Skip to content
mastra-skills logo

Mastra Skills

mastra-skills

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

SKILL.md

Full skill instructions

Mastra Skills

Core principle: Build composable, observable, and testable AI agents.

When to Use This Skill

Always use when:

  • Creating new Mastra agents
  • Implementing agent tools
  • Setting up workflows
  • Debugging agent behavior
  • Integrating external APIs with agents

Don't use for:

  • Non-agent-related code
  • Pure frontend components without agent interaction

Documentation Quick Links

Development Checklist

When creating a new agent, use TodoWrite to track:

  • Define clear agent purpose and capabilities
  • Identify required tools and integrations
  • Plan observability and logging strategy
  • Design agent memory and state management
  • Consider error handling and fallbacks
  • Write tests for key scenarios

Essential Requirements

Every Agent Must Have

  1. Clear purpose and instructions - Specific, not generic
  2. Descriptive name - Not 'agent1' or 'myAgent'
  3. Appropriate model selection - Choose based on task complexity
  4. Explicit tool registration - No implicit assumptions

Every Tool Must Have

  1. Descriptive ID - Clear what it does
  2. Clear description - For the LLM to understand
  3. Zod schema validation - Type-safe inputs
  4. Error handling - Never let tools crash agents
  5. Logging - For debugging and observability

Every Workflow Must Have

  1. Clear trigger schema - Validated inputs
  2. Proper step sequencing - Sequential vs parallel
  3. Error handling - In each step
  4. Observability hooks - beforeAll/​afterAll for logging

Core Patterns

Basic Agent

import { Agent } from '@mastra/​core';

const agent = new Agent({
  name: 'descriptive-name',
  instructions: 'Clear, specific instructions',
  model: {
    provider: 'ANTHROPIC',
    name: 'claude-sonnet-4-5',
  },
  tools: { /​* ... */ },
});

📚 More details: reference.md | https://mastra.ai/docs/agents/

Basic Tool

import { z } from 'zod';

const tool = {
  id: 'descriptive-id',
  description: 'What this tool does',
  inputSchema: z.object({
    param: z.string().describe('Parameter description'),
  }),
  execute: async ({ context }) => {
    try {
      const result = await operation();
      return { success: true, data: result };
    } catch (error) {
      logger.error('Operation failed', { error, context });
      return { success: false, error: error.message };
    }
  },
};

📚 More examples: examples.md | https://mastra.ai/docs/tools/

Basic Workflow

import { Workflow } from '@mastra/​core';

const workflow = new Workflow({
  name: 'workflow-name',
  triggerSchema: z.object({ input: z.string() }),
});

workflow
  .step({ id: 'step1', execute: async () => { /​* ... */ } })
  .then({ id: 'step2', execute: async () => { /​* ... */ } })
  .commit();

📚 More examples: examples.md | https://mastra.ai/docs/workflows/

Red Flags - Stop If You See

  • Agent without clear purpose
  • Tools without input validation
  • No error handling in tools
  • Missing observability/​logging
  • Hardcoded credentials
  • No rate limiting for external APIs
  • Unbounded memory growth

Common Rationalizations

ExcuseReality
"Agent instructions don't need to be specific"Vague instructions → unpredictable behavior
"Error handling adds complexity"Unhandled errors → crashed agents
"We can add observability later"Can't debug what you can't observe
"Tool schemas are optional"Invalid inputs → runtime failures

Integration Checklist

When integrating external services, use TodoWrite to track:

  • Create typed tool interface
  • Add input validation with Zod
  • Implement error handling
  • Add logging for debugging
  • Consider rate limiting
  • Handle authentication securely
  • Test with edge cases
  • Document tool usage

Testing Requirements

// Unit test for tools
describe('myTool', () => {
  it('should handle valid input', async () => {
    const result = await myTool.execute({
      context: { param: 'test' },
      mastra: mockMastra,
    });
    expect(result.success).toBe(true);
  });
});

// Integration test for agents
describe('myAgent', () => {
  it('should respond to queries', async () => {
    const response = await myAgent.generate([
      { role: 'user', content: 'test query' }
    ]);
    expect(response.role).toBe('assistant');
  });
});

📚 More examples: examples.md

Quick Workflow

  1. Need API details? → Check reference.md
  2. Need examples? → Check examples.md
  3. Building something? → Follow checklists above, use TodoWrite
  4. Stuck? → Check official docs at https://mastra.ai/docs/

Final Rule

Every agent must have:
1. Clear purpose and instructions
2. Type-safe tools with validation
3. Error handling and observability
4. Tests covering key scenarios

Follow these principles for reliable, maintainable Mastra agents.

More skills from majiayu000

xiaohongshu logo
majiayu000/claude-arsenal

xiaohongshu

xiaohongshu

286 148
View
agent-task-conductor logo
majiayu000/claude-skill-registry

agent-task-conductor

Conduct multi-agent task orchestration and workflow coordination.

663 1
View
conductor-setup logo
majiayu000/claude-skill-registry

conductor-setup

Initialize project with Conductor artifacts (product definition,

663 1
View
animation-designer logo
majiayu000/claude-skill-registry

animation-designer

Expert in web animations, transitions, and motion design using Framer Motion and CSS

663 1
View
diagramming logo
majiayu000/claude-skill-registry

diagramming

Creates Mermaid and ASCII diagrams for flowcharts, architecture, ERDs, state machines, mindmaps, and more. Use when user mentions diagram, flowchart, mermaid, ASCII diagram, text diagram, terminal diagram, visualize, C4, mindmap, architecture diagram, sequence diagram, ERD, or needs visual docume...

663 1
View
h3-pg logo
majiayu000/claude-skill-registry-data

h3-pg

PostgreSQL bindings for H3 hexagonal grid system. Use when working with H3 cells in Postgres, including spatial indexing, geometry/geography integration, and raster analysis.

23 1
View
conductor-development logo
majiayu000/claude-skill-registry

conductor-development

Context-Driven Development skill for projects using Conductor. Use this skill when you detect a `conductor/` directory in the project, when working on tasks defined in a `plan.md` file, or when the user asks about tracks, specs, or plans. Automatically applies TDD workflow, tracks task completion...

663 1
View
conductor-status logo
majiayu000/claude-skill-registry

conductor-status

Display project status, active tracks, and next actions

663 1
View
dockerization logo
majiayu000/claude-skill-registry

dockerization

Official Stakpak application containerization standard operating procedure, a step-by-step guidline to properly dockerize applications. This is a rule book curated by the Stakpak Team.

663 1
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View