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	9957
title	Scaffold pull-request Progressive Disclosure Skill
state	Closed
labels	documentationenhancementai
assignees	tobiu
createdAt	Apr 13, 2026, 11:34 AM
updatedAt	Apr 14, 2026, 12:32 AM
githubUrl	https://github.com/neomjs/neo/issues/9957
author	tobiu
commentsCount	0
parentIssue	9950
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 13, 2026, 3:04 PM

Scaffold pull-request Progressive Disclosure Skill

Closed v13.0.0/archive-v13-0-0-chunk-4 documentationenhancementai

tobiu commented on Apr 13, 2026, 11:34 AM

Goal

Remove raw Git and gh execution mandates from the root AGENTS.md system prompt and isolate them into an on-demand pull-request skill.

Implementation Checklist

Use the create-skill architecture to scaffold .agent/skills/pull-request/SKILL.md.
Document the native Git sequence (git checkout, git commit, gh pr create --fill).
Embed the signal_state_transition execution mandate as the final algorithmic step of the skill.
Incorporate the 'Stepping Back' reflective protocol explicitly within the act of opening a PR entirely autonomously, without coupling it to the pr-review phase.

tobiu added the documentation label on Apr 13, 2026, 11:34 AM

tobiu added the enhancement label on Apr 13, 2026, 11:34 AM

tobiu added the ai label on Apr 13, 2026, 11:34 AM

tobiu added parent issue #9950 on Apr 13, 2026, 11:34 AM

tobiu referenced in commit 528e1e7 - "feat: progressive disclosure for pull request skill (#9957)" on Apr 13, 2026, 2:47 PM

tobiu cross-referenced by PR #9968 on Apr 13, 2026, 2:49 PM

tobiu referenced in commit 33b2302 - "fix: chain pr-review skill for post-PR reflection (#9957)" on Apr 13, 2026, 2:54 PM

tobiu referenced in commit 8702217 - "fix: prohibit autonomous agents from self-reviewing PRs (#9957)" on Apr 13, 2026, 2:57 PM

tobiu referenced in commit dcfb64b - "fix: restore iterative polish mandate into the Pre-PR reflection phase (#9957)" on Apr 13, 2026, 2:59 PM

tobiu referenced in commit abf8a80 - "refactor: align Pre-COMMIT reflection explicitly with pr-review semantic guidelines (#9957)" on Apr 13, 2026, 3:03 PM

tobiu closed this issue on Apr 13, 2026, 3:04 PM

tobiu referenced in commit ddf4b38 - "feat: progressive disclosure for pull request skill (#9957) (#9968) on Apr 13, 2026, 3:04 PM

tobiu assigned to @tobiu on Apr 14, 2026, 12:32 AM