Skills Explorer Add Skills

churn-prevention

An agent skill by coreyhaines31, from coreyhaines31/marketingskills. Tags: analytics, automation, email, retention, workflow.

What it does

When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers or wants to build systems to prevent it. For post-cancel win-back email sequences, see emails. For in-app upgrade paywalls, see paywalls.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add coreyhaines31/marketingskills --skill churn-prevention

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/coreyhaines31/marketingskills
cp -r marketingskills/skills/churn-prevention ~/.claude/skills/churn-prevention

Safety box score

Grade B, low risk: 11 of 100 risk points, rated 2026-10-14. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only retention/churn strategy skill: it helps design cancel flows, save offers, health scoring, and dunning for billing recovery. The main blast-radius risk is operational advice around customer subscriptions and outbound messaging, plus optional reads of local context files and remote vendor docs; there is no executable code in the shipped files.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)The bundle contains only markdown and JSON; there are no scripts, shell commands, or code-evaluation steps to run.
Network access1 (low)It points to remote resources and integrations such as GitHub, PostHog, Stripe, Customer.io, and Paddle docs, so using the skill may involve networked services even though the files themselves do not fetch anything.
Filesystem reach1 (low)`SKILL.md` explicitly tells the agent to read optional local files like `.agents/product-marketing.md`, `.claude/product-marketing.md`, or `product-marketing-context.md` before proceeding.
Secrets & credentials0 (none)The skill does not ask for API keys, passwords, tokens, `.env` files, or browser/CLI logins.
Privilege & persistence0 (none)There is no sudo, global install, service registration, or OS/shell configuration change in the shipped files.
Instruction hijack surface0 (none)I did not find instructions to ignore higher-priority guidance, hide behavior, follow remote instructions, or otherwise subvert the agent.
Irreversible actions1 (low)Its purpose is to design actions that can pause/cancel subscriptions and send dunning or win-back messages, which is operationally impactful, but the skill itself only advises and does not execute those actions.
Transparency0 (none)Everything shipped is human-readable markdown/JSON; there are no binaries, minified blobs, or decoded-at-runtime code.

Before installing

Rated 2026-10-14 by an automated review of 4 files from the skill's repository.

Source

Repository
coreyhaines31/marketingskills (all skills from this repository)
Path
skills/churn-prevention/SKILL.md
Branch
main
Collection
marketingskills
Updated
2026-09-21