skills.rest
Nima-MM
Nima-MMCOMMUNITY
Explore all skills by this author →
Website𝕏@Nima_M_M_GitHub

agent-creator

Design, evaluate, and iterate AI Agents within the Antigravity IDE framework.

Updated Aug 27, 2026
Search Tags:#automation#workflow#ai#agent#evaluation#iteration#prompt-engineering
One-click install
npx skills add https://github.com/Nima-MM/agentic-consultant --skill agent-creator-nima-mm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-creator
Source: https://github.com/Nima-MM/agentic-consultant/tree/main/.agents/skills/shared/agent-creator
Command: npx skills add https://github.com/Nima-MM/agentic-consultant --skill agent-creator-nima-mm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, pyyaml, anthropic, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps you design, scaffold, and iteratively improve AI Agents for the Antigravity IDE framework, turning goals into repeatable agent definitions and automated evaluation loops.

Core Features & Use Cases

  • Focused, constrained agent design aligned with domain tasks.
  • End-to-end evaluation: draft, test prompts, benchmark, and iterate agent definitions.
  • Seamless integration with scripts, references, and assets to support testing, tooling, and documentation.
  • Trigger optimization: refine descriptions to improve routing and domain coverage.

Quick Start

Draft an initial agent definition for your task, then run the evaluation loop to test and refine it.

Frequently Asked Questions about agent-creator

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

FAQPage Schema
How do I design and evaluate AI agents for the Antigravity IDE?▼

To design and evaluate AI agents for the Antigravity IDE, this skill provides end-to-end workflows from intent capture through benchmarking, supporting description optimization across multiple iterations.

Can I use YAML frontmatter to define automation workflows for AI agents?▼

Yes, YAML frontmatter is required when defining automation workflows. The skill enforces these frontmatter requirements to properly structure agent definitions and enable on-demand tooling.

What is the best way to iterate on prompt engineering for agent definitions?▼

The best way to iterate on prompt engineering is running the evaluation loop to test prompts and benchmark agent definitions, refining descriptions to improve routing and domain coverage.

How do scripts, references, and assets integrate with AI agent workflows?▼

Scripts, references, and assets integrate with AI agent workflows by being detected as optional resources. This enables on-demand tooling and documentation integration during agent design and evaluation.

Do I need Anthropic and Google GenAI dependencies to scaffold AI agents?▼

Yes, you need Anthropic and Google GenAI dependencies along with PyYAML to scaffold AI agents. These provide the underlying models and parsing capabilities required for evaluation and iteration.

Why does my AI agent trigger routing not matching the intended domain tasks?▼

Trigger routing fails when agent descriptions lack optimization. The skill addresses this by refining descriptions through evaluation loops to improve domain coverage and routing accuracy.

Related Skills

Explore More Software Engineering Skills→
modu-aimodu-ai
1.2k

moai-ai-nano-banana

Automate content and image generation via Nano Banana Pro AI.

Official
Advanced
locdinh209locdinh209

antigravity

Coordinates tasks, artifacts, and agents within the Antigravity IDE.

Community
Advanced
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic
mcauduro0mcauduro0
1

senior-prompt-engineer

Analyze and optimize LLM prompts with Python scripts.

Community
Advanced