Electron Multi-Process Architecture

What it does

When your agent uses it

• Deciding which folder a new module or component belongs in
• Turning a single-file component into a directory
• Adding a new bridge, service, agent or worker
• Reviewing a change for structure and process-boundary violations

Example prompts

• “Where should the new settings page and its hook live in this Electron app?”
• “Add a bridge for the file export feature and tell me which process owns it.”
• “Review this PR for imports that cross process boundaries.”
• “Convert ChatPanel.tsx into a component directory that follows our conventions.”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Directory size limit: Max 10 direct children. Split into subdirectories by responsibility when approaching.
2. 2No single-file directories: Merge into parent or related directory.
3. 3Single file vs directory: If a component needs a private sub-component or hook, convert to a directory with index.tsx.
4. 4Page-private first: Start code in pages//. Promote to shared only when a second consumer appears.

What it can do on your machine

Read from SKILL.md and the folder at commit 6744099. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Electron Multi-Process Architecture loads about 1.8k tokens when it runs, and up to ~5.6k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 404 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~80

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from iOfficeAI/AionUi at commit 6744099, republished under its Apache-2.0 licence (© iOfficeAI). 404 words, ~1,791 tokens.

name

architecture

description

Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.

Is it UI (React components, hooks, pages)?
  └── YES → packages/desktop/src/renderer/              → see references/renderer.md

Is it an IPC handler responding to renderer calls?
  └── YES → packages/desktop/src/process/bridge/        → see references/process.md

Is it business logic running in the main process?
  └── YES → packages/desktop/src/process/services/      → see references/process.md

Is it an AI platform connection (API client, message protocol)?
  └── YES → packages/desktop/src/process/agent/<platform>/

Is it a background task that runs in a worker thread?
  └── YES → packages/desktop/src/process/worker/

Is it used by BOTH main and renderer processes?
  └── YES → packages/desktop/src/common/

Is it an HTTP/WebSocket endpoint?
  └── YES → packages/desktop/src/process/webserver/

Is it a plugin/extension resolver or loader?
  └── YES → packages/desktop/src/process/extensions/

Is it a messaging channel (Lark, DingTalk, Telegram)?
  └── YES → packages/desktop/src/process/channels/

// NEVER in renderer
import { something } from '@process/services/foo'; // crashes at runtime

// Use IPC instead
const result = await window.api.someMethod(); // goes through preload

© iOfficeAI, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .claude/skills/architecture of iOfficeAI/AionUi.

• SKILL.md
• references/process.md
• references/project-layout.md
• references/renderer.md

Open the folder on GitHubat commit 6744099

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in iOfficeAI/AionUi, which our catalogue first saw on October 7, 2026.

• FerroxLabs/wayland.claude/skills/architecture