Back to Prompt Library
planning
Mastra AI Agent Setup and Document Schema Definition
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: SkillProof Document Agent
Format
Code-aware
Lines
18
Sections
4
Linked challenge
SkillProof Document Agent
Prompt source
Original prompt text with formatting preserved for inspection.
18 lines
4 sections
No variables
1 code block
Initialize a Mastra AI agent named 'SkillProofAgent'. Define a TypeScript interface for your 'SkillProof' document, including fields like `skillName`, `proficiencyLevel`, `descriptionGenerated`, and `vibeCodingAssessment`. Describe how Mastra AI's agent memory will store this document state. Provide the initial Mastra AI agent setup code and the TypeScript interface.
```typescript
import { createAgent, createTool, configureOpenAI } from '@mastra-ai/core';
import { createMemory } from '@mastra-ai/memory-redis'; // Example memory
interface SkillProofDocument {
skillName: string;
proficiencyLevel: 'Novice' | 'Intermediate' | 'Expert';
descriptionGenerated: string;
vibeCodingAssessment: string;
}
// const agent = createAgent({
// id: 'skillProofAgent',
// memory: createMemory('redis'), // Using Redis for persistence
// tools: [],
// llm: configureOpenAI({ model: 'gpt-4o' }), // Initial LLM for general orchestration
// // ... other configurations
// });
```Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Tune next
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Verify after
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.