サプライチェーン最適化コンサルティングスキル。需要予測、在庫最適化、調達戦略、 物流ネットワーク設計、S&OP(Sales and Operations Planning)を支援。
Use when optimizing supply chain operations, improving inventory management, designing logistics networks, or conducting supply chain risk assessments. Triggers: "supply chain", "在庫最適化", "inventory optimization", "demand forecasting", "S&OP", "procurement strategy", "logistics network".
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Professional supply chain management consulting: demand forecasting, inventory optimization, procurement strategy, logistics network design, and S&OP.
Primary language: Japanese (default), English supported Frameworks: SCOR (Supply Chain Operations Reference), S&OP best practices, Lean Supply Chain, Theory of Constraints Output format: Supply chain analysis reports, optimization recommendations, S&OP plans, network design proposals
Use this skill when:
SCOR is the global standard for supply chain process modeling (APICS).
SCOR Structure:
Level 1: Process Types
|- Plan: Demand/Supply planning, S&OP
|- Source: Procurement, supplier management
|- Make: Manufacturing, production planning
|- Deliver: Order fulfillment, logistics, warehousing
|- Return: Returns management, reverse logistics
|- Enable: Support processes (IT, finance, HR, quality)
Level 2: Process Categories (30 categories across 6 process types)
Level 3: Process Elements (Detailed activities)
Level 4: Implementation (Company-specific practices)
SCOR Performance Attributes:
Purpose: Improve demand forecast accuracy to reduce stockouts and excess inventory.
Decision Procedure:
Detail: Load
references/demand_forecasting_guide.mdfor formulas, segmentation matrix, KPI dashboard template. Script: Runscripts/generate_demand_kpi_dashboard.pyto generate a KPI dashboard from data.
Purpose: Determine optimal inventory levels to balance cost and service level.
Decision Procedure:
SS = Z * sigma_DLT where sigma_DLT = sqrt(LT * sigma_D^2 + D_avg^2 * sigma_LT^2)sigma_DLT = demand variability over lead time (composite)sigma_D = daily demand std dev, sigma_LT = lead time std dev (days)EOQ = sqrt(2 * D * S / H)ROP = (D_avg * LT) + SSDetail: Load
references/inventory_optimization_guide.mdfor full formulas, worked examples, and policy templates. Script: Runscripts/generate_inventory_policy.pyto generate inventory policy tables from data.
Purpose: Balance demand and supply at aggregate level, align cross-functional plans.
Decision Procedure:
Detail: Load
references/sop_planning_guide.mdfor templates, agenda, and scenario analysis format. Script: Runscripts/generate_sop_agenda.pyto generate a meeting agenda.
Purpose: Optimize distribution network to minimize cost while meeting service level requirements.
Decision Procedure:
Detail: Load
references/logistics_network_guide.mdfor cost templates, scenario analysis, and design recommendation format.
Purpose: Develop strategic sourcing approach to optimize cost, quality, and supply risk.
Decision Procedure:
Detail: Load
references/procurement_strategy_guide.mdfor Kraljic matrix, scorecard templates, and risk mitigation plan format.
Full reference: Load
references/kpi_reference.mdfor all KPIs, benchmarks, best practices, and common pitfalls.
| Area | Key Metric | Target |
|---|---|---|
| Delivery | On-Time Delivery (OTD) | >=95% |
| Delivery | Perfect Order Rate | >=90% |
| Inventory | Inventory Turnover | Industry benchmark |
| Inventory | Days of Inventory | 45-60 days |
| Demand | MAPE | <20% |
| Procurement | Supplier OTD | >=95% |
| Procurement | Supplier Quality | <500 PPM |
| Financial | Supply Chain Cost % Revenue | 8-12% |
このスキルの目的は、組織のサプライチェーンを最適化し、コスト削減とサービスレベル向上を両立させることです。需要予測、在庫管理、S&OP、物流ネットワーク、調達戦略の各領域において、データに基づいた意思決定と継続的改善を推進してください。
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Track and update action item status from natural language updates like 'Seanのメールには返信しておいた' or 'Lu対応予定'. Integrates with daily-comms-ops workflow. Use when managing action items across communication channels.
AI活用提案の専門コンサルタントスキル。LLM・AIエージェントの活用事例知識を基に、業界別、部門別、シーン別に最適なAI導入提案を行います。システム化、業務改善、効率化を得意とし、具体的な活用事例、期待効果、導入ステップを含む実践的な提案を提供します。Use when proposing AI/LLM adoption strategies for specific industries, departments, or business scenarios.
Generate AI-powered BPO service proposals for Japanese companies in the US market. Use when creating outsourcing proposals with AI service menus, ROI estimation, implementation roadmaps, and bilingual (JA/EN) proposal documents for 在米日系企業向けAI実装.
日本語の概要は準備中です。原文の説明を表示しています。
AI（LLM）が生成した日本語テキストの「AI臭」を検出・診断し、人間らしい文章にリライトするスキル。 Use when: 「AIっぽい文章を直して」「人間らしくリライトして」「AI臭を消して」「この文章をもっと自然にして」 「テキストのAI感を減らして」「機械っぽさを取りたい」 "make this sound more human", "remove AI tone", "humanize this text", "detect if this is AI-generated". 6つのAI特有パターン（視覚的マーカー、単調なリズム、マニュアル的構成、非コミット姿勢、抽象語の濫用、 定型メタファー）を正規表現ベースで検出し、0-100のAI臭スコアを算出。3つの人間化技法 （バランスを崩す・客観を崩す・論理を崩す）でリライトを実行する。 Note: 検出スクリプトは日本語テキスト専用。英語テキストの場合はClaude自身がreferences/を参照して分析・リライトする。
Generate audit-ready internal control design documents from As-Is business process inventories. Produces control IDs, assertion mappings, procedures, SoD analysis, KPIs, materiality thresholds, and implementation roadmaps. Use when building internal controls for new audit engagements, SOX/J-SOX compliance, or process improvement initiatives.
日本語の概要は準備中です。原文の説明を表示しています。
Review audit-related documents (control design documents, bottleneck analyses, requirements definitions, etc.) for quality, scoring them 0-100 with a severity-rated findings list. Use when reviewing audit documents, checking control design quality, or verifying cross-document consistency. Supports documents governed by US GAAP, IFRS, or J-GAAP.
日本語の概要は準備中です。原文の説明を表示しています。