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.
ma-budget-actual-variance
予算実績差異分析スキル。勘定科目タイプ(収益/費用)に応じた有利・不利差異の自動判定、 差異の分解(価格差異・数量差異)、重要度ランキング、根本原因の仮説提示を行う。CSVデータのアップロードによる自動分析に対応。
Use when: 予算と実績の比較分析を行いたいとき。月次・四半期の予実管理レポート作成、 差異の原因分析、経営会議向けの予実サマリ作成に使用。
Triggers: "予実差異", "予算実績", "budget variance", "budget vs actual", "予算対比", "差異分析", "variance analysis"
含まれるファイル(5)
- SKILL.md7.2 KB
- assets/variance_report_template_en.md2.0 KB
- assets/variance_report_template_ja.md2.1 KB
- references/05_evidence-based-budgeting_20250507.md5.9 KB
- references/08_budget-actual-variance-analysis_20250820.md8.1 KB
SKILL.md(原文)
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。
Budget-Actual Variance Analysis
Overview
Analyzes the differences between budgeted and actual figures, identifying favorable and unfavorable variances with account-type awareness. Provides materiality ranking, root cause hypotheses, and actionable recommendations for management decision-making.
When to Use This Skill
Use this skill in the following scenarios:
- Monthly/Quarterly Budget Review - Compare actual results against budget to identify significant deviations
- 「今月の予実差異を分析して」「月次の予算対比レポートを作成して」
- Management Meeting Preparation - Create executive-level variance summaries with root cause analysis
- 「経営会議向けに予実サマリを作って」「取締役会用の業績報告資料を準備して」
- Cost Overrun Investigation - Identify which line items are over budget and why
- 「コスト超過の原因を特定して」「予算オーバーしている勘定科目を洗い出して」
- Revenue Shortfall Analysis - Determine revenue gaps and contributing factors
- 「売上未達の原因を分析して」「予算未達の要因分解をして」
- Rolling Forecast Adjustment - Use variance trends to update future projections
- 「差異トレンドから今後の見通しを修正して」「ローリングフォーキャストを更新して」
Prerequisites
Before running this skill, ensure the following data is available:
- Budget Data: Approved budget figures by account (CSV or manual input)
- Actual Data: Actual performance figures for the same period
- Account Classification: Each account must be classified as
revenueorcost/expense - Period Information: Target analysis period (month, quarter, or year)
Required CSV Format
account_name,account_type,budget,actual
Sales Revenue,revenue,1000000,1200000
Material Cost,cost,400000,380000
Labor Cost,cost,300000,320000
Required Columns:
| Column | Type | Description |
|---|---|---|
account_name | string | Account or line item name |
account_type | string | revenue or cost (determines favorable/unfavorable logic) |
budget | numeric | Budgeted amount |
actual | numeric | Actual amount |
Workflow 1: Data Preparation
- Validate Input Format: Verify CSV structure and required columns are present
- Classify Accounts: Confirm account type assignments (revenue vs. cost/expense)
- Period Alignment: Ensure budget and actual figures correspond to the same period
- Data Cleansing: Handle missing values, zero budgets, and currency formatting
Workflow 2: Variance Calculation
- Compute Absolute Variance:
Variance = Actual - Budgetfor each line item - Compute Percentage Variance:
Variance % = (Actual - Budget) / Budget * 100 - Determine Direction: Apply account-type-aware favorable/unfavorable logic:
| Account Type | Actual > Budget | Actual < Budget |
|---|---|---|
| Revenue | Favorable (+) | Unfavorable (-) |
| Cost/Expense | Unfavorable (+) | Favorable (-) |
- Materiality Ranking: Sort by absolute variance amount to highlight significant items
- Threshold Flagging: Flag items exceeding materiality threshold (default: 10% or top 5 items)
Workflow 3: Root Cause Analysis
- Pattern Identification: Look for correlated variances (e.g., higher sales + higher variable costs)
- Root Cause Hypotheses: For each material variance, suggest possible explanations:
- Revenue variances: volume changes, pricing changes, product mix shifts, seasonal effects
- Cost variances: input price changes, efficiency changes, activity level changes, one-time items
- Offsetting Analysis: Identify variances that partially cancel each other
- Trend Comparison: Compare current period variance to prior periods if data available
- Action Recommendations: Prioritized corrective actions for unfavorable variances
Output
The analysis produces a structured variance report containing:
- Executive Summary: Total favorable/unfavorable variance, key highlights
- Variance Detail Table: Per-account breakdown with amounts, percentages, and direction
- Materiality Ranking: Top variances sorted by absolute impact
- Root Cause Analysis: Hypotheses and supporting evidence for major variances
- Recommended Actions: Prioritized list of corrective/follow-up actions
Output template: assets/variance_report_template_ja.md (Japanese) or assets/variance_report_template_en.md (English)
Resources
References (load into context for guidance)
references/08_budget-actual-variance-analysis_20250820.md- Comprehensive guide on budget-actual variance analysis methodology with practical bakery business examplesreferences/05_evidence-based-budgeting_20250507.md- Budget planning fundamentals and evidence-based budgeting approaches
Assets (templates for output generation)
assets/variance_report_template_ja.md- Japanese variance analysis report templateassets/variance_report_template_en.md- English variance analysis report template
Best Practices
- Always verify account type classification before calculating variance direction
- Present both absolute amounts and percentages - large percentage on a small base may not be material
- Consider the business context: seasonal patterns, one-time events, and structural changes
- Look for offsetting variances - a favorable cost variance paired with unfavorable revenue may indicate reduced activity
- When budget assumptions have changed significantly, consider rebasing before analysis
- Focus management attention on actionable variances rather than uncontrollable factors
Examples
Example: Bakery Business Monthly Variance
Input Data:
account_name,account_type,budget,actual
Bread Sales,revenue,500000,480000
Cake Sales,revenue,300000,350000
Flour Cost,cost,120000,135000
Sugar Cost,cost,80000,75000
Labor Cost,cost,200000,210000
Rent,cost,100000,100000
Analysis Output (Summary):
- Total Revenue Variance: +30,000 (Favorable) - Cake sales overperformance offsets bread shortfall
- Total Cost Variance: +40,000 (Unfavorable) - Flour cost increase and overtime labor
- Net Variance: -10,000 (Unfavorable)
Key Findings:
- Cake Sales +50,000 (F): New seasonal menu drove demand
- Flour Cost +15,000 (U): Wheat price increase due to supply shortage
- Labor Cost +10,000 (U): Overtime to meet cake demand
- Bread Sales -20,000 (U): Competitor opened nearby - requires strategic response
レビュー
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。
同じリポジトリのスキル
概要と使いどころ
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。