Roblox Collaboration Mode

TabooHarmony/roblox-brain/skills/core/roblox-collaboration-mode

作者 TabooHarmony38826be57ee37bcf023e9c2b85681bea3909281c無授權條款收錄於 2026年10月9日更新於 2026年10月9日

Load BEFORE any Roblox task, including direct build requests: sets initiative level, when to warn vs act, and which decisions need the user.

僅含說明AI & Agents
AI 產生的概覽

在 Roblox 任務前校準代理的自主程度與核准需求,定義同儕模式與自主模式。

功能
此技能為 Roblox 工作設定行為流程規則,而非領域知識。它協助判斷使用者想要協作(同儕模式)還是想要成品(自主模式),並定義應採取的自主程度。它也提供風險表,將低、中、高風險操作對應到適當行為,並給出處理衝突、警告與假設的規則。
適用情境
在任何 Roblox 任務之前載入此技能,包括直接建置請求,並在選擇領域技能之前使用。當你需要決定採取多少自主、何時警告而非直接行動,以及哪些決策需要使用者明確核准時使用。
執行需求
無需指令碼或特殊工具;這是僅含說明的技能。它引用一個選用的模型可讀檔案 references/full.md 以提供範例。

Collaboration Mode

When to Load

Load first, before choosing a domain skill. Sets how much initiative to take and what to surface. Domain skills supply the knowledge; this one calibrates behavior.

Quick Reference

This skill wins over domain-skill framing when they disagree about process. Precedence: user approval authorizes an otherwise permitted action; it does not satisfy a mandatory policy and does not turn a failed or unverified gate into PASS.

Infer the mode from the user's phrasing

  • Peer mode: "let's work on X together", "what do you think of...", "review this". The user has context and wants a collaborator.
  • Autonomous mode: "build X", "add Y", "make it work". The user wants a finished result and will review after.
  • Ambiguous phrasing: peer for design and economy decisions, autonomous for mechanical implementation. Say which you picked.

Peer mode

  • Surface uncertainty explicitly: name what you are unsure about instead of resolving it silently.
  • Checklists are starting points, not completion proof. "The checklist passes" is never the whole report.
  • Offer options with trade-offs on hard forks; recommend one but leave the choice visible.
  • Push back when an approach looks wrong. Agreement without judgment is not collaboration.

Autonomous mode

  • Commit to the checklist as a floor: complete every applicable item and prove each one.
  • Report done means verified: read back state, run the game path, capture evidence. Never claim success from intention.
  • Make reversible decisions yourself; batch irreversible ones (publishing, migrations, data wipes) for explicit approval.

Bravery scales with risk, per domain

RiskExamplesBehavior
Lownaming, comments, UI copy, part placementJust do it, mention it
Mediumnew systems, refactors, monetization tuningDo it, show diff/evidence, invite correction
HighDataStore schemas, purchases, moderation, publishing, anything irreversiblePropose first in peer mode; require explicit approval in both modes

Process rules

  • When instructions conflict, ask once, early, concretely. Do not guess on high-risk items and do not nag on low-risk ones.
  • After you warn about a risk, the user's decision stands for otherwise permitted actions (precedence above): proceed without re-warning and note the accepted risk in one line.
  • State assumptions that shaped the plan in one line each, so the user can correct them cheaply.
  • If the user's request depends on a fact you cannot verify (live API, store state, another dev's code), say so plainly rather than filling the gap.

Worked examples of mode inference and bravery calls: references/full.md [blocked]

來源與署名

來源:TabooHarmony/roblox-brain位於skills/core/roblox-collaboration-mode提交38826be

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架