inventory-optimizer

Inventory optimization skill for safety stock, reorder point, and order quantity calculations.

Repositório: a5c-ai/babysitter
Última atividade na origem: 1 de junho de 2026 às 07:46
Idioma detectado do SKILL.md: inglês
Estrelas: 1.652
Forks: 96

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.

npx skills add https://github.com/a5c-ai/babysitter --skill inventory-optimizer

O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.

Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

SKILL.md

Instruções da origem · Visualização somente leitura

Voltar à pesquisa Voltar à instalação

atlas-graph-query

Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)

2026-06-12

atlas

Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real systems, scan your cloud + repos + directories, mine the real processes or data they contain, or collect their real constraints/gotchas. (atlas, scan my systems, inventory our azure account, map my repos, real systems atlas, process mining, data mining, collect nuances, system discovery)

2026-06-12

assimilate-popular-workflows

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.

2026-06-07

Ver todas deste repositório

name	inventory-optimizer
description	Inventory optimization skill for safety stock, reorder point, and order quantity calculations.
allowed-tools	Bash(*) Read Write Edit Glob Grep WebFetch
metadata	{"author":"babysitter-sdk","version":"1.0.0","category":"supply-chain","backlog-id":"SK-IE-025"}
graph	{"domains":["domain:industrial-engineering"],"skillAreas":["skill-area:statistical-analysis","skill-area:organizational-design","skill-area:data-analysis"],"roles":["role:operations-analyst","role:research-engineer"]}

inventory-optimizer

You are inventory-optimizer - a specialized skill for optimizing inventory policies including safety stock, reorder points, and order quantities.

Overview

This skill enables AI-powered inventory optimization including:

ABC/XYZ classification
Economic Order Quantity (EOQ) calculation
Safety stock calculation by service level
Reorder point determination
Periodic review (R,S) policy optimization
Continuous review (r,Q) policy optimization
Multi-echelon inventory optimization
Inventory investment analysis

Capabilities

1. ABC/XYZ Classification

import numpy as np import pandas as pd def abc_analysis(items: pd.DataFrame, value_column: str, quantity_column: str): """ ABC classification based on annual value (Pareto analysis) A: Top 80% of value (typically 20% of items) B: Next 15% of value (typically 30% of items) C: Remaining 5% of value (typically 50% of items) """ # Calculate annual value items = items.copy() items['annual_value'] = items[value_column] * items[quantity_column] items = items.sort_values('annual_value', ascending=False) # Calculate cumulative percentage total_value = items['annual_value'].sum() items['cum_value'] = items['annual_value'].cumsum() items['cum_pct'] = items['cum_value'] / total_value * 100 # Assign ABC class def assign_class(pct): if pct <= 80: return 'A' elif pct <= 95: return 'B' else: return 'C' items['ABC_class'] = items['cum_pct'].apply(assign_class) return items def xyz_analysis(items: pd.DataFrame, demand_history_columns: list): """ XYZ classification based on demand variability X: CV < 0.5 (stable demand) Y: 0.5 <= CV < 1.0 (moderate variability) Z: CV >= 1.0 (high variability) """ items = items.copy() # Calculate coefficient of variation demand_data = items[demand_history_columns] items['mean_demand'] = demand_data.mean(axis=1) items['std_demand'] = demand_data.std(axis=1) items['CV'] = items['std_demand'] / items['mean_demand'] # Assign XYZ class def assign_xyz(cv): if cv < 0.5: return 'X' elif cv < 1.0: return 'Y' else: return 'Z' items['XYZ_class'] = items['CV'].apply(assign_xyz) return items def abc_xyz_matrix(items: pd.DataFrame): """ Create combined ABC-XYZ matrix """ matrix = items.groupby(['ABC_class', 'XYZ_class']).size().unstack(fill_value=0) recommendations = { 'AX': 'High value, stable - continuous review, tight control', 'AY': 'High value, variable - safety stock important, frequent review', 'AZ': 'High value, unpredictable - careful forecasting, higher safety stock', 'BX': 'Medium value, stable - periodic review', 'BY': 'Medium value, variable - moderate control', 'BZ': 'Medium value, unpredictable - consider min-max system', 'CX': 'Low value, stable - simple rules, minimal attention', 'CY': 'Low value, variable - periodic review, simple rules', 'CZ': 'Low value, unpredictable - consider elimination or consignment' } return { "matrix": matrix, "recommendations": recommendations }

def economic_order_quantity(annual_demand: float, ordering_cost: float, holding_cost_per_unit: float): """ Classic EOQ calculation EOQ = sqrt(2 * D * S / H) D: Annual demand S: Ordering cost per order H: Holding cost per unit per year """ eoq = np.sqrt((2 * annual_demand * ordering_cost) / holding_cost_per_unit) # Calculate associated costs orders_per_year = annual_demand / eoq annual_ordering_cost = orders_per_year * ordering_cost average_inventory = eoq / 2 annual_holding_cost = average_inventory * holding_cost_per_unit total_cost = annual_ordering_cost + annual_holding_cost return { "EOQ": round(eoq, 0), "orders_per_year": round(orders_per_year, 1), "order_interval_days": round(365 / orders_per_year, 1), "annual_ordering_cost": round(annual_ordering_cost, 2), "annual_holding_cost": round(annual_holding_cost, 2), "total_relevant_cost": round(total_cost, 2), "average_inventory": round(average_inventory, 0) } def eoq_with_quantity_discounts(annual_demand: float, ordering_cost: float, holding_rate: float, price_breaks: list): """ EOQ with quantity discounts price_breaks: [(min_qty, unit_price), ...] """ results = [] for min_qty, unit_price in sorted(price_breaks, key=lambda x: x[1], reverse=True): holding_cost = unit_price * holding_rate eoq = np.sqrt((2 * annual_demand * ordering_cost) / holding_cost) # Check if EOQ is feasible for this price bracket if eoq < min_qty: order_qty = min_qty else: order_qty = eoq # Calculate total cost orders_per_year = annual_demand / order_qty annual_ordering = orders_per_year * ordering_cost annual_holding = (order_qty / 2) * holding_cost annual_purchase = annual_demand * unit_price total_cost = annual_ordering + annual_holding + annual_purchase results.append({ "min_quantity": min_qty, "unit_price": unit_price, "calculated_eoq": round(eoq, 0), "order_quantity": round(order_qty, 0), "total_annual_cost": round(total_cost, 2) }) # Find optimal optimal = min(results, key=lambda x: x['total_annual_cost']) return { "all_options": results, "optimal": optimal }

inventory-optimizer

Opções de instalação

Revise os arquivos de origem

inventory-optimizer

Overview

Capabilities

1. ABC/XYZ Classification

inventory-optimizer

Overview

Capabilities

1. ABC/XYZ Classification

2. Economic Order Quantity (EOQ)

3. Safety Stock Calculation

4. Reorder Point Determination

5. Continuous Review (r, Q) Policy

6. Periodic Review (R, S) Policy

Process Integration

Output Format

Best Practices

Constraints

inventory-optimizer

Informações da origem

Opções de instalação

Revise os arquivos de origem

Mais deste repositório

Mais deste repositório

inventory-optimizer

Overview

Capabilities

1. ABC/XYZ Classification

inventory-optimizer

Overview

Capabilities

1. ABC/XYZ Classification

2. Economic Order Quantity (EOQ)

3. Safety Stock Calculation

4. Reorder Point Determination

5. Continuous Review (r, Q) Policy

6. Periodic Review (R, S) Policy

Process Integration

Output Format

Best Practices

Constraints