-registry.mjs first to verify the provider key and model name are valid. Do not guess model names from memory as they change frequently. See references/model-selection.md.

When you see errors

Type errors often mean your knowledge is outdated.

Common signs of outdated knowledge:

  • Property X does not exist on type Y
  • Cannot find module
  • Type mismatch errors
  • Constructor parameter errors

What to do:

  1. Check references/common-errors.md
  2. Verify current API in embedded docs
  3. Don't assume the error is a user mistake - it might be your outdated knowledge

Development workflow

Always verify before writing code:

  1. Check whether Mastra packages are installed
  2. Look up current API
  3. Write code based on current docs
  4. Test with the project scripts or Studio when available

Thêm skills từ mastra-ai

testing-mastracode-tui
mastra-ai
Kiểm thử tương tác các tính năng TUI của mastracode trong Konsole. Bao gồm cấu hình mô hình, vòng đời luồng, cách ly trạng thái tác vụ và các rào cản phổ biến.
official
mastra-smoke-test
mastra-ai
Kiểm tra nhanh các dự án Mastra cục bộ hoặc triển khai lên môi trường staging/production. Kiểm tra Studio UI, tác nhân, công cụ, quy trình làm việc, dấu vết, bộ nhớ và nhiều hơn nữa. Hỗ trợ cả cục bộ…
official
security-review
mastra-ai
Danh sách kiểm tra đánh giá mã nguồn tập trung vào bảo mật để xác định các lỗ hổng
official
technical-writing
mastra-ai
Hướng dẫn tạo tài liệu kỹ thuật rõ ràng, có cấu trúc tốt
official
code-standards
mastra-ai
Tiêu chuẩn chất lượng mã và hướng dẫn phong cách để xem xét pull requests
official
debugging-difficult-bugs
mastra-ai
Sử dụng sớm khi gỡ lỗi một lỗi ở mức trung bình hoặc khó, đặc biệt khi chỉ kiểm thử có thể không phát hiện ra lỗi thời gian chạy thực sự. Kích hoạt kỹ năng này trước khi lặp lại TDD kéo dài…
official
e2e-frontend-validation
mastra-ai
Quy trình xác thực E2E cho các thay đổi frontend trong các gói playground sử dụng Playwright MCP
official
e2e-tests-studio
mastra-ai
BẮT BUỘC khi sửa đổi bất kỳ tệp nào trong packages/playground-ui hoặc packages/playground. Kích hoạt khi: tạo/sửa/tái cấu trúc component React, thay đổi UI,…
official