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.
financial-analyst
Professional financial analysis skill for investment decisions, budgeting, financial statement analysis, and business plan evaluation. Use this skill when you need to analyze financial ratios (profitability, safety, efficiency), calculate DCF/NPV/IRR valuations, perform budget variance analysis, or conduct sensitivity/scenario analysis. Triggers include "analyze financial statements", "calculate DCF", "investment evaluation", "budget variance", "財務分析", "投資評価", "予算差異分析".
含まれるファイル(11)
- SKILL.md14.3 KB
- assets/budget_variance_template_en.md5.1 KB
- assets/budget_variance_template_ja.md5.2 KB
- assets/financial_report_template_en.md6.0 KB
- assets/financial_report_template_ja.md6.0 KB
- references/dcf_methodology.md7.2 KB
- references/financial_ratios_guide.md8.2 KB
- references/sensitivity_analysis_guide.md8.7 KB
- scripts/financial_analyzer.py34.1 KB
- scripts/tests/__init__.py36 B
- scripts/tests/test_financial_analyzer.py10.5 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。
Financial Analyst
Overview
A comprehensive financial analysis toolkit that enables systematic evaluation of financial health, investment opportunities, and business performance. This skill combines quantitative analysis with professional reporting to support informed decision-making.
Core Capabilities:
- Financial ratio analysis (Profitability, Safety/Liquidity, Efficiency)
- DCF/NPV/IRR investment evaluation
- Budget variance analysis with root cause decomposition
- Sensitivity and scenario analysis for risk assessment
Output Formats:
- Structured analysis reports (Markdown)
- Visualization charts (PNG via matplotlib/seaborn)
- Summary tables with interpretation
Prerequisites
- Python 3.8+ with the following packages:
pandas(for CSV data handling and variance analysis)numpy(for numerical calculations)matplotlib(optional, for visualization charts)
- Input data in JSON or CSV format (see Input Requirements in each workflow)
- Optional: Industry benchmarks for comparative analysis
Workflow
- Gather Input Data - Collect financial statements, cash flow projections, or budget data
- Select Analysis Type - Choose from ratio analysis, DCF evaluation, variance analysis, or sensitivity analysis
- Execute Analysis - Run the appropriate workflow or script command
- Review Results - Interpret metrics, identify areas of concern, compare to benchmarks
- Generate Report - Produce structured output using templates
Output
- Financial Ratio Report (Markdown) - Profitability, safety, and efficiency metrics with interpretations
- DCF Analysis Report (Markdown) - NPV, IRR, payback period, and investment recommendation
- Budget Variance Report (Markdown) - Line-by-line variances with materiality flags
- Sensitivity Analysis - Tornado chart data and scenario comparison tables
- Visualization Charts (PNG) - Radar charts, tornado charts via matplotlib
When to Use This Skill
Use this skill when you need to:
-
Analyze Financial Statements
- "Analyze these financial statements and calculate key ratios"
- "What's the financial health of this company based on their balance sheet?"
- "この会社の財務諸表から収益性を分析してください"
-
Evaluate Investment Opportunities
- "Calculate the NPV and IRR for this investment project"
- "Perform a DCF valuation for this acquisition target"
- "この投資案件のDCF評価を行ってください"
-
Analyze Budget Performance
- "Compare actual vs budget and identify variances"
- "What's causing the budget overrun in Q3?"
- "予算差異分析を行い、原因を特定してください"
-
Assess Risk and Scenarios
- "Run a sensitivity analysis on revenue assumptions"
- "What happens to NPV under different scenarios?"
- "感度分析でリスク要因を評価してください"
Core Workflow 1: Financial Statement Analysis
Analyze financial ratios from structured data to assess company health.
Input Requirements
Accept data in JSON or CSV format:
{
"company": "ABC Corp",
"period": "2024-Q4",
"balance_sheet": {
"total_assets": 100000000,
"current_assets": 40000000,
"cash": 10000000,
"inventory": 15000000,
"receivables": 12000000,
"total_liabilities": 60000000,
"current_liabilities": 25000000,
"long_term_debt": 30000000,
"total_equity": 40000000
},
"income_statement": {
"revenue": 80000000,
"cost_of_goods_sold": 48000000,
"gross_profit": 32000000,
"operating_expenses": 16000000,
"operating_income": 16000000,
"interest_expense": 2000000,
"net_income": 10000000
}
}
Step 1: Load and Validate Data
Read the input file and validate required fields:
- Ensure all balance sheet items are present
- Verify income statement completeness
- Check for negative values that shouldn't be negative
Step 2: Calculate Financial Ratios
Profitability Ratios:
| Ratio | Formula | Interpretation |
|---|---|---|
| ROE (Return on Equity) | Net Income / Total Equity | >15% is generally good |
| ROA (Return on Assets) | Net Income / Total Assets | >5% is acceptable |
| Gross Margin | Gross Profit / Revenue | Industry-dependent |
| Operating Margin | Operating Income / Revenue | >10% is strong |
| Net Profit Margin | Net Income / Revenue | >5% is healthy |
Safety/Liquidity Ratios:
| Ratio | Formula | Interpretation |
|---|---|---|
| Current Ratio | Current Assets / Current Liabilities | >1.5 is healthy |
| Quick Ratio | (Current Assets - Inventory) / Current Liabilities | >1.0 is acceptable |
| Debt-to-Equity | Total Liabilities / Total Equity | <1.0 is conservative |
| Interest Coverage | Operating Income / Interest Expense | >3.0 provides safety margin |
Efficiency Ratios:
| Ratio | Formula | Interpretation |
|---|---|---|
| Asset Turnover | Revenue / Total Assets | Higher is more efficient |
| Inventory Turnover | COGS / Inventory | Higher means faster sales |
| Receivables Turnover | Revenue / Receivables | Higher means faster collection |
| Working Capital Turnover | Revenue / (Current Assets - Current Liabilities) | Measures working capital efficiency |
Step 3: Generate Interpretation
For each ratio:
- Calculate the value
- Classify as: Strong (green), Acceptable (yellow), or Weak (red)
- Provide industry context if available
- Note any significant deviations from norms
Step 4: Visualize Results
Generate a radar chart showing:
- All three ratio categories
- Comparison to benchmarks
- Strengths and weaknesses at a glance
Step 5: Output Report
Use assets/financial_report_template_ja.md or assets/financial_report_template_en.md as the template. Include:
- Executive summary with key findings
- Detailed ratio table with interpretations
- Visualization charts
- Recommendations based on analysis
Core Workflow 2: Investment Evaluation (DCF)
Perform Discounted Cash Flow analysis for investment decisions.
Input Requirements
{
"project_name": "New Factory Investment",
"initial_investment": 50000000,
"projected_cash_flows": [10000000, 15000000, 20000000, 22000000, 25000000],
"terminal_growth_rate": 0.02,
"discount_rate": 0.10,
"analysis_years": 5
}
Step 1: Calculate NPV
NPV = -Initial Investment + Σ(CFt / (1 + r)^t) + Terminal Value / (1 + r)^n
Where:
- CFt = Cash flow at time t
- r = Discount rate
- n = Number of years
Terminal Value Methods:
- Gordon Growth Model: CF_n × (1 + g) / (r - g)
- Exit Multiple: Final Year EBITDA × Industry Multiple
Step 2: Calculate IRR
Find the discount rate where NPV = 0 using Newton-Raphson iteration:
def calculate_irr(cash_flows, guess=0.10, tolerance=0.0001):
rate = guess
for _ in range(100):
npv = sum(cf / (1 + rate)**i for i, cf in enumerate(cash_flows))
if abs(npv) < tolerance:
return rate
derivative = sum(-i * cf / (1 + rate)**(i+1) for i, cf in enumerate(cash_flows))
rate = rate - npv / derivative
return rate
Step 3: Calculate WACC (if components provided)
WACC = (E/V × Re) + (D/V × Rd × (1 - Tc))
Where:
- E = Market value of equity
- D = Market value of debt
- V = E + D
- Re = Cost of equity
- Rd = Cost of debt
- Tc = Tax rate
Step 4: Calculate Payback Period
Simple Payback:
Payback = Years until cumulative cash flow >= initial investment
Discounted Payback:
Payback = Years until cumulative discounted cash flow >= initial investment
Step 5: Investment Decision Criteria
| Metric | Accept Criteria | Interpretation |
|---|---|---|
| NPV | > 0 | Project creates value |
| IRR | > WACC (or hurdle rate) | Returns exceed cost of capital |
| Payback | < Target period | Quick capital recovery |
Refer to references/dcf_methodology.md for detailed methodology.
Core Workflow 3: Budget Variance Analysis
Compare actual results to budget and identify causes.
Input Requirements
Two data files: actual.csv and budget.csv with matching structure:
category,item,amount
Revenue,Product Sales,85000000
Revenue,Service Revenue,15000000
Cost,Material Costs,35000000
Cost,Labor Costs,25000000
Expenses,Marketing,8000000
Expenses,Administration,5000000
Step 1: Calculate Variances
For each line item:
Variance = Actual - Budget
Variance % = (Actual - Budget) / Budget × 100
Classify variances:
- Favorable: Revenue > Budget or Cost < Budget
- Unfavorable: Revenue < Budget or Cost > Budget
Step 2: Decompose Variances
For volume-driven items, decompose into:
- Price Variance: (Actual Price - Budget Price) × Actual Quantity
- Volume Variance: (Actual Quantity - Budget Quantity) × Budget Price
- Mix Variance: For multi-product analysis
Step 3: Identify Material Variances
Flag items where:
- Variance % exceeds threshold (typically 5-10%)
- Absolute variance is significant
- Trend indicates persistent deviation
Step 4: Root Cause Analysis
For each material variance, document:
- Category and item
- Variance amount and percentage
- Potential causes (internal/external)
- Recommended corrective actions
Step 5: Generate Variance Report
Use assets/budget_variance_template_ja.md or assets/budget_variance_template_en.md:
- Summary dashboard with key variances
- Waterfall chart showing variance buildup
- Detailed variance table by category
- Action items and recommendations
Core Workflow 4: Sensitivity and Scenario Analysis
Assess risk by varying key assumptions.
Step 1: Identify Key Variables
Common sensitivity variables:
- Revenue growth rate
- Cost inflation
- Discount rate
- Market size
- Price elasticity
Step 2: Single-Variable Sensitivity
For each key variable:
- Define range: Base ± 10%, ± 20%
- Calculate NPV at each point
- Record results
| Variable | -20% | -10% | Base | +10% | +20% |
|-------------|---------|---------|---------|---------|---------|
| Revenue | $2.1M | $3.5M | $4.8M | $6.2M | $7.5M |
| Costs | $6.5M | $5.7M | $4.8M | $4.0M | $3.1M |
Step 3: Generate Tornado Chart
Rank variables by impact on NPV:
- Calculate NPV swing (high case - low case)
- Sort by swing magnitude
- Visualize as horizontal bar chart
Step 4: Multi-Variable Scenario Analysis
Define scenarios:
- Best Case: Favorable assumptions
- Base Case: Expected assumptions
- Worst Case: Conservative assumptions
For each scenario:
- Set all variable values
- Calculate NPV, IRR, Payback
- Assess probability
Step 5: Break-Even Analysis
Calculate break-even points:
- Revenue required for NPV = 0
- Cost level where IRR = WACC
- Volume needed to recover investment
Refer to references/sensitivity_analysis_guide.md for methodology details.
Python Script Usage
The scripts/financial_analyzer.py provides CLI automation:
Financial Ratio Analysis
python scripts/financial_analyzer.py ratios <input.json> --output report.md --visualize
DCF Valuation
python scripts/financial_analyzer.py dcf <project.json> --discount-rate 0.10 --terminal-method gordon
Budget Variance
python scripts/financial_analyzer.py variance <actual.csv> <budget.csv> --threshold 5
Sensitivity Analysis
python scripts/financial_analyzer.py sensitivity <model.json> --variables revenue,costs --range 20
Best Practices
Data Quality
- Verify source data before analysis
- Standardize formats (currency, units, dates)
- Document assumptions clearly
- Cross-check calculations with known values
Analysis Rigor
- Use multiple metrics - No single metric tells the whole story
- Consider industry context - Benchmarks vary by sector
- Account for timing - NPV is time-sensitive
- Stress test assumptions - Challenge optimistic projections
Reporting
- Lead with key findings - Executive summary first
- Visualize data - Charts communicate faster than tables
- Provide recommendations - Analysis should drive action
- Document limitations - Be transparent about uncertainties
Resources
Scripts
scripts/financial_analyzer.py- Main analysis automation script
References
references/financial_ratios_guide.md- Detailed ratio definitions and benchmarksreferences/dcf_methodology.md- DCF calculation methodologyreferences/sensitivity_analysis_guide.md- Sensitivity/scenario analysis guide
Templates
assets/financial_report_template_ja.md- Japanese financial report templateassets/financial_report_template_en.md- English financial report templateassets/budget_variance_template_ja.md- Japanese variance report templateassets/budget_variance_template_en.md- English variance report template
Quick Reference
Financial Ratio Formulas
| Category | Ratio | Formula |
|---|---|---|
| Profitability | ROE | Net Income / Equity |
| Profitability | ROA | Net Income / Assets |
| Profitability | Gross Margin | Gross Profit / Revenue |
| Profitability | Operating Margin | Operating Income / Revenue |
| Safety | Current Ratio | Current Assets / Current Liabilities |
| Safety | Quick Ratio | (Current Assets - Inventory) / Current Liabilities |
| Safety | D/E Ratio | Total Debt / Equity |
| Efficiency | Asset Turnover | Revenue / Assets |
| Efficiency | Inventory Turnover | COGS / Inventory |
Investment Metrics
| Metric | Accept If | Reject If |
|---|---|---|
| NPV | > 0 | < 0 |
| IRR | > WACC | < WACC |
| Payback | < Target | > Target |
Variance Classification
| Variance Type | Favorable | Unfavorable |
|---|---|---|
| Revenue | Actual > Budget | Actual < Budget |
| Cost | Actual < Budget | Actual > Budget |
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。