agentleFS
JingHao-LeonJingHao-Leon/fde-case-lab/skills/state-reminder/SKILL.md

state-reminder

Skill0 starsChanged 2 months agoMITView on GitHub

履约/工单状态机与 SLA 超时提醒——把"每天人工翻表催人"改成"系统拉出今日待办,人只处理逾期项"。当用户要"自动跟进/催办/履约追踪"时使用。

The file

Files
SKILL.md

State Reminder · 履约状态机与 SLA 提醒

对应案例:NO.5(达人履约 30 天→18 天)、NO.13(维保工单复用与路由)。 参考实现:cases/05-influencer-crm/(漏催归零、履约周期 -34%)。

何时使用

  • 运营每天人工翻 Excel 找"谁到期了",漏催频繁
  • 履约/工单有明确阶段(建联→寄样→收样→创作→提交),各阶段应有停留上限
  • 要把人的精力从"找人"转移到"处理逾期"

流程

  1. 状态机定义:与业务确认阶段序列与每阶段 SLA(如建联 3 天/寄样 4 天/ 收样 3 天/创作 7 天);SLA 是业务规则,Agent 不擅自设定。
  2. 历史复盘校准:用历史轨迹统计各阶段实际停留分布,验证 SLA 合理 (P50/P90),并找出"惯发问题"(案例 13:某些设备每月重复同样异常)。
  3. 每日待办生成:状态停留超 SLA → 待办项(对象/阶段/逾期天数/建议动作), 按逾期天数排序;全量扫描,不存在漏看。
  4. 复用推荐(工单场景):检索对象近 N 期历史,最常见 (描述, 处置) 作为 自动填充建议;新对象回退到类型规则,再无 → 人工。
  5. 提醒分级:首轮自动提醒;超期未动 → 升级人工跟进。高价值对象的 实际沟通永远留给人(案例 5:一句话说错的损失远超自动化收益)。
  6. 效果基线:上线前记录人工耗时与履约周期,上线后对比(案例 22 的 效果基线纪律)。

验收

  • 全量扫描下 SLA 漏提醒 = 0
  • 待办排序正确(逾期降序)、SLA 计算与定义一致
  • 履约周期对比基线可量化(案例 5 实测 -34%)

边界

  • 提醒文案触达达人/客户前的措辞由人审核
  • 催办升级规则(几次提醒升级、谁接手)由业务定

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.