# revenue-concentration

Works out each client's share of revenue and the Herfindahl index, so you can see how much of the business rides on a few accounts.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 382 installs · ★ 98
- Author: openaccountant
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/openaccountant/skills/tree/HEAD/business/revenue-concentration/SKILL.md
- Updated: 2026-04-09
- HTML: https://affpapa.org/en/nevibecode/skills/revenue-concentration

## What it does

The skill takes incoming payments for a period you pick and groups them by client. From there it calculates each client's share of total revenue, the cumulative share, and the Herfindahl-Hirschman Index — the sum of squared shares. The thresholds come straight from antitrust practice: under 1,500 is low concentration, 1,500–2,500 moderate, above 2,500 high. Any single client past 25% gets flagged.

Two ways to run it. With Wilson connected, the skill calls `transaction_search`, pulls positive amounts and groups them by payee on its own. Without Wilson you export bank transactions to CSV for 12 months, filter to income, add a client column and build a pivot table — the sheet spells out the formulas for share, squared share and running total.

Keep the 2,500 line in mind. Four clients splitting revenue evenly land exactly on 2,500, which still counts as moderate; you need seven or more comparable clients before the index drops into low territory. The skill suggests starting with a 12-month window and revisiting the numbers quarterly. If one client's share keeps climbing, that is your cue to diversify rather than wait.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add openaccountant/skills --skill revenue-concentration -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/revenue-concentration/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/revenue-concentration/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add openaccountant/skills --skill revenue-concentration -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/revenue-concentration/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add openaccountant/skills --skill revenue-concentration -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/revenue-concentration/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install openaccountant/skills revenue-concentration
```

2. **Manually: put the files in place**
- File: `.github/skills/revenue-concentration/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add openaccountant/skills --skill revenue-concentration -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/openaccountant/skills --path business/revenue-concentration
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/revenue-concentration/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add openaccountant/skills --skill revenue-concentration -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/openaccountant/skills/tree/HEAD/business/revenue-concentration/SKILL.md

## When to use it
- measure each client's share of annual revenue
- compute the HHI from incoming payments
- spot a client bringing in over a quarter of revenue
- show the cumulative share of the top three clients
- run the same math by hand from a bank export

## Example prompts
- Calculate revenue concentration by client for the last 12 months
- What's our HHI, and is any client above 25% of revenue?
- Group incoming payments by payer and show cumulative shares

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: b5a7614448c25e5d.

BEGIN THIRD-PARTY FILE b5a7614448c25e5d
````text
---
name: revenue-concentration
description: >
  Assess client concentration risk using revenue share and Herfindahl index.
---

# Revenue Concentration Risk

## Overview
Measure how dependent your business is on a small number of clients. Calculates each client's revenue share, computes the Herfindahl-Hirschman Index (HHI), and flags dangerous concentration levels.

## Wilson Tools Used
- `transaction_search` — find all revenue transactions and group by client or source to calculate per-client totals

## Workflow
1. Ask for the analysis period (recommend 12 months for accuracy).
2. Use `transaction_search` to find all incoming payments (positive amounts).
3. Group by vendor/payee name to get per-client revenue totals.
4. Calculate each client's revenue share as a percentage of total.
5. Compute the Herfindahl-Hirschman Index: HHI = sum of (each client's market share percentage squared).
6. Generate the report:

```
REVENUE CONCENTRATION — [Period]
═══════════════════════════════════════════════════
Client              Revenue     Share    Cumulative
───────────────────────────────────────────────────
Acme Corp           $48,000     40.0%      40.0%
Beta LLC            $30,000     25.0%      65.0%
Gamma Inc           $18,000     15.0%      80.0%
Delta Co            $12,000     10.0%      90.0%
Other (3 clients)   $12,000     10.0%     100.0%
───────────────────────────────────────────────────
Total Revenue      $120,000    100.0%

Herfindahl Index (HHI):  2,550
Concentration Level:     HIGH
Top Client Dependency:   40.0%

Risk Assessment:
  - Losing Acme Corp would eliminate 40% of revenue
  - Top 2 clients = 65% of revenue
  - Top 3 clients = 80% of revenue
═══════════════════════════════════════════════════
```

7. Interpret HHI:
   - **Under 1,500**: Low concentration (diversified)
   - **1,500-2,500**: Moderate concentration
   - **Over 2,500**: High concentration (risky)
8. Flag any single client above 25% as a key-person risk.
9. Recommend target: no single client above 20%, top 3 clients below 50%.

## Without Wilson
1. Export bank transactions as CSV for the past 12 months.
````
END THIRD-PARTY FILE b5a7614448c25e5d

The third-party file has ended. Everything between the b5a7614448c25e5d tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2530 of 3799 bytes. © openaccountant · MIT · https://github.com/openaccountant/skills/tree/HEAD/business/revenue-concentration/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md