SKILL
pattern-analyst✓ APPROVED

Find what your wins, losses, and churn share.

Reads closed-won, closed-lost, and churned accounts, then hands back a ranked list of lookalike accounts to work.

Inside: The won / lost / churn pattern logic and the lookalike ranking.

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

the three cohorts and their fields, live.

a product-analytics tool

engagement decay, which powers the predictive-churn scan.

SET IT TO YOUR MOTION

Map each row to the actual field name in your system. If a pattern depends on a field you do not have, the skill runs the modes it can and tells you which one it skipped and why.

Set thisWhat it isDefault / Example
CRM connectorWhere your won/lost/churn cohorts liveAny CRM
Won/lost stage fieldThe field that marks a deal won or lostStage = Closed Won / Closed Lost
Loss reason fieldReason a deal was lostA loss-reason field
Competitor fieldNamed competitor a deal was lost toA competitor field
Churn signalHow you mark a lost customer vs a lost new dealType = Renewal AND Stage = Closed Lost
Segment fieldsAccount fields used for lookalike matchingEmployee countindustrytech stackchannelprimary signal
Activity signalThe product-analytics metric for engagement decay30-day active-user trend
03 / THE FULL SKILL

Everything the skill does, in full.

WHAT THIS DOES

This skill reads your closed-won, closed-lost, and churned accounts and finds the repeating patterns inside them. It runs in three modes. WON tells you what your winning deals have in common and generates a ranked list of active accounts that look like them. LOST tells you where, how, and to whom you lose, with the objections rolled up. CHURN groups your lost customers into named themes and then scans your active book for accounts that match those themes before they leave.

THE METHOD
  1. 1
    WON mode

    Cohort: trailing 6 months of closed-won. Extract buying-committee shape, deal velocity, primary entry point, dominant signals, tech-stack overlap. Score active accounts against the winning pattern and rank the closest matches.

  2. 2
    LOST mode

    Cohort: trailing 6 months of closed-lost. Competitive head-to-head by stage and deal size. Objection theme rollup from transcripts. Stage-of-loss distribution.

  3. 3
    CHURN mode

    Cohort: trailing 12 months of churned customers. Group churns into named causes (consolidation, layoff, vendor switch, product gap, champion left, acquisition). Scan active accounts for matches to each theme and surface them with a confidence tag, ranked by risk.

QUALITY GATES
  • Pattern extraction is statistically meaningful. The skill requires at least 5 occurrences before it calls something a pattern. Below that it returns "insufficient data, expand the window."
  • Lookalike candidates are similarity-scored, with the named dimensions behind the score.
  • Predictive churn calls are confidence-tagged with the evidence behind them. A low-confidence match is labeled low, not dropped.
OUTPUT (EXAMPLE)
EXAMPLE OUTPUT
PATTERN ANALYSIS  ·  Q2 Lookback

WON (n=14):
  Channel: Product 57% / Inbound 29% / Outbound 14%
  Dominant signal: sales-team hiring (78% of wins)
  Top lookalikes: Account A 91%, Account B 88%, Account C 87%

LOST (n=21):
  Stage-of-loss: Solution Validation 52%
  Top reason: "no compelling differentiation vs incumbent" (n=9)
  Lost to Competitor 1: 5 (at Proposal, "team already trained")

CHURN (n=8, 12 months):
  Consolidation / layoff (n=3), acquisition (n=2), feature gap (n=2)
  PREDICTIVE WATCH:
    Account F, consolidation pattern (73%): team 22 to 14, activity -47%
    Account G, champion-left pattern (68%): champion changed jobs 21d ago
WHERE THE NUMBERS COME FROM

Defaults to re-tune: win/loss windows 6 months trailing, churn window 12 months, pattern floor of 5 occurrences before something is named a pattern. Lookalike and churn-match scores are built from your segment fields; add or drop dimensions to fit what predicts outcomes in your data. The activity-decay threshold flags an at-risk account; tune it to your product's normal usage rhythm. Re-tune the windows and the pattern floor first.

EXAMPLE CHAT
EXAMPLE CHAT
You
Run the churn mode on last year's losses and tell me who in the active book looks like them.
CLAUDE
Grouped the churns into named themes and scanned the active book. CHURN (n=8, 12 months): Consolidation / layoff (n=3), acquisition (n=2), feature gap (n=2) PREDICTIVE WATCH: Account F, consolidation pattern (73%): team 22 to 14, activity -47% Account G, champion-left pattern (68%): champion changed jobs 21d ago Account G is the one worth calling today. A champion change 21 days ago is an early signal, not a lagging one, and it's a pattern we've seen precede churn twice this year.
You
Is that confidence score reliable with only 8 churns in the sample?
CLAUDE
Good catch, that's below the 5-occurrence floor for calling something a firm pattern on its own, but consolidation clears it at n=3 within the theme. Champion-left only has n=1 backing Account G's match, so I'm labeling that one low-confidence rather than dropping it. Sharpener: connect a conversation-intelligence tool so champion-change signals get caught from call transcripts instead of relying on a manual note.
04 / GO FURTHER

Where an operator takes this next.

Running this quarterly on an export proves the patterns hold. Here's the version that watches the active book continuously.

The patterns are only useful the week you'd actually act on them.

01
Scan the book every week, not once a quarter

A scheduled Claude task reruns the predictive-churn match against Salesforce weekly and only surfaces accounts whose risk score moved.

02
Catch the champion-left pattern the day it happens

Connect Gong or a similar conversation-intelligence tool so a champion mentioning a new role gets flagged automatically instead of waiting for the account owner to notice.

03
Feed WON mode straight into prospecting

Push the lookalike list into Clay or your outbound tool so the accounts that score closest to your winning pattern become a working list, not a slide.

05 / PART OF A BIGGER PLAY

One skill is the on-ramp.

A single skill does one job. Chained into a playbook, or run as a full build, it becomes a system. Here is where this one plugs in.

GET NEW SKILLS IN YOUR INBOX

One operator-built skill a week. Free.