Roblox Collaboration Mode

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

作者 TabooHarmony38826be57ee37bcf023e9c2b85681bea3909281c无许可证收录于 2026年10月9日更新于 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.

仅含说明AI & Agents
AI 生成的概览

在 Roblox 任务前校准智能体的主动程度与审批需求,定义同伴模式与自主模式。

功能
该技能为 Roblox 工作设定行为流程规则,而非领域知识。它帮助判断用户想要协作(同伴模式)还是想要成品(自主模式),并定义应采取的主动程度。它还提供风险表,将低、中、高风险操作对应到适当行为,并给出处理冲突、警告和假设的规则。
适用场景
在任何 Roblox 任务之前加载此技能,包括直接构建请求,并在选择领域技能之前使用。当你需要决定采取多少主动、何时警告而非直接行动,以及哪些决策需要用户明确批准时使用。
运行要求
无需脚本或特殊工具;这是仅含说明的技能。它引用一个可选的模型可读文件 references/full.md 以提供示例。

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]

来源与署名

来源:TabooHarmony/roblox-brain位于skills/core/roblox-collaboration-mode提交38826be

许可证: 无许可证

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架