oa-agent-library-builder

Analyze successful agent runs and generate structured JSON agent templates.

4|Updated Feb 26, 2026

Search Tags:#automation #template #code generation #ai development #agent #reusability

Ready to run

npx skills add https://github.com/OpenAEC-Foundation/Open-Agents --skill oa-agent-library-builder

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: oa-agent-library-builder
Source: https://github.com/OpenAEC-Foundation/Open-Agents/tree/main/.claude/skills/oa-agent-library-builder
Command: npx skills add https://github.com/OpenAEC-Foundation/Open-Agents --skill oa-agent-library-builder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the process of creating new, reusable AI agents by analyzing successful agent runs and extracting patterns, preventing redundant work and promoting efficiency.

Core Features & Use Cases

Template Extraction: Analyzes completed agent workspaces to identify repeatable tasks and extract key parameters.
Pattern Analysis: Determines task category, required tools, complexity, and atomicity for new agent templates.
Model Hint Assignment: Selects the most cost-effective Claude model (Haiku, Sonnet, Opus) based on task complexity.
Template Generation: Creates a JSON template file adhering to a strict schema for new agents.
Use Case: After an agent successfully generates documentation from code, use this Skill to turn that successful run into a reusable agent template for future documentation tasks.

Quick Start

Use the oa-agent-library-builder skill to save the last successful agent run as a reusable template.

Frequently Asked Questions about oa-agent-library-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I create reusable AI agent templates from successful runs?▼

To create reusable AI agent templates, this Skill analyzes completed agent workspaces to identify repeatable tasks and extracts key parameters into a structured JSON template. It evaluates task categories, necessary tools, and complexity to generate a template for agent library integration.

How does pattern analysis work when generating an AI agent template?▼

Pattern analysis for AI agent templates works by evaluating completed agent runs to determine task category, required tools, complexity, and atomicity. It then uses these patterns to automate template generation and assigns the optimal Claude model for cost efficiency.

Can I automate Claude model selection for new AI agents?▼

Yes, you can automate Claude model selection during agent template generation. The Skill assigns the most cost-effective Claude model—Haiku, Sonnet, or Opus—based on the extracted complexity and atomicity of the identified task pattern.

What is the best way to save a successful agent run as a reusable template?▼

The best way to save a successful agent run is to use a template extraction process that identifies repeatable tasks and generates a structured JSON template file. This file adheres to a strict schema for seamless agent library integration.

Do I need a strict JSON schema to integrate AI agents into a library?▼

Yes, a strict JSON schema is required for agent library integration. The Skill generates a structured JSON template file that captures the extracted task patterns, tools, and model hints to ensure the new agent is reusable and standardized.

When should I not use automated agent template extraction?▼

You should avoid automated agent template extraction when a completed agent run involves highly unique, non-repeatable tasks. The process relies on identifying consistent patterns, so one-off complex workflows without reusable components are not suitable for JSON template generation.