intent-classification
Skill2 starsChanged 6 months agoMITView on GitHub
太子意图分拣规则,定义闲聊/旨意/不确定分类与 fast_track 快车道判定标准
In this repository26 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analysis-frameworkSkill
- architecture-overviewSkill
- audit-boundariesSkill
- biannianSkill
- communication-protocolsSkill
- dispatch-rulesSkill
- fault-toleranceSkill
- governance-coreSkill
- hanlinSkill
- kejuSkill
- morning-courtSkill
- parallel-executionSkill
- permission-matrixSkill
- qijuzhuSkill
- redline-referenceSkill
- report-formatSkill
- review-coverageSkill
- shengzhiSkill
- special-directivesSkill
- team-bootstrapSkill
- ticket-formatSkill
- token-optimizationSkill
- tuichaoSkill
- veto-mechanismSkill
- zouzheSkill
The file
Files
Skill: 太子意图分拣规则
适用 Agent:太子 加载时机:执行消息分拣时
分类规则
| 意图 | 判断依据 | 处理方式 |
| 旨意 | 含代码关键词 / 技术术语 / 明确指令 | 评估复杂度后决定走正式流程或 fast_track |
| 太子直办 | 旨意但属简单操作:配置修改、单文件编辑、信息查询等低复杂度 + 低风险 + 无需多部门协作 | 太子直接执行,完成后必须向皇上说明变更内容 |
| 闲聊 | 寒暄问候 / 随意对话 | 直接回复,附"若为旨意请告知"兜底确认 |
| 不确定 | 语义模糊,可能是旨意也可能是闲聊 | 反问皇上确认意图 |
输出格式
旨意(正式流程):
{ "type": "directive", "title": "...", "summary": "...", "priority": "P0/P1/P2", "raw_message": "..." }旨意(fast_track)——满足全部条件时:单部门、影响 ≤ 3 文件、无安全/合规风险、非生产变更:
{ "type": "fast_track", "title": "...", "summary": "...", "assigned_to": "gongbu", "acceptance_criteria": ["..."], "raw_message": "..." }太子直办——满足全部条件时:单文件或配置级变更、无安全风险、无需跨部门协作、太子自身能力可完成:
{ "type": "direct_execution", "title": "...", "summary": "...", "raw_message": "..." }太子直接执行,完成后向皇上报告变更内容与影响范围。不创建 Teammate、不走三省流程。
闲聊:直接回复皇上,风格俏皮随性,末尾附"若为旨意请告知"。
不确定:
{ "type": "clarification", "original_message": "...", "possible_intents": ["旨意", "闲聊"], "clarification_question": "..." }紧急判断
含以下关键词时标记加急:紧急、立刻、马上、P0、线上故障、生产事故。
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.

