Create Atomic Tool
Skill Verified ActiveBuild 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`.
To provide a structured and guided process for developers to create custom tools for AI agents using the Atomic Agents framework.
Features
- Builds `BaseTool` subclasses with typed schemas.
- Supports synchronous (`run`) and asynchronous (`run_async`) methods.
- Guides configuration of secrets via environment variables and `BaseToolConfig`.
- Promotes typed failure outputs for robust error handling.
- Provides skeleton implementations for local and HTTP-backed tools.
Use Cases
- When a user asks to add a new tool to their AI agent.
- When a user needs to wrap an external API as a tool.
- When building utility tools like calculators, search functions, or database query tools.
- When creating custom `BaseTool` implementations within the Atomic Agents framework.
Non-Goals
- Creating agents or entire AI applications.
- Managing the deployment or distribution of tools.
- Handling general framework questions outside of tool creation.
Practices
- Tool Development
- Schema Design
- Error Handling
Prerequisites
- Python 3.8+
- Atomic Agents library installed
- Pydantic installed
Installation
First, add the marketplace
/plugin marketplace add BrainBlend-AI/atomic-agents/plugin install atomic-agents@brainblend-pluginsQuality Score
VerifiedTrust Signals
Similar Extensions
Cli Creator
100Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.
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
Create Atomic Schema
98Design 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`.
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
Context Mode Ops
100Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.
Fixflow
100Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.