vuaassistant-dev-guidelines

Enforces development standards, verification levels, and release rules for the VuaAssistant Tauri desktop repository.

1|Updated Jul 10, 2026
One-click install
npx skills add https://github.com/360org/vuaassistant --skill vuaassistant-dev-guidelines-360org
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vuaassistant-dev-guidelines
Source: https://github.com/360org/vuaassistant/tree/main/.agents/skills/vuaassistant-dev-guidelines
Command: npx skills add https://github.com/360org/vuaassistant --skill vuaassistant-dev-guidelines-360org

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents AI agents and developers from making changes to the VuaAssistant repository that contradict the product vision, skip real verification, or break working subsystems like the AI Router sidecar and agent-runner. ## Core Features & Use Cases - Product-idea alignment guard: Requires reading idea.md before proposing changes, with hard rules such as subscription-first OAuth login, no Bash/Terminal exposure to models, and an internal AES-256 Vault. - Three-level verification workflow: Mandates compile checks, tests, and real hands-on testing of the macOS app before reporting any task as done. - Sidecar and release discipline: Covers agent-runner TypeScript builds, better-sqlite3 native module version matching, background process supervision with restart caps, and PO-controlled version tagging. - Use Case: Before refactoring the sign-in screen, an agent loads this skill, confirms the current OAuth-first connection order is intentional per idea.md, and avoids a costly incorrect rewrite. ## Quick Start Load the vuaassistant-dev-guidelines skill before modifying anything in the vuaassistant repository and follow its verification and release rules.

Frequently Asked Questions about vuaassistant-dev-guidelines

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify changes in a Tauri desktop app before reporting done?▼

Run three verification levels in order: npx tsc --noEmit and cargo check for compilation, npm run check for logic tests, then npm run tauri dev or npm run build:local to operate the real macOS app UI. Only level three proves the product works.

How should the agent-runner sidecar be rebuilt after editing its source?▼

Compile it with npx tsc --project agent-runner/tsconfig.json or npm run build:runner after changing agent-runner/src. Ensure better-sqlite3 matches the running Node version, and avoid blind npm rebuild since a failed rebuild deletes the working binding.

Why does better-sqlite3 cause a NODE_MODULE_VERSION mismatch crash loop?▼

The native module was compiled against a different Node version than the one running the runner, so the binary binding fails to load. Upgrading the package version is safer than rebuilding in place, which can destroy the existing working binding.

Can I tag a release version after fixing a bug in this repository?▼

No. Record the change in CHANGELOGS.md under [Unreleased] and commit it, but never tag versions for individual fixes. Release tags and builds happen only when the product owner explicitly commands it.

Should background sidecar processes be restarted automatically when they die?▼

Yes. Every sidecar such as the AI Router must have periodic health checks, automatic restart with a capped retry count, and log dumps on failure. UI retry buttons must respawn the actual process, not just re-call the HTTP API.