### Install Claude for Office Add-in

Source: https://github.com/anthropics/financial-services/blob/main/claude-for-msft-365-install/README.md

Use these commands to add the plugin to your marketplace and then install it. After installation, run the setup command within the session.

```bash
claude plugin marketplace add anthropics/financial-services
claude plugin install claude-for-msft-365-install@claude-for-financial-services
```

--------------------------------

### Install Core Financial Services Plugin

Source: https://github.com/anthropics/financial-services/blob/main/README.md

Install the core financial analysis skills and connectors. This should be installed before other specific agents or vertical bundles.

```bash
claude plugin install financial-analysis@claude-for-financial-services
```

--------------------------------

### Install Investment Banking Plugin

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/investment-banking/README.md

Install the investment banking plugin by specifying its directory to the claude CLI.

```bash
claude --plugin-dir /path/to/investment-banking
```

--------------------------------

### Install Dependencies and Run with Fake Token

Source: https://github.com/anthropics/financial-services/blob/main/claude-for-msft-365-install/examples/python-bootstrap/README.md

Installs dependencies, generates a fake Entra token for a specific user and group, sets the tenant ID and token as environment variables, and starts the FastAPI application in the background. It also includes a curl command to test the /bootstrap endpoint with the generated token.

```bash
pip install -r requirements.txt
export TENANT_ID=dev-tenant
TOKEN=$(python mint_dev_token.py --oid alice --group investment-banking)
DEV_JWKS_PATH=dev_jwks.json python app.py &
curl -H "Authorization: Bearer $TOKEN" \
     -H "X-Claude-User-Agent: claude-word/1.0.0" \
     http://127.0.0.1:8080/bootstrap
```

--------------------------------

### Install Dependencies

Source: https://github.com/anthropics/financial-services/blob/main/plugins/partner-built/spglobal/skills/funding-digest/SKILL.md

Install the `simple-icons` and `sharp` npm packages. `simple-icons` provides brand SVGs, and `sharp` is used for SVG to PNG conversion.

```bash
npm install simple-icons sharp
```

--------------------------------

### Commit Message Examples

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/financial-analysis/skills/skill-creator/references/output-patterns.md

Provide input/output pairs to guide the generation of commit messages. This pattern is useful when output quality depends on seeing concrete examples of the desired style and detail.

```markdown
## Commit message format

Generate commit messages following these examples:

**Example 1:**
Input: Added user authentication with JWT tokens
Output:
```
feat(auth): implement JWT-based authentication

Add login endpoint and token validation middleware
```

**Example 2:**
Input: Fixed bug where dates displayed incorrectly in reports
Output:
```
fix(reports): correct date formatting in timezone conversion

Use UTC timestamps consistently across report generation
```

Follow this style: type(scope): brief description, then detailed explanation.
```

--------------------------------

### Install Dependencies and Run with Real Tenant

Source: https://github.com/anthropics/financial-services/blob/main/claude-for-msft-365-install/examples/python-bootstrap/README.md

Installs project dependencies, retrieves your Entra tenant ID, sets it as an environment variable, and then runs the FastAPI application.

```bash
pip install -r requirements.txt
# Find your tenant ID:
python get_tenant_id.py you@yourcompany.com
export TENANT_ID=<your-tenant-guid>
python app.py
```

--------------------------------

### Valuation Multiples Verification Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/agent-plugins/pitch-agent/skills/pitch-deck/reference/calculation-standards.md

Example showing how to verify a valuation multiple by dividing the deal value by the relevant metric.

```plaintext
Verify: 436 ÷ 45 = 9.69 ≈ 9.7x ✓
```

--------------------------------

### Example Valuation Range and Recommendation

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/equity-research/skills/initiating-coverage/references/valuation-methodologies.md

Illustrates how to present a valuation range based on different case scenarios (Bear, Base, Bull) and provides an example of a final investment recommendation with a target price.

```plaintext
Bear Case: $38 - $40
Base Case: $42 - $46
Bull Case: $48 - $52

Recommendation: BUY with target price of $45 (midpoint of base case)
```

--------------------------------

### Install Vertical Skill Bundles

Source: https://github.com/anthropics/financial-services/blob/main/README.md

Install bundles of skills tailored for specific financial services verticals, such as investment banking and equity research. These provide specialized capabilities.

```bash
claude plugin install investment-banking@claude-for-financial-services
```

```bash
claude plugin install equity-research@claude-for-financial-services
```

--------------------------------

### Deploy Meeting Prep Agent

Source: https://github.com/anthropics/financial-services/blob/main/managed-agent-cookbooks/meeting-prep-agent/README.md

Set API keys and URLs, then run the deployment script for the meeting-prep-agent.

```bash
export ANTHROPIC_API_KEY=sk-ant-...
export CRM_MCP_URL=... CAPIQ_MCP_URL=...
../../scripts/deploy-managed-agent.sh meeting-prep-agent
```

--------------------------------

### Example Verification Dialogue

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/equity-research/skills/initiating-coverage/SKILL.md

This dialogue demonstrates how Claude, the AI assistant, handles input verification for a user request. It shows the process of checking prerequisites, reporting failures, and guiding the user on next steps.

```dialogue
User: "Use initiating-coverage, Task 5 for Tesla"

Claude: "Starting Task 5: Report Assembly for Tesla

VERIFICATION - Checking prerequisites:
- Task 1 (Company research)... ❌ NOT FOUND
- Task 2 (Financial model)... ❌ NOT FOUND
- Task 3 (Valuation)... ❌ NOT FOUND
- Task 4 (Charts)... ❌ NOT FOUND

⚠️ VERIFICATION FAILED

Task 5 requires ALL previous tasks to be complete.

To proceed:
1. Complete Task 1: Company Research
2. Complete Task 2: Financial Modeling
3. Complete Task 3: Valuation Analysis
4. Complete Task 4: Chart Generation
5. Then return to Task 5

Would you like to start with Task 1 first?"
```

--------------------------------

### Chart Package Structure Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/equity-research/skills/initiating-coverage/references/task4-chart-generation.md

This illustrates the expected file structure within the zip archive containing all generated charts and the chart index. Ensure all required charts and the index file are included.

```bash
[Company]_Charts_[Date].zip
├── chart_01_stock_price_performance.png
├── chart_02_revenue_growth_trajectory.png
├── chart_03_revenue_by_product_stacked_area.png ⭐
├── chart_04_revenue_by_geography_stacked_bar.png ⭐
├── chart_05_company_overview.png
├── ... (all 25-35 chart files)
├── chart_28_dcf_sensitivity_heatmap.png ⭐
├── chart_32_valuation_football_field.png ⭐
├── chart_34_historical_valuation_multiples.png
└── chart_index.txt
```

--------------------------------

### Install Required Libraries for Charting

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/equity-research/skills/initiating-coverage/references/task4-chart-generation.md

Installs essential Python libraries for data visualization and manipulation, including matplotlib, seaborn, pandas, and numpy. Ensure these are installed before proceeding with chart generation.

```bash
pip install matplotlib seaborn pandas numpy plotly
```

--------------------------------

### CAGR Projection Verification Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/agent-plugins/pitch-agent/skills/pitch-deck/reference/calculation-standards.md

Example demonstrating how to verify a CAGR projection by plugging in the values into the formula.

```plaintext
Verify: 22.1 × (1.164)^6 = 22.1 × 2.488 = 55.0 ✓
```

--------------------------------

### Initialize New Skill

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/financial-analysis/skills/skill-creator/SKILL.md

Use this script to create a new skill directory with a template structure. It generates necessary files and directories for a new skill.

```bash
scripts/init_skill.py <skill-name> --path <output-directory>
```

--------------------------------

### Projection Consensus Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/agent-plugins/pitch-agent/skills/pitch-deck/reference/calculation-standards.md

Example of calculating a projection consensus by applying a consensus CAGR to the midpoint of a size range.

```plaintext
Size range: $15-22bn → Midpoint: $18.5bn
CAGR consensus: 16-17%
At 16%: 18.5 × (1.16)^6 = $45.1bn
At 17%: 18.5 × (1.17)^6 = $47.5bn
Consensus projection: $45-48bn
```

--------------------------------

### SKILL.md Structure Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/financial-analysis/skills/skill-creator/SKILL.md

Illustrates the required file structure for a skill, including the YAML frontmatter and markdown body.

```markdown
skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)
```

--------------------------------

### Revenue by Geography Chart Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/equity-research/skills/initiating-coverage/assets/report-template.md

Example regions for a stacked bar chart showing revenue breakdown by geographic region over time.

```text
Example regions:
- North America
- Europe
- Asia-Pacific
- Rest of World
```

--------------------------------

### Sensitivity Analysis Table Setup (Python/openpyxl)

Source: https://github.com/anthropics/financial-services/blob/main/plugins/vertical-plugins/financial-analysis/skills/dcf-model/SKILL.md

Outlines the programmatic approach to creating sensitivity analysis tables using openpyxl. It emphasizes populating every cell with formulas that recalculate the DCF based on varying assumptions.

```python
# CRITICAL: All sensitivity table cells must be populated programmatically with formulas using openpyxl.
# DO NOT use linear approximation shortcuts. DO NOT leave placeholder text or notes about manual steps.
# DO NOT rationalize leaving cells empty because "it's complex" - use a Python loop to generate the formulas.

# Table Setup:
# 1. Create table structure with row/column headers (the assumption values to test)
# 2. Populate EVERY data cell with a formula that:
#    - Uses the row header value (e.g., WACC = 9.0%)
#    - Uses the column header value (e.g., Terminal Growth = 3.0%)
#    - Recalculates the full DCF with those specific assumptions
#    - Returns the implied share price for that scenario
# 3. All cells must contain working formulas when delivered
# 4. Format cells with conditional formatting: Green scale for higher values, red scale for lower values
# 5. Bold the base case cell
# 6. Leave 1-2 blank rows between tables

# No manual intervention required - the sensitivity tables must be fully functional when the user opens the file.
```

--------------------------------

### Size Consensus Range Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/agent-plugins/pitch-agent/skills/pitch-deck/reference/calculation-standards.md

Example of calculating a size consensus range by taking the minimum and maximum values from a set of sources.

```plaintext
Sources: $14.9bn, $18.3bn, $21.1bn, $21.2bn, $22.1bn
Consensus: $15-22bn (rounded to nearest $1bn)
```

--------------------------------

### Market Share Verification Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/agent-plugins/pitch-agent/skills/pitch-deck/reference/calculation-standards.md

Example demonstrating market share verification by dividing segment size by total market size.

```plaintext
Verify: 18 ÷ 65 = 0.277 = 27.7% ≈ 28% ✓
```

--------------------------------

### Install LSEG Plugin

Source: https://github.com/anthropics/financial-services/blob/main/plugins/partner-built/lseg/README.md

Use this command to add the LSEG plugin to your environment. Ensure you have the necessary access and entitlements.

```bash
claude plugins add LSEG
```

--------------------------------

### Build M365 Office Manifest

Source: https://github.com/anthropics/financial-services/blob/main/claude-for-msft-365-install/commands/manifest.md

Use this command to generate the `manifest.xml` file for M365 Office add-ins. Replace `<value>` placeholders with your specific GCP project ID and region. `auto_connect=0` is a common setting.

```bash
node "${CLAUDE_PLUGIN_ROOT}/scripts/build-manifest.mjs" office manifest.xml \
  gcp_project_id=<value> \
  gcp_region=<value> \
  auto_connect=0 \
  ...
```

--------------------------------

### CAGR Consensus Central Cluster Example

Source: https://github.com/anthropics/financial-services/blob/main/plugins/agent-plugins/pitch-agent/skills/pitch-deck/reference/calculation-standards.md

Example of calculating a CAGR consensus by excluding outliers and using the central cluster of growth rates.

```plaintext
Sources: 10.6%, 16.4%, 17.2%, 19.0%, 22.7%
Exclude outliers: 10.6% (low), 22.7% (high)
Central cluster: 16.4%, 17.2%, 19.0%
Consensus: 16-19% or 16-17% (conservative)
```

--------------------------------

### Create Revenue and EPS Chart

Source: https://github.com/anthropics/financial-services/blob/main/plugins/partner-built/spglobal/skills/earnings-preview-beta/report-template.md

Initializes a chart for Revenue and EPS data. This is a partial example and requires the full function definition and data.

```javascript
try {
  createRevEpsChart('chart-rev-eps',
    ['Q1 FY24','Q2 FY24','Q3 FY24','Q4 FY24','Q1 FY25','Q2 FY25','Q3 FY25','Q4 FY25'],
    [152.3, 161.6, 160.8, 173.4, 161.5, 169.3, 165.8, 178.0],  // revenue in $B

```

--------------------------------

### Excel Formula Examples for Ratios

Source: https://github.com/anthropics/financial-services/blob/main/plugins/agent-plugins/model-builder/skills/comps-analysis/SKILL.md

Provides example Excel formulas for calculating core and optional financial ratios, emphasizing division by Revenue.

```excel
// Core ratios - these are always calculated
Gross Margin (F7): =E7/C7
EBITDA Margin (H7): =G7/C7

// Optional ratios - include if relevant
FCF Margin: =[FCF]/[Revenue]
Net Margin: =[Net Income]/[Revenue]
Rule of 40: =[Growth %]+[FCF Margin %]
```