Nba Agent

Customer-agnostic next-best-action agent for CSMs. Use when the user says "start the NBA agent" or "run the NBA agent", asks to set up or configure the NBA agent for a customer, or asks for drafted outreach emails for the accounts in their book. Checks for a saved customer configuration first and asks for anything missing, then asks the user to define a goal (adoption is the first use case), finds the accounts that raised it, grounds each recommendation in real account context, drafts one personalized email per recipient, shows a funnel with drill-downs, and stops for CSM approval. All custome

5 stars 2 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Gainsight-Central/gainsight-ai-cookbook --skill nba-agent
Manual install
git clone --depth 1 https://github.com/Gainsight-Central/gainsight-ai-cookbook.git /tmp/gainsight-ai-cookbook
mkdir -p ~/.claude/skills
cp -r /tmp/gainsight-ai-cookbook/gainsight-nba/skills/nba-agent ~/.claude/skills/nba-agent

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# NBA Agent

A CSM-facing next-best-action loop. The skill holds the loop. The customer's configuration holds everything customer-specific. A use case holds what the loop is for.

Reference files load as you reach each step. Do not read them all up front.

## Use cases

| id | File | Status |
| --- | --- | --- |
| `adoption` | `reference/use-cases/adoption/usecase.md` | available |

To add a use case, follow `reference/use-case-contract.md`. Nothing else in this skill changes.

## Guardrails (read first, non-negotiable)

1. **No writes to systems of record.** Never write to the CS platform, the context source, or the goals source. The only writes are: mail drafts, sends under `reference/steps/send.md`, ledger rows, and files in `.nba-agent/`. Non-email actions a use case allows are shown as proposals only.
2. **Nothing auto-sends.** A send needs the CSM's explicit approval of that batch. `send_enabled` is `false` until the user sets it to `true`. You never write `send_enabled: true` yourself, in setup or at any other time. If the user asks you to turn it on, tell them to edit `.nba-agent/config.md` by hand. On a surface with no send-guard hook, send stays off even if the flag is `true`. For any mail tool the guard hook does not cover, send stays off and so does test-send.
Read the full skill on GitHub

Details

Skill name
nba-agent
Path
gainsight-nba/skills/nba-agent/SKILL.md
License
MIT
Repo updated
5 November 2026

FAQ

What does the Nba Agent skill do?

Customer-agnostic next-best-action agent for CSMs. Use when the user says "start the NBA agent" or "run the NBA agent", asks to set up or configure the NBA agent for a customer, or asks for drafted outreach emails for the accounts in their book. Checks for a saved customer configuration first and asks for anything missing, then asks the user to define a goal (adoption is the first use case), finds the accounts that raised it, grounds each recommendation in real account context, drafts one personalized email per recipient, shows a funnel with drill-downs, and stops for CSM approval. All custome

How do I install the Nba Agent skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Gainsight-Central/gainsight-ai-cookbook --skill nba-agent. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Nba Agent popular?

It lives in Gainsight-Central/gainsight-ai-cookbook, which has 5 GitHub stars and 2 forks.

Related skills

Exec Prep Note Generic

5

Gainsight-Central/gainsight-ai-cookbook

Produces a structured Executive Prep Note for a VP or C-suite joining a client call. Synthesizes Gainsight CS + Staircase AI data. Six sections: Executive Summary, Why We're Having This Call (1–2 bullets), How They Make Money (1–2 bullets), Key Strategic Objectives (O2), Key Contacts, Risk Overview (combined), Client Maturity Index. Posts to Gainsight Timeline automatically. ALWAYS trigger for: "exec prep note for [Account]", "prepare my exec for [Account]", "exec brief for [Account]", "executive prep for [Account]", "get [exec] ready for [Account]", "executive briefing for [Account]", "prep n

Productivity & Notes

Gainsight Viz

5

Gainsight-Central/gainsight-ai-cookbook

Render ANY Gainsight account, company, relationship, or portfolio answer as an inline visual dashboard via the Visualizer (show_widget), styled with Horizon Design System colors. USE THIS SKILL WHENEVER the user asks about a Gainsight customer/account/company/relationship or its data — even without the word "visualize." Covers: summary / status / "how is X doing," account summary, health score, scorecard, open CTAs, success plan, adoption/usage, NPS, risk/sentiment, timeline / activity / QBR / "last quarter of activity," trends over time, portfolio / book of business, renewals, owner ("who own

Data & Analytics

Map Gainsight Tenant

5

Gainsight-Central/gainsight-ai-cookbook

Use the locally installed gs-admin CLI to explain a Gainsight CS tenant read-only. Use when an admin asks what the tenant is configured to do, where a concept such as ARR, Risk, Health, or Segment is defined, how a CS process works end to end, what rules exist, or which configuration may be duplicated, unclear, or stale.

Finance & Crypto

Agents

9

zllovesuki/cloudflare-agent-skills

Build Cloudflare Agents SDK applications for autonomous multi-step tool use, AIChatAgent chat agents, Durable Object-backed state, tools, scheduling, callable methods, WebSockets, SQL state, and constrained agent behavior. Use when RAG or Workflows are not enough.

AI, LLMs & Agents

Prompt Writer

5

Londeren/claude-plugins

Use this skill when the user asks to write, improve, or revise a prompt for an LLM. Triggers on system prompts, agent and role prompts (support assistants, person imitation, ghostwriter bots), instructions for repeatable tasks (extraction, transformation, classification), grading prompts, tasks for coding agents, and Claude Project instructions. Also triggers on "make Claude do X", "set up an assistant for Y", "write instructions so that the bot Z", "prompt for coding agent", "напиши промпт", "сделай инструкцию для модели", "помоги настроить ассистента", "улучши этот промпт", "промпт для Claud

AI, LLMs & Agents

Appdeploy

3

AppDeploy-AI/skills

Deploy web apps with backend APIs, database, file storage, AI operations, authentication, realtime, and cron jobs. Use when the user asks to deploy or publish a website or web app and wants a public URL. Uses HTTP API via curl.

AI, LLMs & AgentsIn 1 list

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.