- Home
- Skills
- Agents & Orchestration
- 督办风险排查 · Risk Supervisor
督办风险排查 · Risk Supervisor
把待办事项按风险督办:识别延期隐患、划分责任人、给出排查清单与升级路径,让问题在变大前被看见。 Supervise pending work by risk: spot delay risks, assign owners, and produce checklists and escalation paths before problems grow.
$7
Works with the AI tools you already use
督办风险排查 · Risk Supervisor
Example session with this skill installed
下周五要上线,现在有12个跨部门待办,帮我做一次风险督办,重点是哪些会拖累上线。
- Read your context and instructions
- Compiled the risk supervisor
督办结论
12 个待办中:高风险 3 个、中风险 4 个、低风险 5 个。最可能拖累上线的是「支付渠道联调」「法务条款确认」「压测环境申请」三项,建议今天逐一催办。
一、高风险督办清单
| 待办 | 责任人 | 截止 | 风险说明 | 升级人 |
|---|---|---|---|---|
| 支付渠道联调 | 王@技术 | 本周二 | 已延期 2 天,阻塞主流程 | 张@技术总监 |
| 法务条款确认 | 李@法务 | 本周三 | 未开始,上线前必须完成 | 刘@VP |
| 压测环境申请 | 赵@运维 | 本周二 | 依赖审批,排队中 | 孙@运维经理 |
二、中风险跟进
- 文案终稿:已完成 70%,周三可交付,暂不阻塞;
- 客服话术培训:安排在周四,若上线提前会冲突;
- 埋点验收:依赖联调环境,与高风险项联动;
- 灰度方案评审:会议未约,需今天定时间。
三、催办话术示例
「王哥,支付联调延期 2 天了,它是上线主流程的必经项。今天下班前能确认卡点吗?如果资源不够,我拉张总监一起对齐。」
四、升级规则
- 高风险项延期超过 1 天 → 自动上报升级人;
- 同一责任人有 2 个高风险项 → 协调拆给他人;
- 上线前 48 小时仍有高风险未关闭 → 触发延期决策会。
下一步
- 今天 15:00 前向三个高风险责任人发催办;
- 约灰度方案评审会,时间定今天;
- 明早重新跑一遍督办,更新风险等级。
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
它解决什么问题
项目里的风险不是突然爆发的,而是没人盯的待办慢慢拖成事故:节点过了没人追、问题发现了没人跟、责任分不清。直接问 AI 排查,常给一堆泛泛的「注意沟通」。
这个技能做什么
先收集待办清单与项目背景,再按「影响 × 发生概率」给每项打风险等级,识别延期隐患与阻塞点;输出督办清单:责任人、截止时间、排查问题与升级路径,高风险项附追问话术。
为什么比裸提示词强
- 分级督办:高中低风险分别对待。
- 责任到人:每项有责任人、截止与升级人。
- 带追问:给出催办话术,不靠吼推进。
典型用例
- 每周例会前排查项目风险点。
- 跨部门待办的交期督办。
- 上线前集中排查阻塞项。
局限
依赖你提供的待办与背景信息;无法自动读取项目工具,涉及人事与合规的风险请由负责人确认。
English · 英文介绍
The problem
The risks in the project do not suddenly erupt, but the to-do items that no one is paying attention to gradually turn into accidents: no one pursues after the node is passed, no one follows the problem when it is discovered, and the responsibilities are unclear. Asking the AI directly for troubleshooting often results in a bunch of general "pay attention to communication."
What it does
First collect the to-do list and project background, and then assign a risk level to each item according to "impact × probability of occurrence" to identify potential delays and blocking points; output a supervision list: responsible person, deadline, troubleshooting and escalation path, and follow-up questioning skills for high-risk items.
Why is it better than naked prompt words?
- Graded supervision: high, medium and low risks are treated separately.
- Responsibility assigned to each person: person responsible for each item, deadline and upgrade person.
- Follow-up questions: Give prompting words and do not rely on yelling to advance.
Typical use cases
- Check project risk points before weekly meetings.
- Supervise the delivery of cross-department pending tasks.
- Focus on troubleshooting blocking items before going online.
Limitations
Relies on the to-do and background information you provide; project tools cannot be automatically read, and risks involving personnel and compliance should be confirmed by the person in charge.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- Passed all security checks, Safe to install