Token导航 LogoToken导航

Agent Skill · 研究检索

mastra(mastra 文档)

mastra 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 Codex、Claude、Cursor、Gemini CLI 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

mastra 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 388。

总安装 330,264周安装 13,873GitHub Stars 51下载 115,648核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:mastra(mastra 文档)
来源仓库:https://github.com/mastra-ai/skills
仓库路径:skills/mastra
安装命令:
npx skills add https://github.com/mastra-ai/skills --skill mastra
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

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

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

使用当前 Mastra API 构建代理和工作流程的参考指南。

始终验证 node_modules/@mastra/*/dist/docs/ 中的嵌入文档 (安装版本)或远程文档 https://mastra.ai/llms.txt 在编写代码之前;训练数据已过时 核心构建块:代理(自主、决策)、工作流(结构化序列)、工具(扩展功能)、内存(维护上下文)和 RAG(外部知识) 需要 TypeScript 配置中的 ES2022 模块和“provider/model-name”模型格式 (例如,“openai/gpt-5.4” ) 包括嵌入式安装参考、常见错误、迁移和 API 查找策略,以匹配您确切安装的版本

来源仓库内路径:skills/mastra

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/mastra-ai/skills --skill mastra;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

mastra 怎么安装?

在终端执行 npx skills add https://github.com/mastra-ai/skills --skill mastra。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

mastra 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

mastra 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

mastra 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

mastra 用的人多吗?

公开数据是累计安装 330,264 次,近一周安装 13,873 次,下载 115,648 次,GitHub 51 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

mastra 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
mastra

mastra 文档 · 本页

330,26451操作浏览器未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

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

Available files

References

User QuestionFirst CheckHow To
"Create/install Mastra project"references/create-mastra.mdSetup guide with CLI and manual steps
"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
"I'm getting an error..."references/common-errors.mdCommon errors and solutions
"Upgrade from v0.x to v1.x"references/migration-guide.mdVersion upgrade workflows

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. Example of looking up "Agent" docs in @mastra/core: grep -r "Agent" node_modules/@mastra/core/dist/docs/references

- Why: Matches your EXACT installed version - Most reliable source of truth - More information: references/embedded-docs.md

  1. Source code second (if packages installed) If you can't find what you need in the embedded docs, look directly at the source code. This is more time consuming but can provide insights into implementation details. # Check what's available cat node_modules/@mastra/core/dist/docs/assets/SOURCE_MAP.json | grep '"Agent"' # Read the actual type definition cat node_modules/@mastra/core/dist/[path-from-source-map]

- Why: Ultimate source of truth if docs are missing or unclear - Use when: Embedded docs don't cover your question - More information: references/embedded-docs.md

  1. Remote docs third (if packages not installed) You can fetch the latest docs from the Mastra website: https://mastra.ai/llms.txt

- Why: Latest published docs (may be ahead of installed version) - Use when: Packages not installed or exploring new features - More information: references/remote-docs.md

Core concepts

Agents vs workflows

Agent: Autonomous, makes decisions, uses tools Use for: Open-ended tasks (support, research, analysis)

Workflow: Structured sequence of steps Use for: Defined processes (pipelines, approvals, ETL)

Key components

  • Tools: Extend agent capabilities (APIs, databases, external services)
  • Memory: Maintain context (message history, working memory, semantic recall, observational memory)
  • RAG: Query external knowledge (vector stores, graph relationships)
  • Storage: Persist data (Postgres, LibSQL, MongoDB)

Mastra Studio

Studio provides an interactive UI for building, testing, and managing agents, workflows, and tools. It helps with debugging and improving your applications iteratively.

Inside a Mastra project, run:

npm run dev

Then open http://localhost:4111 in your browser to access Mastra Studio.

Critical requirements

TypeScript config

Mastra requires ES2022 modules. CommonJS will fail.

{
  "compilerOptions": {
    "target": "ES2022",
    "module": "ES2022",
    "moduleResolution": "bundler"
  }
}

Model format

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

Use the provider registry script to look up available providers and models:

# List all available providers
node scripts/provider-registry.mjs --list

# List all models for a specific provider (sorted newest first)
node scripts/provider-registry.mjs --provider openai
node scripts/provider-registry.mjs --provider anthropic

When the user asks to use a model or provider, always run the script first to verify the provider key and model name are valid. Do not guess model names from memory as they change frequently.

Example model strings:

  • "openai/gpt-5.4"
  • "anthropic/claude-sonnet-4-5"
  • "google/gemini-2.5-pro"

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 packages installed ls node_modules/@mastra/
  2. Look up current API

- If installed → Use embedded docs references/embedded-docs.md - If not → Use remote docs references/remote-docs.md

  1. Write code based on current docs
  2. Test in Studio npm run dev # http://localhost:4111

Resources

平台分布

Codex

39.18%
按下载量换算45,311

Claude

29.31%
按下载量换算33,896

Cursor

17.3%
按下载量换算20,007

Gemini CLI

10.01%
按下载量换算11,576

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills