── SKILL
save-play✓ APPROVED

Run a churn-save on the real reason, not the stated one.

Diagnoses the actual cause, matches commercial and non-commercial levers to it, and runs a multi-touch save sequence.

Inside: The root-cause diagnosis, the lever match, and the save sequence with exit criteria.

01 / HOW TO USE

Install it in one line, or paste it in.

1
In Claude Code (one command)
Copy the install line, paste it into your terminal, and restart Claude Code. The skill installs itself to ~/.claude/skills/ and runs automatically when it is relevant.
2
In Claude, ChatGPT, or a Project (no terminal)
Open the file, then upload it to your chat or paste its contents in. A skill is just a markdown file of instructions, so any capable AI can follow it.
New to skills? A skill is a plain-text file that teaches your AI a workflow. Point any capable assistant at it and it follows the steps, on your data.
02 / MAKE IT YOURS

Connect your context. Set it to your motion.

CONNECT YOUR CONTEXT · AND WHY IT HELPS
a CRM

it reads the account, ARR, renewal date, contacts, and open cases automatically.

a product-analytics tool

shows whether usage is actually falling, and where it fell off first.

a support or ticketing tool

surfaces the unresolved pain the customer may not be naming.

SET IT TO YOUR MOTION

This was built for a B2B SaaS org saving at-risk renewals. Set these to your stack:

Diagnose before you discount. A price cut aimed at a product problem loses the money and the account both.

Set thisWhat it isDefault / Example
RISK signalswhat flagged the accountusage dropquiet sponsorescalationnon-renewal notice
USAGE sourcewhere adoption livesproduct analyticsa usage export
SUPPORT sourcewhere unresolved pain livesticketing toolescalation log
COMMERCIAL leverswhat you can offerdiscountterm changeright-sizepause
NON-COMMERCIAL leverswhat you can do without priceexec sponsorre-onboardingnew use caseroadmap commit
RENEWAL fieldthe renewal date and ARRAccount.RenewalDateAccount.ARR
SAVE windowdays you have to work the play60 (re-tune to your notice period)
03 / THE FULL SKILL

Everything the skill does, in full.

── WHAT THIS DOES

Takes an at-risk account and builds the play to save it: the real reason it is slipping (which is rarely the reason first given), the levers you can actually pull (commercial and not), and a multi-touch sequence with owners and dates so the save is a plan, not a hope. It is honest about when an account is not savable, so you spend your effort where it pays.

── THE METHOD
  1. 1
    Diagnose the real reason

    The stated reason ("too expensive") is usually a symptom. Trace it to the root: low adoption, a lost champion, an unresolved escalation, a use case that never landed, a reorg, a competitor. Show the evidence, usage trend, ticket history, sponsor activity, that points to the real cause. Fix the wrong reason and you lose the account anyway.

  2. 2
    Match levers to the cause

    Commercial levers (discount, shorter term, right-sizing seats, a pause) fix commercial problems. Non-commercial levers (an executive sponsor, re-onboarding, a new use case, a roadmap commitment, a success plan reset) fix value and relationship problems. Most saves need the non-commercial lever first; the discount alone rarely holds.

  3. 3
    Build the multi-touch sequence

    A save is a sequence, not a single call. Space the touches across the save window: an acknowledgment, a working session on the real issue, a value or plan reset, an executive touch, the commercial conversation last. Each touch has an owner, a date, and a goal. One heroic email saves nothing.

  4. 4
    Set the exit criteria

    Name what "saved" looks like (renewed, re-engaged, a signed plan) and what "not savable" looks like (no sponsor will engage, the decision is made above your line). Call it early. Effort spent on a dead account is effort stolen from a savable one.

  5. 5
    Escalate deliberately

    Say when to pull in a leader or an executive sponsor, and for what. Escalation is a lever, not a panic button. Use it on the touch where a peer-level voice changes the room.

── QUALITY GATES
  • The diagnosis names a root cause with evidence, never just the stated reason.
  • Commercial levers are matched to commercial causes, not thrown at value problems.
  • The sequence has owners and dates on every touch, and the commercial ask comes last.
  • The play states its exit criteria, including when to stop. Not every account is savable.
── OUTPUT (EXAMPLE)
EXAMPLE OUTPUT
SAVE PLAY · sample account · renewal in 52 days
Stated reason:   "too expensive"
Real reason:     adoption fell after the champion left; usage down sharply
Evidence:        weekly seats dropped by half, sponsor quiet 40 days, 1 open escalation

Levers:
  Non-commercial (first): new exec sponsor intro, re-onboard the team, reset the plan
  Commercial (last):      right-size seats to actual usage, hold the rate

Save sequence (52-day window):
  1. Day 0   CSM      acknowledge, book a working session
  2. Day 5   CSM      resolve the open escalation
  3. Day 14  CSM+Lead re-onboarding + plan reset with the new sponsor
  4. Day 30  Exec     executive-to-executive value check
  5. Day 45  CSM      commercial conversation, right-size to usage

Exit criteria: saved = signed plan + renewal. Not savable = no sponsor engages by day 20.
── WHERE THE NUMBERS COME FROM

The usage drops, day counts, and any figure come from the data you paste or the tools you connect. Nothing above is a real customer number; it is illustrative. When the skill cannot see whether usage actually fell, it marks the diagnosis provisional and names the input, a usage export or ticket history, that would confirm it.

── EXAMPLE CHAT
EXAMPLE CHAT
You
This account says we're too expensive and they're not renewing. Build the save play. Here's what I know: champion left two months ago, usage has been dropping.
CLAUDE
Built it, but the stated reason isn't the real one. SAVE PLAY · sample account · renewal in 52 days Stated reason: "too expensive" Real reason: adoption fell after the champion left; usage down sharply Evidence: weekly seats dropped by half, sponsor quiet 40 days Levers: Non-commercial (first): new exec sponsor intro, re-onboard the team Commercial (last): right-size seats to actual usage, hold the rate Save sequence (52-day window): 1. Day 0 CSM acknowledge, book a working session 5. Day 45 CSM commercial conversation, right-size to usage Caught the trap: "too expensive" almost always shows up when adoption drops, not the other way around. If I'd taken it at face value, the play would've opened with a discount and lost the account and the margin both.
You
What tells us this account isn't actually savable, versus just needs work?
CLAUDE
The exit criteria in the plan: if no sponsor engages by day 20, that's the "not savable" line, not a vibe call, a dated checkpoint. Sharpener: connect your product-analytics tool and I'll confirm the usage drop is real instead of working from the note you pasted, so the diagnosis stops being provisional.
04 / GO FURTHER

Where an operator takes this next.

The diagnosis proves the account is worth the effort. Here is the version that catches it earlier and runs itself.

The account gets diagnosed correctly before anyone reaches for the discount.

01
Flag the risk signal automatically

Connect your product-analytics tool so a usage drop past a set threshold opens a save play in Salesforce before the customer says a word.

02
Route the sequence to real owners with real dates

Push the multi-touch plan into Salesforce tasks so "Day 5, resolve the open escalation" shows up as an assignment, not a line in a doc.

03
Watch the exit criteria, not just the start

Schedule a Claude task to check the day-20 checkpoint and alert the CSM lead the moment an account crosses from savable to not.

05 / PART OF A BIGGER PLAY

One skill is the on-ramp.

── GET NEW SKILLS IN YOUR INBOX

One operator-built skill a week. Free.