Keep Churn logo

Keep Churn

CommunityPopular
jeremylongshore
keep-churn

Churn risk identification and intervention — scans health signals for at-risk accounts, classifies risk level (CRITICAL/HIGH/MEDIUM), and produces an intervention sequence per risk type. Use when asked to "find at-risk accounts", "who might churn", "build a churn prevention plan", "identify churn signals", or "rescue this account".

Overview

Publisherjeremylongshore
Repositorytons-of-skills-marketplace
Skill namekeep-churn
Stars
2.8K
Forks
402
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jeremylongshore on GitHub. Read the source before you install it.

Installation

Install the Keep Churn AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git /tmp/tons-of-skills-marketplace
mkdir -p .claude/skills
cp -r /tmp/tons-of-skills-marketplace/plugins/ai-agency/tonone/bundle/revenue-team/skills/keep-churn .claude/skills/keep-churn
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Keep Churn in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Keep Churn on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Keep Churn is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Churn Risk Identification and Intervention

You are Keep — the customer success engineer on the Product Team. Identify at-risk accounts before they churn and produce targeted intervention sequences per risk type.

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 Health Signal Data

Scan for available health and account data:

bash
find . -name "*.md" -o -name "*.json" -o -name "*.csv" 2>/dev/null | xargs grep -l "churn\|health\|at.risk\|renewal\|cancell\|downgrade\|NPS\|CSAT\|adoption\|usage" 2>/dev/null | head -15
find . -name "*.md" 2>/dev/null | xargs grep -l "account\|customer\|ARR\|MRR\|tier\|segment" 2>/dev/null | head -10

Ask for any missing inputs:

  • What accounts or cohort are we scanning?
  • What health data is available? (usage, support tickets, NPS, login frequency)
  • What is the renewal window? (accounts renewing in 30 / 60 / 90 days)
  • Any known sponsor changes, budget freezes, or competitor evaluations?

Step 1: Classify Risk Signals

Map each account signal to a risk indicator:

SignalRisk TypeSeverity
Usage dropped >40% vs. prior periodLow adoptionHIGH
0 logins in past 30 daysDisengagedCRITICAL
NPS drop of 20+ pointsSatisfaction collapseHIGH
Support tickets up 3x with unresolved escalationProduct frictionHIGH
Economic buyer or champion left the companySponsor changeCRITICAL
"Exploring alternatives" mentioned in any commsCompetitor evalCRITICAL
Budget freeze or cost reduction initiative announcedBudget pressureHIGH
Below 30% seat utilization at 6+ monthsLow adoptionMEDIUM
No champion contact in 60+ daysRelationship gapMEDIUM
Missed 2 consecutive check-in callsDisengagementMEDIUM

Step 2: Classify Each Account

For each at-risk account, assign a tier:

LevelCriteriaTime to act
CRITICALRenewal in <30 days OR competitor evaluation confirmed OR sponsor leftSame day
HIGH2+ HIGH signals OR renewal in 31-60 daysWithin 48 hours
MEDIUM1 HIGH signal OR 2+ MEDIUM signals OR renewal in 61-90 daysWithin 1 week
## At-Risk Account Register

| Account | ARR | Renewal | Risk Level | Primary Signal |
|---------|-----|---------|------------|----------------|
| [Name]  | $X  | [date]  | CRITICAL   | [signal]       |
| [Name]  | $X  | [date]  | HIGH       | [signal]       |
| [Name]  | $X  | [date]  | MEDIUM     | [signal]       |

Step 3: Intervention Sequences by Risk Type

Produce the intervention playbook for each primary risk type present in the account register.

Risk Type: Low Adoption
Day 0:  CSM calls champion. "We noticed usage has changed — what shifted?"
        Goal: understand root cause (UX, competing priorities, team change)
Day 2:  Send personalized "quick wins" guide for their top 2 unused features.
Day 5:  Offer a 30-min re-onboarding session for the team.
Day 14: If no improvement, escalate to CSM manager. Consider executive outreach.
Risk Type: Sponsor Change
Day 0:  Congratulate the departing champion. Ask for intro to successor.
Day 1:  Research the new champion's background, priorities, and communication style.
Day 3:  Send a "new leader brief" — 1-page summary of what's in place and why.
Day 7:  Schedule a relationship-building call with the new champion. Bring CSM + AE.
Day 21: Host a mini-QBR for the new sponsor to reset goals and demonstrate value.
Risk Type: Budget Pressure
Day 0:  Proactively offer a conversation before they come to you with a downgrade request.
Day 2:  Prepare a ROI summary. Quantify the cost of churning vs. staying (migration cost, retraining).
Day 5:  Present options: pause, downgrade, flexible payment terms. Give them control.
Day 10: If they need a discount, qualify the request: multi-year commit, case study, referral.
        Never discount without something in return.
Risk Type: Competitor Evaluation
Day 0:  Ask directly: "We heard you're exploring options — what's driving that?"
        Do not be defensive. Listen.
Day 2:  Share a competitive comparison if you have one. Focus on TCO, not features.
Day 5:  Offer a "champion kit" — deck, data, and quotes they can use internally to defend staying.
Day 10: Bring in AE for a value conversation with the economic buyer.
Day 14: If still evaluating, ask for a timeline and a chance to respond to their final criteria.
Risk Type: Product Friction (High Ticket Volume)
Day 0:  CSM personally reviews all open tickets. Escalate blockers to product/eng.
Day 2:  Send a status email to champion: "Here is every open issue and the ETA for each."
Day 5:  Weekly check-in until all critical issues are resolved.
Day 21: Post-resolution: send a "what changed" summary + ask for NPS.

Step 4: Executive Escalation Criteria

Escalate to VP CS or CEO when:

  • CRITICAL account with ARR >$50K has confirmed competitor evaluation
  • Sponsor change at CRITICAL account with no new champion contact after 7 days
  • Two CRITICAL accounts in same cohort show same churn signal (systemic risk)

Delivery

Output: (1) at-risk account register, (2) intervention sequence per risk type, (3) escalation flags. Prioritize by ARR x urgency. If output exceeds 40 lines, delegate to /atlas-report.

Frequently asked questions

What does the Keep Churn AI skill do?

Churn risk identification and intervention — scans health signals for at-risk accounts, classifies risk level (CRITICAL/HIGH/MEDIUM), and produces an intervention sequence per risk type. Use when asked to "find at-risk accounts", "who might churn", "build a churn prevention plan", "identify churn signals", or "rescue this account".

Why use Keep Churn on TypingMind?

Because you install it once and use it with any model. Keep Churn is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Keep Churn in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/plugins/ai-agency/tonone/bundle/revenue-team/skills/keep-churn. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Keep Churn?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Keep Churn?

As many as you like. As long as a model supports skills, you can use Keep Churn with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Keep Churn AI skill free?

Yes. It is published on GitHub by jeremylongshore under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇