Skip to content
ai101.tools
navigateopenescclose
Claude+372Whisper+228LangChain+168Codex+223NotebookLM+276DALL-E 3+192DeepL+249n8n+208Topaz Video AI+153LlamaIndex+161
Atomic Agents Skills logo
Skill

Atomic Agents Skills

Scaffolds Atomic Agents code where every agent, tool and context boundary is a validated schema.

0
SaveVisit website ↗

Install

Official
Claude Code: /plugin marketplace add anthropics/claude-plugins-official → /plugin install atomic-agents@claude-plugins-official
Triggers on

Atomic Agents ile ajan, araç ya da şema yazılırken; çok ajanlı bir akış kurulurken

Needs tools
ReadWriteEdit
Author
Kenny Vaneetvelde
License
MIT

Atomic Agents sits on Instructor and Pydantic and makes every boundary — user to agent, agent to tool, context provider to prompt — a validated schema instead of a string. The skills follow that shape: separate generators for an agent, a tool, a schema and a context provider, plus orientation and troubleshooting skills and two subagents, one that explores an existing project and one that reviews changes against the framework's conventions. Triggering on an import of atomic_agents or a BaseIOSchema subclass rather than on the product name being mentioned is what keeps it present during ordinary editing.

Comments(0)

Sign in to comment

No comments yet — be the first.

Similar skills

Report this comment

Why are you reporting this?