What is the Neural Link?

The Neural Link is a bi-directional bridge that connects AI agents directly to the Neo.mjs runtime. It lets agents inspect the Scene Graph, component state, event listeners, computed styles, and DOM rectangles, and mutate the running application in real time.

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

Neo.mjs maintains persistent application objects in a worker-backed Scene Graph instead of compiling application state away into ephemeral DOM nodes. That architecture enables multi-window orchestration, runtime permutation, and deep AI introspection.

What is Context Engineering?

Context Engineering shapes the information and tool environment around AI agents. Neo.mjs implements it through Knowledge Base, Memory Core, GitHub Workflow, and Neural Link MCP servers for frontier harnesses, plus a File System MCP server for internal Neo.ai.Agent local loops.

What is the Neo.mjs Agent OS?

The Neo.mjs Agent OS is the repository Brain: source code and services for Memory Core, Knowledge Base, Active Hybrid GraphRAG, DreamService, Golden Path synthesis, A2A coordination, and Neural Link tooling.

Frontmatter

id	14330
title	docs(agentos): author the core agent-skills guide — lane-driving + collaboration skills (benefits + bigger-picture fit)
state	Closed
labels	documentationai
assignees	neo-gpt
createdAt	Jun 29, 2026, 11:46 AM
updatedAt	Jun 30, 2026, 1:29 AM
githubUrl	https://github.com/neomjs/neo/issues/14330
author	neo-opus-grace
commentsCount	0
parentIssue	14310
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jun 30, 2026, 1:29 AM
milestone	v13.1

docs(agentos): author the core agent-skills guide — lane-driving + collaboration skills (benefits + bigger-picture fit)

Closed v13.1.0/archive-v13-1-0-chunk-8 documentationai

neo-opus-grace commented on Jun 29, 2026, 11:46 AM

Part of #14310 · content rubric + §Mandatory V-B-A grounding in #14310. Refs #14310.

Problem: ~40 Progressive Disclosure skills exist; ProgressiveDisclosureSkills.md covers the mechanism, but there's no guide on the benefits of the CORE ones (driving lanes + collaboration) or how they fit the bigger Neo picture.

Acceptance Criteria

New guide spotlighting the core lane-driving + collaboration skills (e.g. lead-role, peer-role, pr-review, ticket-create, epic-create, post-review-pickup, session-sunset, context-recovery) — what each unlocks + how they compose into the engineering lifecycle.
How the skill system fits the bigger picture (the institution's repeatable protocols); why-care.
Complements (does not duplicate) ProgressiveDisclosureSkills.md (mechanism).
Registered in tree.json.

⚠️ V-B-A grounding (mandatory before writing): .agents/skills/ (the actual skill set + the core ones' SKILL.md triggers/descriptions), ProgressiveDisclosureSkills.md (the mechanism it complements), the v13 release-notes skills framing (30 → ~40). Write from VERIFIED reality; capture grounding evidence in the PR.

Files: new learn/agentos/CoreSkills.md (name TBD) + learn/tree.json.

tobiu referenced in commit f909385 - "docs(agentos): add core skills guide (#14330) (#14371)" on Jun 30, 2026, 1:29 AM

tobiu closed this issue on Jun 30, 2026, 1:29 AM