# next-best-action

This skill designs next-best-action engines that watch client data for portfolio, life, market and compliance events and tell advisors what to do next.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 680 installs · ★ 218
- Author: JoelLewis
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/JoelLewis/finance_skills/tree/HEAD/plugins/advisory-practice/skills/next-best-action/SKILL.md
- Updated: 2026-07-18
- HTML: https://affpapa.org/en/nevibecode/skills/next-best-action

## What it does

The skill walks through how a recommendation engine for financial advisors is put together. It monitors client data across custodial feeds, CRM records, financial plans, compliance calendars and market data, spots events, and suggests a specific action. Unlike a plain task list, it works proactively: the advisor does not have to remember who to call, the system hands over a recommendation with context attached.

Five event categories are covered. Portfolio events include drift past the tolerance band, a large cash movement, a position that grew past a concentration threshold, a tax-loss harvesting opening, an RMD deadline and a margin call. Life events cover birthday milestones such as 59-1/2 or 73, marriage, divorce, death of a spouse, a new child, a job change or retirement. Market events cover a drawdown in a sector the client holds, a rate move affecting fixed income, and a new fund replacing a current holding. From there the skill covers action identification, prioritization across the whole book, routing to the right team member, delivery and outcome tracking.

A margin call needs margin balance and equity data from the custodian; tax-loss harvesting needs lot-level cost basis. Without those feeds some triggers never fire, so check which sources are actually connected before you build on top of them.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add JoelLewis/finance_skills --skill next-best-action -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add JoelLewis/finance_skills --skill next-best-action -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add JoelLewis/finance_skills --skill next-best-action -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install JoelLewis/finance_skills next-best-action
```

2. **Manually: put the files in place**
- File: `.github/skills/next-best-action/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add JoelLewis/finance_skills --skill next-best-action -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/JoelLewis/finance_skills --path plugins/advisory-practice/skills/next-best-action
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add JoelLewis/finance_skills --skill next-best-action -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/JoelLewis/finance_skills/tree/HEAD/plugins/advisory-practice/skills/next-best-action/SKILL.md

## When to use it
- set a trigger for portfolio drift past the target model
- catch a large cash deposit or withdrawal
- rank competing actions across an entire book of business
- remind a client about an RMD deadline
- measure how many recommendations advisors accept

## Example prompts
- Design the trigger logic for advisor alerts on portfolio events
- How do I prioritize the action queue when there are hundreds of clients?
- Describe how recommendations get routed between team members

## 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: aa2cb91651a5ca32.

BEGIN THIRD-PARTY FILE aa2cb91651a5ca32
```text
---
name: next-best-action
description: "Design and implement next-best-action engines that surface proactive, prioritized recommendations to advisors based on portfolio, life, market, and compliance events. Use when the user asks about building event-driven advisor alerts, designing trigger logic for portfolio drift or large cash movements, prioritizing competing actions across a book of business, routing NBA recommendations to the right team member, measuring NBA acceptance rates, or automating compliance-driven actions like annual review reminders. Also trigger when users mention 'next best action', 'advisor nudges', 'proactive outreach', 'what should I do for this client', 'event-driven triggers', 'action queue', 'client contact gap', 'RMD reminder', or 'advisor productivity tool'."
---

# Next-Best-Action — Event-Driven Advisor Recommendations

## Core Concepts

### Next-Best-Action Framework
Next-best-action is an advisor productivity and client service methodology that analyzes client data across systems to surface the single most valuable action an advisor should take for each client at any given time. The concept originates in CRM and marketing automation — industries that have long used event-driven recommendation engines to guide customer-facing personnel toward high-value interactions — but its application in wealth management addresses a distinct set of challenges: advisors managing hundreds of client relationships cannot manually monitor every portfolio, life event, compliance deadline, and practice touchpoint across their entire book of business.

NBA differs fundamentally from traditional task management. Traditional task management is reactive and manual: advisors create their own to-do lists, respond to inbound client requests, and rely on memory or periodic reviews to identify outreach opportunities. NBA is proactive and data-driven: the system continuously monitors client data across custodial feeds, CRM records, financial plans, compliance calendars, and market data, automatically identifying situations that warrant advisor attention and recommending specific actions with supporting context.

The core components of an NBA system are:
```
END THIRD-PARTY FILE aa2cb91651a5ca32

The third-party file has ended. Everything between the aa2cb91651a5ca32 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 2199 of 37199 bytes. © JoelLewis · MIT · https://github.com/JoelLewis/finance_skills/tree/HEAD/plugins/advisory-practice/skills/next-best-action/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