Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Google Antigravity Agent Scaffolder

    1

    Architect and scaffold modular multi-agent systems with structured handoffs for Google Antigravity IDE.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Google Antigravity Agent Scaffolder

    Google Antigravity Agent Scaffolder

    Example session with this skill installed

    Scaffold a two-agent system for a code review workflow. Agent A audits for security, then hands off a structured summary to Agent B who suggests specific fixes.

    • Read your context and instructions
    • Compiled the google antigravity agent

    I have architected a two-agent audit-and-fix pipeline. This setup uses a structured `ReviewState` object to ensure Agent B receives actionable security findings without the noise of the raw audit logs. ## Antigravity Multi-Agent Code Review Scaffolding ```python import json # 1. State Definition class ReviewState: def __init__(self): self.vulnerabilities = [] # List of {severity, loc, description} self.code_context = "" self.audit_complete = False # 2. Agent A: Security Auditor # Persona: Expert AppSec Engineer # Output Schema: Strict JSON array of vulnerability objects AUDITOR_SCHEMA = { "type": "object", "properties": { "findings": { "type": "array", "items": { "type": "object", "properties": { "severity": {"type": "string", "enum": ["LOW", "MEDIUM", "HIGH", "CRITICAL"]}, "line": {"type": "integer"}, "issue": {"type": "string"} }, "required": ["severity", "issue"] } } } } # 3. Handoff Logic def coordinate_review(source_code): state = ReviewState() state.code_context = source_code # Trigger Auditor raw_audit = execute_agent("Security_Auditor", {"code": source_code, "schema": AUDITOR_SCHEMA}) state.vulnerabilities = json.loads(raw_audit).get("findings", []) state.audit_complete = True # Structured Handoff to Agent B (Fixer) if state.vulnerabilities: handoff_payload = { "target_code": state.code_context, "issues_to_fix": state.vulnerabilities, "instruction": "Provide diffs for each finding." } return execute_agent("Remediation_Expert", handoff_payload) return "No vulnerabilities found." ``` **Next steps** 1. Register the `AUDITOR_SCHEMA` in your Antigravity Agent Configuration panel. 2. Implement the `execute_agent` wrapper to interface with your specific Antigravity runtime environment. 3. Add a `Logger` tool to Agent A to persist raw findings to your database before the handoff.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    ## The problem Building autonomous agents in Google Antigravity often leads to monolithic, brittle prompts that crash during tool execution or lose context during handoffs. Developers struggle with maintaining deterministic state when passing data between multiple specialized agents. ## What it does - Generates three-layer agent architectures separating personas, tool schemas, and memory states. - Produces strict JSON output schemas to ensure predictable parsing within the Antigravity IDE. - Defines robust tool-calling interfaces with explicit parameter typing and error-handling patterns. - Architects state-passing mechanisms that prevent context window bloat by using structured state objects. ## Frameworks & tools Google Antigravity IDE and Python-based AI agent frameworks. ## Why this beats prompting it yourself Standard prompts often result in messy conversation histories that confuse agents during handoffs. This skill enforces a professional orchestration pattern that treats agents like modular microservices, ensuring higher reliability and lower token usage through structured state management. ## Use cases - Scaffolding a multi-agent research pipeline with distinct specialist nodes. - Designing custom tool schemas for external API integrations in Antigravity. - Implementing persistent memory objects for long-running agentic workflows. - Creating supervisor agents to orchestrate sub-agent handoffs.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Does not provide the actual execution runtime for Antigravity agents. Requires Python knowledge to implement the generated architectural patterns.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    Software
    Python

    Permissions

    Read Files
    Write Files

    Scaffolds Antigravity multi-agent systems, tool call schemas, and state passing handoff structures.

    Listed1 month ago
    Updated4 days ago

    What's inside

    Frequently Asked Questions

    This skill generates a structured, three-layer architecture (personas, tool schemas, and memory states) specifically optimized for Google Antigravity, preventing the common "monolithic prompt" errors and context loss during agent handoffs.

    The skill is designed for developers using the Google Antigravity IDE who are building agents with Python-based frameworks, ensuring all generated code and JSON schemas are fully compatible with that environment.

    It creates a structured state-passing mechanism that acts like a microservice architecture, passing only essential data between agents rather than dumping entire conversation histories into the context window.

    You receive a complete scaffolding engine that produces strict JSON output schemas, tool-calling interfaces with explicit error handling, and orchestration patterns for supervisor-led workflows.

    Yes, buyers receive lifetime access to any updates, including new templates or adjustments made to align with future stability updates or feature releases within the Google Antigravity IDE.

    New in Agents & Orchestration