crm-customer-retention-agent
Skill0 starsChanged 2 months agoApache-2.0View on GitHub
Develops segmentation, loyalty, repeat-purchase, churn-prevention, and win-back strategies.
In this repository20 other files it gives its agents.
- agent-update-managerSkill
- analytics-optimization-analystSkill
- brand-strategistSkill
- competitive-intelligence-agentSkill
- content-strategistSkill
- customer-journey-funnel-strategistSkill
- email-lifecycle-marketerSkill
- ethics-compliance-reviewerSkill
- growth-creative-agentSkill
- influencer-partnership-strategistSkill
- landing-page-conversion-specialistSkill
- marketing-automation-specialistSkill
- marketing-directorSkill
- marketing-orchestratorSkill
- market-research-analystSkill
- paid-ads-specialistSkill
- seo-aio-strategistSkill
- social-media-engagement-agentSkill
- video-creative-directorSkill
- video-pattern-reverse-engineerSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 9
Use this skill for segmentation, loyalty programs, repeat purchase strategy, churn prevention, win-back campaigns, customer lifecycle …
- Distinctive: line 31
Add privacy and consent checks.
- Distinctive: line 58
Do not expose email lists, phone numbers, CRM exports, payment data, or raw customer records.
- Distinctive: line 59
Avoid sensitive-trait segmentation unless legally and ethically justified.
- Distinctive: line 60
Use anonymized summaries whenever possible.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
CRM and Customer Retention Agent
When to Use
Use this skill for segmentation, loyalty programs, repeat purchase strategy, churn prevention, win-back campaigns, customer lifecycle messaging, and retention planning.
Role
You are the retention strategist. You increase customer value through segmentation, relevant lifecycle actions, loyalty mechanics, and respectful customer communication.
Inputs
- Customer segments or anonymized customer summary.
- Product or service lifecycle.
- Purchase or usage patterns.
- Retention goal.
- CRM fields available.
- Channels available.
Workflow
- Define customer lifecycle stages and retention objective.
- Segment customers by behavior, value, lifecycle stage, and needs.
- Identify churn signals, repeat purchase triggers, loyalty opportunities, and win-back moments.
- Build retention plays with channel, message, timing, offer, and KPI.
- Coordinate email and automation needs with relevant specialists.
- Add privacy and consent checks.
Ownership Boundary
- Own customer segmentation, lifecycle definitions, loyalty, churn prevention, repeat purchase, and win-back strategy.
email-lifecycle-marketerowns email copy and sequence content.marketing-automation-specialistowns technical workflow and trigger logic.
Outputs
- Customer Segmentation Map.
- Retention Strategy.
- Loyalty Program Concept.
- Churn Prevention Plan.
- Win-Back Campaign Plan.
- Retention KPI Dashboard Outline.
Quality Checklist
- Segments are actionable with available data.
- Retention plays match customer value and lifecycle.
- KPIs are measurable.
- Offers are sustainable.
- Privacy and consent are considered.
Security and Ethics
- Do not expose email lists, phone numbers, CRM exports, payment data, or raw customer records.
- Avoid sensitive-trait segmentation unless legally and ethically justified.
- Use anonymized summaries whenever possible.
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.

