القائمة
Help a user choose the easiest VIVERSE PlayCanvas Toolkit workflow for their current goal, especially when they are unsure which tools they actually need.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Three.js Polygon Streaming .xrg integration and debugging playbook for @polygon-streaming/web-player-threejs, including correct wrapper events, asset publishing, model fitting, and fallback replacement policy
Bundle entry for the exported VIVERSE PlayCanvas Toolkit workflow pack. Use when you want bundled VIVERSE PlayCanvas Toolkit skills, prompts, catalogs, and helper assets in one standalone package.
Collision detection patterns for Three.js games without physics engines
Protect third-party API keys by moving secret-bearing calls into VIVERSE Play Lambda scripts and keeping only non-secret user data in VIVERSE Storage.
Build or fix CPU racing drivers for Three.js or VIVERSE racing games. Use for waypoint loops, tile-to-route reconstruction, lap completion, recovery logic, and low-overhead debug workflows.
VIVERSE Login SDK integration for user authentication and SSO
| name | choose-viverse-workflow |
| description | Help a user choose the easiest VIVERSE PlayCanvas Toolkit workflow for their current goal, especially when they are unsure which tools they actually need. |
| argument-hint | Describe where you edit your world now, what you want to do next, and whether PlayCanvas is part of your workflow |
This skill helps the user pick the simplest path before giving detailed steps.
Treat the user as the end user of the VIVERSE workflow by default. If they invoke this skill directly, do not reinterpret the request as an instruction to maintain or rewrite prompts, skills, or other customization files unless they explicitly ask to edit those files.
Use it first when the user is unsure whether they should:
| If the user says... | Recommended workflow | Primary tools |
|---|---|---|
| "I mostly work in the PlayCanvas web editor" | Editor-first | PlayCanvas Editor, Toolkit extension |
| "My project mostly lives in a folder on my computer" | Local-first | local folder, VIVERSE publish flow |
| "I want to edit locally, but keep PlayCanvas updated" | Hybrid | PlayCanvas sync, PlayCanvas Editor, Toolkit extension or VIVERSE CLI |
| "Build me a world in this folder, no PlayCanvas Editor" | Engine-only local-first | local folder, PlayCanvas Engine via CDN, VIVERSE publish flow |
| "I want to add one leaderboard to my world" | Local-first | local project runtime, leaderboard skill |
| "I only need simple shared multiplayer in one default room" | Local-first | local project runtime, default-room multiplayer skill |
| "I only want to publish what I already built" | Local-first | local build, VIVERSE publish flow |
| "I still need to check scenes or content in PlayCanvas" | Hybrid | PlayCanvas sync plus PlayCanvas validation |
Use this path when:
Recommend:
Use this path when:
Recommend:
Use this path when:
Recommend:
Do not ask the user to choose an engine version, bundler, or module system on this path. Pick safe defaults silently.
Use this path when:
Recommend:
Before going deeper, identify:
If the user's wording is too vague to answer those questions safely, ask in plain language and include a short template such as Main work happens in: PlayCanvas/local folder/both Next goal: keep editing/sync/publish PlayCanvas involved: yes/no.
Do not add questions such as "Do you want the simple route or the complete route?" or "Do you want Toolkit or custom code?" The agent should choose the implementation route.
Do not pre-read downstream skill files, prompt files, or repo memory before making the first workflow choice unless the user explicitly asked for customization maintenance or the initial route genuinely cannot be chosen without one nearby fact. The default first move is a user-facing route, not internal exploration.
When using this skill, return:
When the user directly invokes /choose-viverse-workflow, the immediate next action should be a user-facing workflow step such as asking one clarifying question, routing to one helper, or recommending one safe next action. It should not be reading or editing customization files unless the user explicitly asked for prompt or skill maintenance.
If the route is already clear, stop at the route, reason, next helper, and one immediate next action. Do not begin deep troubleshooting, package archaeology, or process inspection inside this skill.
If the user sounds non-technical, avoid presenting multiple competing routes unless there is a real decision to make.
If the user already has a final folder ready to upload and does not need PlayCanvas to stay in sync, prefer the direct local-to-VIVERSE path.
If the user wants to stay inside the visual PlayCanvas flow and avoid command-line steps, prefer the existing extension upload path.
Treating every local folder as if it were ready for both PlayCanvas sync and final publishing. First decide whether the folder is for editing, syncing, or publishing.
After choosing the path, hand off to the matching skill:
If the user replies with a follow-up such as "continue" right after a clear route, keep the next move short and workflow-specific. For PlayCanvas sync, prefer one forced refresh plus one watch retry before any deeper diagnosis.
