agentleFS
etrebelsetrebels/claude-code-growth-os/.claude/skills/churn-save/SKILL.md

churn-save

Skill21 starsChanged 2 months agoMITView on GitHub

Turn a red/amber account into a recovery play β€” the real risk, the re-engagement outreach, the renewal-clock timing. Trigger when account-health flags a πŸ”΄/🟑 account, when the user says "save this account", "they're going to churn", "the customer went quiet", "renewal at risk", or right after a RETENTION-RISK line is logged.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • β‰ˆ0

    Common Β· estimate

    Many files like this have a rule of this kind.

  • β‰ˆ2

    Distinctive Β· estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Re-thread if it's single-threaded: If one name carried the account and that name went quiet, the save is a *second* relationship, not a …

    line 14
  2. Very specific:

    Route the cause if it's a product gap: If a missing capability is what's blocking value, that's a RETENTION-RISK / FEATURE-REQUEST for …

    line 16
  3. Distinctive:

    Don't paper a value miss over with a nicer email.

    line 19

β‰ˆ β€œCommon” 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. β€œVery specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Churn Save

The act-skill on the right side of the bowtie. account-health detects β€” it scores the account and writes the RETENTION-RISK line; this one acts on it. The split mirrors the left side, where lead-qualify scores and the pursuit skills work the deal. A save is re-earning the outcome the customer bought β€” not sending a warmer email.

From the at-risk row in ops/customers.md, the RETENTION-RISK line that flagged it, and any recent notes:

  1. Name the real risk, not the symptom. The cancellation is the lagging indicator; the cause is upstream β€” usage trending down, the champion gone quiet, a single-threaded account after a reorg, or the value the deal was sold on never landing. Separate the one that's actually moving from the noise.
  2. Time the motion. The renewal clock starts at day 60, not day 85. If the renewal date is inside 60 days, the save runs now, in parallel with the renewal β€” don't let the contract surface the risk for you.
  3. Re-thread if it's single-threaded. If one name carried the account and that name went quiet, the save is a second relationship, not a better message to the first. Name who else to reach, and why they'd care.
  4. Draft the re-engagement. Lead with their outcome β€” the metric the deal was bought to move β€” not "just checking in". One concrete next step, with a date. Offer to debrief any reply with follow-up.
  5. Route the cause if it's a product gap. If a missing capability is what's blocking value, that's a RETENTION-RISK / FEATURE-REQUEST for product β€” hand it on with product-signal so the save and the roadmap move together (handoff H4 in docs/operating-model.md).
  6. Log the play and update the book. Record the play and its outcome; update the account's stage, signal, and next step in ops/customers.md. If it's lost anyway, log the real reason β€” /retention-report's churn-by-reason read depends on it.

Don't paper a value miss over with a nicer email; a save the customer can see through costs you the reference too. And don't tag every quiet week as a churn β€” a book full of false alarms gets ignored.

Depth

  • quick: the real risk + the one next move.
  • standard: the full play above β€” risk, timing, re-thread, the re-engagement draft, routed cause.
  • deep: + the internal escalation note and the day-by-day renewal-motion timing to the renewal date.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.