Skills Plugins MCP Prompt Model 博客 我的中心

mfg-production-planning

Design production plans using MPS (Master Production Schedule), MRP (Material Requirements Planning), and capacity planning. Use this skill when the user needs to schedule production, plan material procurement, balance capacity with demand, or optimize production sequencing — even if they say 'we can't keep up with orders', 'when should we order materials', 'production scheduling', or 'how do we plan for next quarter's demand'.

DeepseekModel 官方收录技能 质量 优秀 · 78 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=asgard-ai-platform-skills-mfg-production-planning-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name mfg-production-planning description Design production plans using MPS (Master Production Schedule), MRP (Material Requirements Planning), and capacity planning. Use this skill when the user needs to schedule production, plan material procurement, balance capacity with demand, or optimize production sequencing — even if they say 'we can't keep up with orders', 'when should we order materials', 'production scheduling', or 'how do we plan for next quarter's demand'. metadata {"category":"WP-03 製造業","tags":["manufacturing","production-planning","mrp","scheduling"]} Production Planning (MPS/MRP) Framework IRON LAW: Plan Hierarchically — Demand → MPS → MRP → Shop Floor Production planning flows TOP-DOWN: 1. Demand forecast / customer orders → what to make, when 2. MPS → master schedule for finished goods 3. MRP → material and component requirements (what to buy, when) 4. Shop floor scheduling → which machine, which sequence Skipping levels (going from demand forecast directly to shop floor) creates chaos — material shortages, capacity conflicts, missed deliveries. Planning Hierarchy Level Plan Horizon Granularity Decides Strategic S&OP (Sales & Operations Planning) 12-18 months Monthly, product family Capacity investments, workforce planning Tactical MPS (Master Production Schedule) 3-6 months Weekly, end product What to produce each week Operational MRP (Material Requirements Planning) 4-12 weeks Daily, component/material What to order, when, how much Execution Shop Floor Scheduling 1-2 weeks Hourly, work center Sequence, machine assignment MPS Process Inputs : Demand forecast + customer orders + current inventory + safety stock targets Logic : For each week, calculate: Production Needed = Demand - Beginning Inventory - Scheduled Receipts + Safety Stock Output : Planned production quantities by week for each finished product Constraint : Must not exceed available capacity (rough-cut capacity planning check) MRP Process Inputs : MPS (what to make) + BOM (Bill of Materials — what it's made of) + Inventory status + Lead times Logic : "Explode" the BOM — for each finished good, calculate when each component/material must be ordered to arrive in time Output : Planned purchase orders and production orders with dates and quantities Key calculation : Order date = Need date - Lead time Scheduling Algorithms Algorithm Rule Best When FCFS (First Come First Served) Process in order received Low complexity, fairness matters SPT (Shortest Processing Time) Shortest job first Minimize average flow time EDD (Earliest Due Date) Most urgent due date first Minimize late deliveries Bottleneck-first Schedule the constraint first, subordinate rest Capacity-constrained environments (TOC logic) SMED (Single-Minute Exchange of Die) Reduce changeover time to increase flexibility: Separate internal setup (machine stopped) from external (can do while running) Convert internal to external where possible Streamline remaining internal steps Practice and standardize Output Format # Production Plan: {Product/Period} ## Demand vs Capacity | Week | Demand | Available Capacity | Gap | |------|--------|-------------------|-----| | W1 | {units} | {units} | {+/-} | ## Master Production Schedule | Week | Product A | Product B | Product C | Total | |------|----------|----------|----------|-------| | W1 | {units} | {units} | {units} | {units} | ## Material Requirements | Material | Quantity | Order Date | Supplier | Lead Time | |----------|---------|-----------|----------|-----------| | {material} | {qty} | {date} | {supplier} | {days} | ## Scheduling | Work Center | Mon | Tue | Wed | Thu | Fri | |------------|-----|-----|-----|-----|-----| | {center} | {job} | {job} | ... | ... | ... | Gotchas Forecast accuracy limits everything : MPS/MRP is only as good as the demand forecast. Track forecast accuracy (MAPE) and build safety stock proportional to forecast error. Lead time variability kills plans : If supplier lead time is "2-6 weeks" (4 week variability), you need safety stock for the worst case. Reduce variability through supplier management. BOM accuracy is critical for MRP : A wrong BOM means ordering wrong materials. Audit BOMs quarterly. Frozen zone : The first 1-2 weeks of MPS should be "frozen" (no changes) to allow stable execution. Changes inside the frozen zone cascade chaos through the system. Finite vs infinite capacity : Basic MRP assumes infinite capacity (ignores machine constraints). Always layer a capacity check (rough-cut or detailed) on top of MRP output. References For S&OP process design, see references/sop-process.md For demand forecasting methods, see references/demand-forecasting.md
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。