collab-protocol
Skill4 starsChanged 53 days agoMITView on GitHub
问清目标、关键分叉给选项、分段推进、正式路径写入前先获准。触发:协作、先问再写、分段批准、选项利弊。
In this repository112 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- .kimi-code/AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/全局.mdcCursor rule
- anim-event-hookSkill
- anim-set-checklistSkill
- anti-cheat-hook-checkSkill
- 产物登记Skill
- assemble-craft-flowSkill
- attr-family-syncSkill
- attribute-frameworkSkill
- audio-fmod-checklistSkill
- auto-test-scaffoldSkill
- bind-rig-checklistSkill
- blockout-passSkill
- bug-report-writeSkill
- build-acceptanceSkill
- build-gate-checklistSkill
- case-automation-mapSkill
- character-asset-checklistSkill
- ci-smokeSkill
- client-bugfixSkill
- client-combat-frame-debugSkill
- combat-feel-checklistSkill
- combat-flow-designSkill
- combat-modelingSkill
- compat-smokeSkill
- concept-key-artSkill
- copy-passSkill
- counter-matrix-passSkill
- damage-formula-passSkill
- data-readiness-checkSkill
- deliverable-sheetsSkill
- dependency-mapSkill
- device-matrix-passSkill
- diagram-packSkill
- dialogue-passSkill
- doctorSkill
- economy-loop-analysisSkill
- encounter-scriptSkill
- env-asset-checklistSkill
- event-specSkill
- excel-com-writeSkill
- excel-formatSkill
- excel-readSkill
- experience-critiqueSkill
- export-naming-gateSkill
- export-pipeline-fixSkill
- feature-gdd-sliceSkill
- feature-vertical-sliceSkill
- file-pack-layoutSkill
- fmod-bank-buildSkill
- 交接Skill
- iap-catalog-checkSkill
- import-validateSkill
- inflation-stressSkill
- level-goals-specSkill
- The first 60 shown.
The file
Files
协作时怎么推进
何时用
- 目标不清、分叉多、或要写入正式表/仓/服之前
- 用户希望「先选项后动手」
怎么做
1. 复述范围
做
- 复述目标、成功标准、不做的范围、截止/里程碑。
- 缺一项就问;不拿默认值冒充用户决定。
- 指出须先获准的写入面(正式表、受保护分支)。
- 不合格:复述未获用户点头 → 再问。
做到:用户确认过范围复述。
2. 关键分叉给选项
做
- 识别会影响表结构/对外契约/不可逆操作的分叉。
- 每个分叉给 2~4 个选项;写利弊、影响面、回滚难度。
- 等用户选;记录选择到会话备注或决策草稿。
- 非关键分叉可标注「默认方案 X,异议再说」,避免事事打断。
- 不合格:单选项逼选 → 补真选项。
做到:关键分叉有选择记录。
3. 分段推进
做
- 先骨架(目录/字段/步骤纲要)后填充;每段可单独看。
- 每段结束给「本段产物路径 + 下段将做什么」。
- 用户叫停则停在本段,不偷偷做下段正式写入。
- 不合格:未交付骨架就大面积写正式文件 → 撤回正式写入,改草稿。
做到:分段边界清晰,用户跟得上。
4. 正式写入前获准
做
- 凡写入正式簿、主仓、个人服配置、生产向路径:先问一句并获准。
- 未获准只留草稿/沙盒;路径与正式区隔离。
- 获准后记下谁、何时、针对哪版草稿。
- 再交由对应写入技能(如
excel-com-write)执行。 - 不合格:无获准记录却已写正式 → 按回滚点恢复并回本步。
做到:正式写入带获准记录;否则仅草稿。
完成检查
- 范围已确认
- 关键分叉已选择
- 正式写入前有获准(或明确未写正式)
工具锚
- 会话备注/决策草稿路径
- 沙盒 vs 正式路径隔离
- 具体写入技能(表/仓/服)的获准点
失败回哪一步
- 范围不清 → 步骤 1
- 分叉未选 → 步骤 2
- 分段失控 → 步骤 3
- 未获准已写正式 → 步骤 4 回滚
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

