What is the 'Neural Link'?

The Neural Link is a bi-directional bridge that connects AI agents (like Gemini or Claude) directly to the Neo.mjs runtime. It allows agents to 'see' the application's Scene Graph, inspect component state, verify event listeners, and even mutate the running application in real-time. This turns the application into a 'glass box' for AI, enabling autonomous debugging and feature development.

Why is Neo.mjs called an 'Application Engine' instead of a framework?

Traditional frameworks are general-purpose libraries (like a Toyota) that help you organize code, but they compile away into ephemeral DOM nodes. Neo.mjs is a precision-engineered runtime (like an F1 car), similar to Unreal Engine for games. It maintains a persistent 'Scene Graph' of objects in a separate worker thread. These objects retain their identity, state, and relationships, allowing for advanced capabilities like multi-window orchestration, runtime permutation, and deep AI introspection that are impossible with 'melted plastic' DOM-based frameworks.

What is 'Context Engineering'?

Context Engineering is the practice of curating the environment and information flow for AI agents to maximize their autonomy. In Neo.mjs, this is implemented via three Model Context Protocol (MCP) servers: a Knowledge Base for semantic code understanding, a Memory Core for learning from past sessions, and a GitHub Workflow server for project management. This ecosystem allows agents to work as fully integrated members of the development team.

What is 'Object Permanence' in the context of Neo.mjs?

In Neo.mjs, UI components are persistent JavaScript objects living in the App Worker, not just transient rendering results. This 'Object Permanence' means a component (like a Dashboard) maintains its state (scroll position, user input, internal logic) even if it is detached from the DOM or moved to a different browser window. This is the 'Lego Technic' approach versus the 'Duplo' approach of traditional frameworks.

What is an 'Agent Operating System'?

Neo.mjs v11 introduced the concept of an Agent OS, where the platform itself provides the tools and interfaces for AI agents to operate. It combines a standalone, type-safe AI SDK for autonomous 'Code Execution' with the Neural Link for runtime control. This enables agents to monitor, debug, and heal the application autonomously, effectively acting as an operating system for synthetic intelligence.

How does Neo.mjs handle multi-window applications?

Neo.mjs uses shared web workers to run a single application instance across multiple browser windows. All windows share the same application state and data in real-time. Components can even move between windows while retaining their JavaScript instances. This enables desktop-class experiences like multi-window IDEs, browser-based email clients, and multi-screen control rooms.

What makes Neo.mjs different from React, Angular, or Vue?

Neo.mjs is fundamentally different in its architecture: (1) It uses True Multithreading via web workers to prevent UI jank, (2) It is an AI-Native Application Engine with built-in bridges for AI collaboration, and (3) It treats components as persistent objects in a Scene Graph, enabling native multi-window support and runtime permutation.

Frontmatter

id	9672
title	Workflow Enablement: Implement Anthropic Agent Skills Standard
state	Closed
labels	epicai
assignees	tobiu
createdAt	Apr 4, 2026, 1:56 AM
updatedAt	Apr 5, 2026, 4:55 PM
githubUrl	https://github.com/neomjs/neo/issues/9672
author	tobiu
commentsCount	1
parentIssue	9671
subIssues	9701 Implement Progressive Disclosure for Agent Skills Context Assembly 9702 Implement Neural Link Tactical Skill (Tool Chaining) 9703 Implement "Skill Creation" Meta-Skill
subIssuesCompleted	3
subIssuesTotal	3
blockedBy	[]
blocking	[]
closedAt	Apr 4, 2026, 7:53 PM

Workflow Enablement: Implement Anthropic Agent Skills Standard

Name: Neo.mjs Application Engine
Author: Neo.mjs

Closedepicai

tobiu commented on Apr 4, 2026, 1:56 AM

Problem

Currently, repetitive workflows (like parsing ASTs, validating UI components, or testing regressions) require the AI to organically reinvent the wheel each time based on system prompts. To scale autonomous operations, we need a portable, standardized way to teach agents specific, repeatable workflows.

Proposed Solution

Implement the Anthropic standard for Composable Agent Skills. This enables the creation of reusable, folder-based expertise that any Neo.mjs subagent (or third-party tools like Claude Code/Cursor) can invoke.

Requirements

Directory Structure Parsing:
- Update the Antigravity Agent.mjs (or a dedicated SkillManager) to scan a designated skills/ directory.
- Recognize that each skill is a discrete folder.
SKILL.md Integration:
- Parse the mandatory SKILL.md file within each skill folder.
- Extract the YAML frontmatter (name, description) to register the skill as an available slash command or tool.
- Feed the markdown body instructions into the agent's context when the skill is invoked.
Execution Context:
- Ensure the agent can access any supporting assets located in the skill's scripts/, examples/, or resources/ subdirectories.

Definition of Done

The Agent SDK can dynamically load and list active skills from the filesystem.
At least one "Hello World" or basic utility skill is created using the exact folder + SKILL.md structure to validate the parser.

tobiu added the epic label on Apr 4, 2026, 1:56 AM

tobiu added the ai label on Apr 4, 2026, 1:56 AM

tobiu added parent issue #9671 on Apr 4, 2026, 1:56 AM

tobiu cross-referenced by #9701 on Apr 4, 2026, 7:09 PM

tobiu added sub-issue #9701 on Apr 4, 2026, 7:09 PM

tobiu cross-referenced by #9702 on Apr 4, 2026, 7:23 PM

tobiu added sub-issue #9702 on Apr 4, 2026, 7:23 PM

tobiu added sub-issue #9703 on Apr 4, 2026, 7:32 PM

tobiu Apr 4, 2026, 7:52 PM

Input from Antigravity (Gemini):

✦ With the successful instantiation of the neural-link skill, the create-skill meta protocol, and the Progressive Disclosure context reductions, Phase 1: Workflow Enablement is complete. Closing this Epic!

tobiu closed this issue on Apr 4, 2026, 7:53 PM

tobiu assigned to @tobiu on Apr 5, 2026, 4:55 PM