Create Atomic Schema
Skill Verified ActiveDesign and write a `BaseIOSchema` input/output pair for an Atomic Agents agent or tool — docstrings, field descriptions, validators, error variants. Use when the user asks to "create a schema", "design the input/output schema", "define an `IOSchema`", "write a `BaseIOSchema`", "model the agent's output", or runs `/atomic-agents:create-atomic-schema`.
To streamline the creation of robust and well-documented input/output schemas for Atomic Agents, ensuring consistency and maintainability in AI application development.
Features
- Guides schema design with clear phases (clarify, write, verify).
- Enforces docstrings and field descriptions for LLM integration.
- Demonstrates discriminated unions and validator usage.
- Provides a minimal template for quick schema implementation.
Use Cases
- When a user asks to create or define a schema for an agent or tool.
- When modifying an existing schema with new fields or error variants.
- When ensuring schemas are properly documented for LLM interpretation.
Non-Goals
- Handling general Atomic Agents framework questions (use the umbrella skill).
- Implementing complex validators or advanced Pydantic patterns beyond the scope of schema definition.
- Writing the actual agent or tool logic that consumes the schema.
Workflow
- Clarify caller, direction, fields, and failure modes.
- Write schema(s) in conventional locations using `BaseIOSchema` and `Field` with descriptions.
- Verify schema imports cleanly and round-trips through `model_json_schema()`.
- Hand off to user with import locations and next steps (agent, tool, context provider).
Practices
- Schema design
- Code documentation
- Type safety
Installation
First, add the marketplace
/plugin marketplace add BrainBlend-AI/atomic-agents/plugin install atomic-agents@brainblend-pluginsQuality Score
VerifiedTrust Signals
Similar Extensions
Create Atomic Tool
99Build a `BaseTool[InSchema, OutSchema]` subclass — input/output schemas, `BaseToolConfig`, `run()` (and optional `run_async()`), env-driven secrets, typed failure outputs. Use when the user asks to "add a tool", "create a tool", "wrap an API as a tool", "build a `BaseTool`", "make a calculator/search/weather tool", or runs `/atomic-agents:create-atomic-tool`.
Instructor
98Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
Instructor
75Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
Embedding Strategies
100Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
Aws Cdk Development
100AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python. Use when creating CDK stacks, defining CDK constructs, implementing infrastructure as code, or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS infrastructure programmatically. Covers CDK app structure, construct patterns, stack composition, and deployment workflows.
Fit Drift Diffusion Model
100Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.