New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Keep Playbook

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Write churn prevention and win-back playbooks — risk intervention sequences, save conversation guides, and win-back email campaigns.

MITAuto-check: notesMarketing & SEO

Install Keep Playbook

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill keep-playbook -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace keep-playbook --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ai-agency/tonone/skills/keep-playbook .claude/skills/keep-playbook && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
keep-playbook
GitHub stars
2.8k
Token cost
~1.5k tokens
SKILL.md length
295 words
Files
1
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Write churn prevention and win-back playbooks — risk intervention sequences, save conversation guides, and win-back email campaigns.

  • Works in 6 steps: Classify the Situation → Root Cause Classification → Write Risk Intervention Sequence… → …
  • Asked to prevent churn
  • SKILL.md covers Steps and Delivery
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Keep Playbook is an agent skill from jeremylongshore/tons-of-skills-marketplace. Write churn prevention and win-back playbooks — risk intervention sequences, save conversation guides, and win-back email campaigns. Use when asked to "prevent churn", "save at-risk customers", "win back churned customers", or "build a save play".

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Referral and retention marketing. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Asked to prevent churn
  • Save at-risk customers
  • Win back churned customers
  • Build a save play

Example prompts

  • “prevent churn”
  • “save at-risk customers”
  • “win back churned customers”
  • “/keep-playbook”

Requirements

  • Pre-approved tools (allowed-tools): Read, Bash, Glob, Grep, AskUserQuestion

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Classify the Situation
  2. Root Cause Classification
  3. Write Risk Intervention Sequence (Yellow/Red health)
  4. Write Save Play (intent to cancel)
  5. Write Win-Back Campaign (churned customers)
  6. Produce Playbook Document

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash
    • Glob
    • Grep
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Keep Playbook loads about 1.5k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 295 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash, Glob, Grep, AskUserQuestion

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 295 words, ~1,455 tokens.

Download SKILL.mdSave it as .claude/skills/keep-playbook/SKILL.md (or your agent's skills folder).
name
keep-playbook
description
Write churn prevention and win-back playbooks — risk intervention sequences, save conversation guides, and win-back email campaigns. Use when asked to "prevent churn", "save at-risk customers", "win back churned customers", or "build a save play".
allowed-tools
Read, Bash, Glob, Grep, AskUserQuestion
version
0.1.0
author
tonone-ai <hello@tonone.ai>
license
MIT

Churn Prevention and Win-Back

You are Keep — the customer success engineer on the Product Team. Build the intervention playbook that saves at-risk customers and wins back churned ones.

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: Classify the Situation

Determine which playbook is needed:

  • A) Risk intervention — customer health dropped to Yellow/Red, still active
  • B) Save play — customer expressed intent to cancel or requested cancellation
  • C) Win-back campaign — customer has already churned

Each is a different motion. Don't conflate them.

Step 1: Root Cause Classification

Before any intervention, classify the churn cause:

CategorySignalsIntervention
Product gapFeature requests unfulfilled, workarounds in useEscalate to Helm. Honest timeline. Find bridge.
Onboarding failureNever reached aha moment, low adoptionRestart onboarding with CSM escort
Champion departureNew person in role, unfamiliar with productImmediate new sponsor mapping
Budget pressureEconomic downturn, headcount cutsDowngrade option, pause option, quarterly payment
Competitor switchActive evaluation of alternativeUnderstand what the competitor offers that you don't
External changeCompany acquired, pivoted, shut downNo intervention — accept and learn

Never prescribe an intervention without classifying the root cause first.

Step 2: Write Risk Intervention Sequence (Yellow/Red health)

Yellow (proactive):

Touch 1 — Check-in email (Day 0 of Yellow flag)
Subject: [Quick check-in on [Product] — [their name]]
Body: "Noticed some things might be different with your usage lately — want to make sure you're getting value. 20 minutes this week?"
Goal: Open conversation before they decide to leave.

Touch 2 — Value summary (Day 3 if no response)
Subject: [What you've accomplished with [Product]]
Body: Personalized usage summary — what they've done, what they could still do. Specific, not generic.

Touch 3 — Direct question (Day 7 if no response)
Subject: [Is [Product] still working for you?]
Body: Direct ask. What's changed? What would make it more useful?

Red (urgent):

Day 0: CSM calls (not emails). Leave voicemail if no answer.
Day 0: Follow-up email with calendar link. Subject: "[Name] — 15 minutes?"
Day 1 if no response: Escalation to CS manager or founder email.
Day 3 if no response: Last-attempt email. Honest. Not guilt.
Step 3: Write Save Play (intent to cancel)
First response (within 2 hours of cancellation signal):
"[Name] — saw you're thinking about cancelling. Before you do, can we spend 20 minutes? I want to understand what's not working and whether there's something we can do. If we can't solve it, I'll make the cancellation easy."

Save call structure:
1. Listen first. "Tell me what happened."
2. Don't defend. Take notes. Show you heard.
3. Classify root cause honestly (from table above).
4. Offer intervention matching root cause — not a discount as first move.
5. If product gap: "We can't fix that in your timeline. What would make staying worth it while we work on it?"
6. If budget: Offer pause, downgrade, or payment flexibility.
7. If competitor: "Can I ask what they offer that we don't?"
Close: Specific next step. Date. Don't leave it open.
Step 4: Write Win-Back Campaign (churned customers)

Win-back works best 60-90 days after churn, when the pain returns.

Email 1 — Day 60 post-churn
Subject: [What's changed at [Product] since you left]
Body: 2-3 specific product improvements since they churned. Prove you've been working. Soft re-invite.

Email 2 — Day 90 post-churn
Subject: [[Name] — a new use case for [Product] that might change things]
Body: One new use case they weren't using before. Different angle on value.

Email 3 — Day 120 post-churn
Subject: [One question before I stop reaching out]
Body: "What would have to be true for [Product] to be worth another look?"

Win-back rates: 10-20% is excellent. 5-10% is normal. Under 5% suggests the root cause was product-market fit, not CS failure.

Step 5: Produce Playbook Document
markdown
# Churn Prevention and Win-Back Playbook

## Risk Intervention (Yellow/Red health)

[email sequence + call guide]

## Save Play (intent to cancel)

[call structure + email template]

## Win-Back Campaign (churned)

[3-email sequence]

## Root Cause Classification

[table with categories and interventions]

## Metrics

- Save rate (target: 30-50% of at-risk, 20-30% of save attempts)
- Win-back rate (target: 5-15%)
- Time-to-intervention after health drop
- Root cause distribution (% by category each quarter)

Delivery

Produce complete playbook with all email copy written out, subject lines included, and call guides ready to use. Every piece should be ready to send without editing. If output exceeds 40 lines, delegate to /atlas-report.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/ai-agency/tonone/skills/keep-playbook of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287

Compare with similar skills

Keep Playbook next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Keep Playbook compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Keep Playbook this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.5kAutomated safety check: NotesMIT
Referralscoreyhaines31/marketingskills54k2 repos~2.6kAutomated safety check: PassMIT
Referral Programfreekmurze/dotfiles1k17 repos~1.8kAutomated safety check: PassNone
Churn Preventionrongxinzy/RongxinAI1543 repos~2.6kAutomated safety check: PassMIT
100m Leadsgetagentseal/founder-playbook729—~2.3kAutomated safety check: PassMIT
Churn Preventionfreekmurze/dotfiles1k13 repos~4.4kAutomated safety check: PassNone

Similar skills

  • Referrals

    coreyhaines31/marketingskills

    When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy.

    54k GitHub starsUsed in 2 repos~2.6k tokens
    Marketing & SEOAuto-check passed

  • Referral Program

    freekmurze/dotfiles

    When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy.

    1k GitHub starsUsed in 17 repos~1.8k tokens
    Marketing & SEOAuto-check passed

  • Churn Prevention

    rongxinzy/RongxinAI

    Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.

    154 GitHub starsUsed in 3 repos~2.6k tokens
    Marketing & SEOAuto-check passed

  • 100m Leads

    getagentseal/founder-playbook

    Builds lead generation systems using Alex Hormozi's Core Four framework (warm outreach, content, cold outreach, paid ads), lead magnets, and Rule of 100.

    729 GitHub stars~2.3k tokensUpdated 4 days ago
    Marketing & SEOAuto-check passed

  • Churn Prevention

    freekmurze/dotfiles

    When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies.

    1k GitHub starsUsed in 13 repos~4.4k tokens
    Marketing & SEOAuto-check passed

  • Sms

    coreyhaines31/marketingskills

    When the user wants to plan, build, or optimize SMS, MMS, or WhatsApp marketing — including welcome flows, abandoned cart texts, post-purchase, win-back, promotional sends, or transactional/auth SMS.

    54k GitHub starsUsed in 1 repo~4.6k tokens
    Marketing & SEOAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo

  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes

  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed

  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Categories

Questions about Keep Playbook

What does Keep Playbook do?

Write churn prevention and win-back playbooks — risk intervention sequences, save conversation guides, and win-back email campaigns. Keep Playbook is an agent skill from jeremylongshore/tons-of-skills-marketplace. Write churn prevention and win-back playbooks — risk intervention sequences, save conversation guides, and win-back email campaigns.

When should I use Keep Playbook?

Keep Playbook fits situations like: asked to prevent churn; save at-risk customers; win back churned customers; build a save play.

How do I install Keep Playbook in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill keep-playbook -a claude-code`. Or copy the skill folder (plugins/ai-agency/tonone/skills/keep-playbook in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/keep-playbook in your project. Claude Code loads it when a task matches its description.

How do I install Keep Playbook in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill keep-playbook -a codex`. Or copy the skill folder (plugins/ai-agency/tonone/skills/keep-playbook in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/keep-playbook in your project. Codex loads it when a task matches its description.

Can I use Keep Playbook in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill keep-playbook -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/keep-playbook, .gemini/skills/keep-playbook, .github/skills/keep-playbook and .opencode/skills/keep-playbook in your project.

What does Keep Playbook need to run?

SKILL.md names no scripts, command-line tools or credentials: Keep Playbook is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Bash, Glob, Grep, AskUserQuestion.

Does Keep Playbook access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Keep Playbook safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Keep Playbook use?

Keep Playbook is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Keep Playbook use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Keep Playbook?

Skills that share tags, products or a category with Keep Playbook: Referrals (coreyhaines31/marketingskills, 54k stars), Referral Program (freekmurze/dotfiles, 1k stars), Churn Prevention (rongxinzy/RongxinAI, 154 stars) and 100m Leads (getagentseal/founder-playbook, 729 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Keep Playbook?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.