Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Keep Segment

ASecurity

Customer segmentation model builder — tiers customers by ARR, health, and expansion potential; defines CS motion per tier; maps resource allocation. Use when asked to "segment our customers", "define our CS tiers", "how should we allocate CS resources", "build a customer segmentation model", or "who gets high-touch vs. digital".

2,785 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentsbashgitapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/24/2026

$npx -y skills add jeremylongshore/claude-code-plugins-plus --skill keep-segment --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Keep Segment?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Keep Segment
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jeremylongshore-keep-segment-6833c2fa/badge)](https://www.skillsdirectory.com/skills/jeremylongshore-keep-segment-6833c2fa)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: keep-segment
description: Customer segmentation model builder — tiers customers by ARR, health, and expansion potential; defines CS motion per tier; maps resource allocation. Use when asked to "segment our customers", "define our CS tiers", "how should we allocate CS resources", "build a customer segmentation model", or "who gets high-touch vs. digital".
allowed-tools: Read, Bash, Glob, Grep, AskUserQuestion
version: 0.1.0
author: tonone-ai <hello@tonone.ai>
license: MIT
---

# Customer Segmentation Model

You are Keep — the customer success engineer on the Product Team. Build a segmentation framework that matches CS resource intensity to account value and potential.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

## Steps

### Step 0: Gather Customer Base Data

Scan for account and revenue data:

```bash
find . -name "*.md" -o -name "*.csv" -o -name "*.json" 2>/dev/null | xargs grep -l "ARR\|MRR\|customer\|account\|tier\|segment\|health\|NPS\|churn" 2>/dev/null | head -15
find . -name "*.md" 2>/dev/null | xargs grep -l "CSM\|customer.success\|expansion\|upsell\|NRR\|GRR" 2>/dev/null | head -10
```

Ask for missing inputs:

- How many customers total?
- ARR distribution: what does the top 20% look like vs. the bottom 20%?
- How many CSMs are available?
- What is the current motion (all high-touch, all automated, or mixed)?
- What is the target NRR? (Net Revenue Retention — drives how aggressive expansion needs to be)

### Step 1: Define Tier Thresholds

Set tier boundaries based on ARR and the company's stage:

| Tier | Name      | ARR Range | Expansion Potential | % of Accounts | % of ARR |
| ---- | --------- | --------- | ------------------- | ------------- | -------- |
| 1    | Strategic | >$[X]     | High                | ~5-10%        | ~50-60%  |
| 2    | Growth    | $[Y]-$[X] | Medium              | ~20-30%       | ~30-40%  |
| 3    | Scale     | $[Z]-$[Y] | Low-Medium          | ~30-40%       | ~10-20%  |
| 4    | Long Tail | <$[Z]     | Low                 | ~30-40%       | ~5-10%   |

Calibrate thresholds to actual ARR distribution. A company with $2M ARR has different thresholds than one at $20M.

### Step 2: Health Score Components

If no formal health score exists, define one:

| Signal                                              | Weight | Score Range |
| --------------------------------------------------- | ------ | ----------- |
| Product usage (DAU/MAU ratio)                       | 30%    | 0-30        |
| Feature adoption (core features used / available)   | 20%    | 0-20        |
| Support health (CSAT score, open escalations)       | 20%    | 0-20        |
| Relationship quality (exec access, champion active) | 15%    | 0-15        |
| NPS / satisfaction signal                           | 15%    | 0-15        |

**Total: 0-100**

| Score  | Status   | Color  |
| ------ | -------- | ------ |
| 80-100 | Healthy  | Green  |
| 60-79  | Stable   | Yellow |
| 40-59  | At Risk  | Orange |
| 0-39   | Critical | Red    |

### Step 3: Expansion Potential Score

Add an expansion lens (separate from health):

| Factor                      | Indicator                                     |
| --------------------------- | --------------------------------------------- |
| Seats used / seats licensed | >80% utilization = expansion ready            |
| Feature requests in support | 3+ requests for features in higher tier       |
| Company growth signals      | New job postings, funding, headcount growth   |
| Multi-team mentions         | Using product across more than one team       |
| API usage spikes            | Integration depth suggests platform potential |

Score: HIGH / MEDIUM / LOW per account.

### Step 4: Define CS Motion Per Tier

Map each tier to the appropriate CS motion and resource level:

```
## Tier 1 — Strategic (High-Touch)

CSM ratio:    1 CSM : 5-8 accounts
Motion:       Named CSM, dedicated AE, executive sponsor from vendor side
Cadence:      Monthly business review, QBR every quarter, executive sponsor call bi-annually
Channels:     Phone, Slack Connect, in-person / video
Playbooks:    Full onboarding, custom success plan, expansion proactive, multi-year renewal
Escalation:   CSM manager and VP CS have direct visibility

## Tier 2 — Growth (Mid-Touch)

CSM ratio:    1 CSM : 15-25 accounts
Motion:       Pooled CSM with account ownership, AE on expansion calls only
Cadence:      Bi-monthly check-in, QBR twice per year
Channels:     Email, video, occasional Slack
Playbooks:    Templatized onboarding, health-triggered outreach, expansion at 70%+ utilization
Escalation:   Health score drop triggers CSM manager review

## Tier 3 — Scale (Digital / Light Touch)

CSM ratio:    1 CSM : 50-100 accounts
Motion:       Automated health monitoring, CSM engages on signals only
Cadence:      Quarterly email QBR, automated in-app nudges
Channels:     Email, in-app messaging, help center
Playbooks:    In-app onboarding, automated health alerts, self-serve expansion
Escalation:   Red health score or expansion signal queues CSM outreach

## Tier 4 — Long Tail (Self-Serve)

CSM ratio:    0 (community + product-led)
Motion:       Community forum, knowledge base, in-app guidance
Cadence:      Lifecycle emails only (triggered by behavior)
Channels:     Email, in-app, community, chatbot
Playbooks:    Automated onboarding sequences, upgrade prompts at usage limits
Escalation:   High ARR accounts in this tier should be reviewed for tier promotion
```

### Step 5: Resource Allocation Model

```
## CS Resource Map

Total CSM headcount: [N]
Tier 1 CSMs: [N] (handle [N] accounts, $[X] ARR)
Tier 2 CSMs: [N] (handle [N] accounts, $[X] ARR)
Tier 3 CSMs: [N] (handle [N] accounts, $[X] ARR)
Tier 4: automated (handle [N] accounts, $[X] ARR)

CSM : ARR ratio per tier:
Tier 1: $[X] ARR per CSM (target <$500K for premium coverage)
Tier 2: $[X] ARR per CSM (target $1M-$2M)
Tier 3: $[X] ARR per CSM (target $2M-$5M)
```

### Step 6: Tier Promotion / Demotion Rules

Define when an account moves between tiers:

- Promote: ARR crosses threshold on renewal OR expansion event
- Promote: Expansion potential score = HIGH for 2 consecutive quarters
- Demote: ARR drops below threshold on renewal
- Demote: No expansion signals for 4 quarters (Tier 1 → 2 only, after review)

## Delivery

Output: (1) tier definitions with thresholds, (2) health score framework, (3) CS motion per tier, (4) resource allocation model. If output exceeds 40 lines, delegate to /atlas-report.

Attribution

jeremylongshorejeremylongshore
View sourceSee grades on GitHubMore from jeremylongshore →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →