| Creates professional investment banking strip profiles (company profiles) for pitch books, deal materials, and client presentations. Generates 1-4 information-dense slides with quadrant layouts, charts, and tables.
npx skills add https://github.com/anthropics/financial-services --skill fsi-strip-profile
Data Sources:
Required Metrics:
Normalization:
Before Building:
CRITICAL: You MUST create ONE slide at a time and get user approval before proceeding to the next slide.
For EACH slide:
soffice --headless --convert-to pdf presentation.pptx
pdftoppm -jpeg -r 150 -f 1 -l 1 presentation.pdf slide
YOU MUST CHECK FOR THESE SPECIFIC ISSUES ON EVERY PAGE:
The #1 goal is MAXIMUM information density. A busy executive should understand the entire company story in 30 seconds. Fill every quadrant to capacity.
Per quadrant targets:
Information packing techniques:
If a quadrant looks sparse, add more:
Line spacing - use single textbox per section:
def add_section(slide, x, y, w, header_text, bullets, header_size=10, bullet_size=8):
"""Header + bullets in single textbox with natural spacing"""
tb = slide.shapes.add_textbox(x, y, w, Inches(len(bullets) * 0.18 + 0.3))
tf = tb.text_frame
tf.word_wrap = True
# Header paragraph
p = tf.paragraphs[0]
p.text = header_text
p.font.bold = True
p.font.size = Pt(header_size)
p.font.color.rgb = RGBColor(0, 51, 102)
p.space_after = Pt(6) # Small gap after header
# Bullet paragraphs
for bullet in bullets:
p = tf.add_paragraph()
p.text = bullet
p.font.size = Pt(bullet_size)
p.space_after = Pt(3)
return tb
Key spacing principles:
space_after = Pt(6) after header, Pt(3) between bullets // CORRECT: Single textbox with bullet list - each array item becomes a bullet
// Position in top-left quadrant (Company Overview) - after header with accent bar
slide.addText(
[
{ text: 'Headquarters: Austin, Texas; Founded 2003', options: { bullet: { indent: 10 }, breakLine: true } },
{ text: 'Employees: 140,000+ globally across 6 continents', options: { bullet: { indent: 10 }, breakLine: true } },
{ text: 'CEO: Elon Musk; CFO: Vaibhav Taneja', options: { bullet: { indent: 10 }, breakLine: true } },
{ text: 'Market Cap: $850B (#6 globally by market cap)', options: { bullet: { indent: 10 }, breakLine: true } },
{ text: 'Segments: Automotive (85%), Energy (10%), Services (5%)', options: { bullet: { indent: 10 } } }
],
{ x: 0.45, y: 0.95, w: 4.5, h: 2.6, fontSize: 11, fontFace: 'Arial', valign: 'top', paraSpaceAfter: 6 }
);
// WRONG: Multiple separate textboxes for each bullet - causes alignment issues
// slide.addText('Headquarters: Austin', { x: 0.5, y: 1.0, bullet: true });
Bullet formatting tips:
bullet: { indent: 10 } - controls bullet indentation (smaller = tighter)paraSpaceAfter: 6 - space after each paragraph in pointsSee examples/Nike_Strip_Profile_Example.pptx for layout inspiration. Adapt colors to each company's brand.
Must pass "30-second comprehension test" for a busy executive.
Use 4:3 aspect ratio (standard IB pitch book format):
const pptx = new pptxgen();
pptx.layout = 'LAYOUT_4x3'; // 10" wide × 7.5" tall - MUST USE THIS
PptxGenJS uses inches. 4:3 slide = 10" wide × 7.5" tall.
┌─────────────────────────────────────────────────────────────────┐
│ y=0.2 Title: Company Name (Ticker) │
├────────────────────────────┬────────────────────────────────────┤
│ y=0.6 Company Overview │ y=0.6 Business & Positioning │
│ x=0.3, w=4.7 │ x=5.0, w=4.7 │
│ h=3.0 │ h=3.0 │
├────────────────────────────┼────────────────────────────────────┤
│ y=3.7 Key Financials │ y=3.7 Stock/Recent Developments │
│ x=0.3, w=4.7 │ x=5.0, w=4.7 │
│ h=3.5 │ h=3.5 │
└────────────────────────────┴────────────────────────────────────┘
y=7.5
Company Name (Ticker) - Example: Tesla, Inc. (TSLA)
slide.addText('Tesla, Inc. (TSLA)', { x: 0.3, y: 0.2, w: 9.4, h: 0.35, fontSize: 18, bold: true });
| Quadrant | Position | Content |
|----------|----------|---------|
| 1 | x=0.3, y=0.6, w=4.7, h=3.0 | Company Overview: HQ, founded, key stats, business summary (4-5 bullets) |
| 2 | x=5.0, y=0.6, w=4.7, h=3.0 | Business & Positioning: revenue drivers, products/services, competitive position, growth drivers (4-5 bullets) |
| 3 | x=0.3, y=3.7, w=4.7, h=3.5 | Key Financials: Revenue, EBITDA, margins, EPS, FCF + Valuation (Mkt Cap, EV, multiples) — table OR chart, not both |
| 4 | x=5.0, y=3.7, w=4.7, h=3.5 | For public companies: 1Y stock price chart + top shareholders. For private: Recent developments or Ownership/M&A history |
| Element | Size | Notes |
|---------|------|-------|
| Slide title | 24pt | Bold, company brand color |
| Quadrant headers | 14pt | Bold, with accent bar |
| Body/bullet text | 11pt | Regular weight |
| Table text | 10pt | Use 9pt for dense tables |
| Chart labels | 9pt | Keep labels short |
| Source/footer | 8pt | Bottom of slide |
CRITICAL: If text overflows, REDUCE font size by 1pt and re-render.
Each quadrant header MUST have a colored accent bar to the left:
// Add accent bar for quadrant header
slide.addShape(pptx.shapes.RECTANGLE, {
x: 0.3, y: 0.6, w: 0.08, h: 0.25,
fill: { color: 'E31937' } // Use company brand color
});
slide.addText('Company Overview', {
x: 0.45, y: 0.6, w: 4.5, h: 0.3, fontSize: 14, bold: true, fontFace: 'Arial'
});
Visual elements to include:
For multi-slide profiles: Include 2-3 actual PptxGenJS charts. Never use placeholder divs or static images.
For single-slide profiles: Use tables for financials (more space-efficient). Only add a chart if it replaces the table, not in addition to it.
| Data Type | Chart Type |
|-----------|------------|
| Revenue trends | Line or column (multi-year) |
| Geographic breakdown | Horizontal bar |
| Product mix | Pie with percentages |
| Financial comparison | Column |
| Stock price (1Y daily) | Line |
Horizontal Bar (fits in bottom-right quadrant for 4:3 slide):
slide.addChart(pptx.charts.BAR, [{
name: 'FY2024 Revenue by Region',
labels: ['North America', 'EMEA', 'China', 'APLA'],
values: [21.4, 13.6, 7.6, 6.7]
}], {
x: 5.0, y: 4.1, w: 4.5, h: 3.0, // Fits in bottom-right quadrant (4:3)
barDir: 'bar', chartColors: ['FF6B35'], showValue: true,
dataLabelFontSize: 10, catAxisLabelFontSize: 10, valAxisLabelFontSize: 10,
dataLabelFormatCode: '$#,##0.0B',
title: 'Revenue by Geography', titleFontSize: 12, titleBold: true
});
Pie Chart (fits in bottom-right quadrant for 4:3 slide):
slide.addChart(pptx.charts.PIE, [{
name: 'Product Mix',
labels: ['Footwear', 'Apparel', 'Equipment'],
values: [68, 29, 3]
}], {
x: 5.0, y: 4.1, w: 4.5, h: 3.0, // Fits in bottom-right quadrant (4:3)
showPercent: true, showLegend: true, legendPos: 'r',
dataLabelFontSize: 10, legendFontSize: 10,
chartColors: ['FF6B35', '2C2C2C', '4A4A4A'],
title: 'Revenue Mix FY24', titleFontSize: 12, titleBold: true
});
Line Chart (full width for subsequent slides):
slide.addChart(pptx.charts.LINE, [{
name: 'Revenue ($B)',
labels: ['FY21', 'FY22', 'FY23', 'FY24', 'FY25E'],
values: [44.5, 46.7, 48.5, 51.4, 54.2]
}], {
x: 0.3, y: 1.2, w: 9.4, h: 5.5, // Full width for 4:3 slide
chartColors: ['FF6B35'], showValue: true, lineSmooth: true,
dataLabelFontSize: 11, catAxisLabelFontSize: 11, valAxisLabelFontSize: 11,
title: 'Revenue Trend & Forecast', titleFontSize: 14, titleBold: true
});
Always use native PptxGenJS tables or charts - NEVER plain text prose or HTML tables.
Use slide.addTable() for financial data (fits in bottom-left quadrant for 4:3 slide):
// Add header with accent bar first
slide.addShape(pptx.shapes.RECTANGLE, {
x: 0.3, y: 3.7, w: 0.08, h: 0.25, fill: { color: 'E31937' }
});
slide.addText('Key Financials & Valuation', {
x: 0.45, y: 3.7, w: 4.5, h: 0.3, fontSize: 14, bold: true, fontFace: 'Arial'
});
// Financial data table
slide.addTable([
[{ text: 'Metric', options: { bold: true, fill: '003366', color: 'FFFFFF' } },
{ text: 'FY24', options: { bold: true, fill: '003366', color: 'FFFFFF' } },
{ text: 'FY25E', options: { bold: true, fill: '003366', color: 'FFFFFF' } }],
['Revenue', '$51.4B', '$54.2B'],
['YoY Growth', '+6.0%', '+5.5%'],
['EBITDA', '$8.9B', '$9.5B'],
['EBITDA Margin', '17.3%', '17.5%'],
['EPS', '$3.42', '$3.75'],
['Market Cap', '$185B', '—'],
['EV/EBITDA', '12.5x', '11.7x']
], {
x: 0.45, y: 4.1, w: 4.3, h: 3.0, // Below header in bottom-left quadrant
fontFace: 'Arial', fontSize: 10,
border: { pt: 0.5, color: 'CCCCCC' },
valign: 'middle',
colW: [1.8, 1.25, 1.25] // Column widths
});
❌ Incorrect: Plain text like Note: FY2024 revenue growth +1.0%, Net Income $5.1B...
❌ Incorrect: HTML tables that don't convert properly to PowerPoint
For projections, use Bear/Base/Bull case scenarios in structured tables.
Note: Reference the PPTX skill for PowerPoint file creation.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
Take anthropics/fsi-strip-profile from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.