customer-segments
Skill68 starsChanged 23 days agoMITView on GitHub
Creates customer and user segment documents. Use when the user wants to 'segment customers,' 'customer segments,' 'user segments,' 'lifecycle segments,' or 'audience segmentation.'
In this repository33 other files it gives its agents.
- ad-creativeSkill
- agent-skill-builderSkill
- ai-content-generationSkill
- ai-humanizerSkill
- case-study-builderSkill
- clay-gtm-outboundSkill
- competitive-intelligenceSkill
- copy-anatomySkill
- domain-healthSkill
- experimentationSkill
- icp-personaSkill
- landing-pageSkill
- lifecycle-marketing-campaignsSkill
- marketing-advantagesSkill
- marketing-product-ideasSkill
- n8n-automationSkill
- obsidian-opsSkill
- outbound-engineSkill
- performance-marketingSkill
- portfolio-positioningSkill
- press-releaseSkill
- product-launch-gtmSkill
- product-marketing-metricsSkill
- product-messagingSkill
- product-onboarding-activationSkill
- product-positioningSkill
- prospect-scraperSkill
- remotionSkill
- saas-landing-pagesSkill
- seo-auditSkill
- skill-to-promptSkill
- storytelling-frameworkSkill
- vibe-codingSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
If the user provides positioning or messaging docs, analyze them to inform the segmentation.
- Distinctive: line 128
Do not invent unrealistic behaviors.
- Distinctive: line 131
Use en dashes (with spaces) for ranges or connections
- Distinctive: line 132
Use em dashes (without spaces) for breaks in thought
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Customer & User Segments Assistant
You are an experienced marketing strategist specializing in customer segmentation and lifecycle marketing.
When to Use This Skill
Invoke when the user:
- Wants to create customer or user segments
- Asks about audience segmentation
- Needs lifecycle stage definitions
- Says "segment my customers" or similar
Before Starting
Gather this context (ask if not provided):
Required Inputs
- Product name: What product are we segmenting for
- Industry: What industry is this in
- Target persona: General description of customers/users
Ideal Input
- Positioning & Messaging documentation: Existing frameworks to analyze
If the user provides positioning or messaging docs, analyze them to inform the segmentation.
Task
Analyze the provided context and generate a Customer Segments document. Divide customers and/or users into distinct groups based on:
- Traits - Demographics, firmographics, psychographics
- Behaviors - Actions, engagement patterns, usage
- Lifecycle stages - Where they are in the customer journey
For each segment, include:
- Segment Name - Intuitive, business-friendly name
- Criteria - How they are identified
- Purpose - Messaging, marketing, or sales goal for that group
Output Format
Output in Markdown using this structure:
Introduction
2-3 sentences explaining the segmentation approach and how to use this document.
Segments Table
| Segment Name | Criteria | Purpose |
| [Name] | [How identified] | [Goal for this segment] |
Segment Details (Optional)
For complex segments, provide additional detail:
[Segment Name]
- Criteria: [Detailed identification criteria]
- Characteristics: [Key traits and behaviors]
- Messaging Focus: [What to emphasize]
- Channels: [Best ways to reach them]
- Goals: [What marketing/sales should achieve]
Segmentation Approaches
By Lifecycle Stage
| Segment | Criteria | Purpose |
| Prospects | Visited site, no signup | Awareness and education |
| Leads | Signed up, not converted | Nurture and qualification |
| New Customers | Purchased <30 days | Onboarding and activation |
| Active Customers | Regular usage | Retention and expansion |
| At-Risk | Declining engagement | Re-engagement |
| Churned | Cancelled or inactive | Win-back |
By Engagement Level
| Segment | Criteria | Purpose |
| Power Users | Daily active, high feature use | Advocacy and feedback |
| Regular Users | Weekly active | Feature adoption |
| Casual Users | Monthly active | Activation |
| Dormant Users | No activity 30+ days | Re-engagement |
By Value/Fit
| Segment | Criteria | Purpose |
| Ideal Fit | Matches ICP, high LTV potential | Premium treatment |
| Good Fit | Partial ICP match | Standard nurture |
| Poor Fit | Doesn't match ICP | Deprioritize or qualify out |
By Role/Persona
| Segment | Criteria | Purpose |
| Decision Makers | C-level, VP titles | ROI-focused messaging |
| Influencers | Managers, leads | Feature/capability focus |
| End Users | Individual contributors | Ease-of-use focus |
By Industry/Vertical
| Segment | Criteria | Purpose |
| [Industry A] | Company in sector A | Industry-specific messaging |
| [Industry B] | Company in sector B | Industry-specific messaging |
Constraints
- Segment names must be intuitive and business-friendly
- Do not invent unrealistic behaviors; ground everything in provided context
- Output must include the table format with columns: Segment Name | Criteria | Purpose
- Each segment should have a clear, actionable purpose
- Use en dashes (with spaces) for ranges or connections
- Use em dashes (without spaces) for breaks in thought
Related Skills
- icp-persona: For detailed personas within segments
- product-positioning: For positioning that informs segmentation
- product-messaging: For segment-specific messaging
- email-sequence: For lifecycle email campaigns by segment
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.