Free Claude skill for sales leaders

A free win-loss analysis template that Claude fills in from your closed deals

Add the free Arrows Sales Skills to Claude and it reads your won and lost deals end to end, with their calls and email, to show why your team wins, why it loses, and what to change this quarter.

Win-loss analysis
Example win-loss analysis report: win rate and cycle, three things to change this quarter, the moves that win counted on wins and losses, win rate by segment, where and why deals die next to the CRM’s loss reasons, the buying group, which methodology elements predict a win, a view by rep, profile checks and open questions
Example report with made-up deals. Yours is built from your CRM, email and calls. Open the full example

Get it running in 3 steps

Free, with no signup and no email gate.

  1. Step 1: Add the free Arrows Sales Skills to Claude

    In Claude Desktop, open Settings, then Connectors, then Add custom connector. Name it Sales Skills by Arrows, paste https://skills.arrows.to, click Add and restart Claude. Prefer files? Download the skill’s SKILL.md from GitHub and upload it under Settings, then Skills.

  2. Step 2: Connect your CRM, email, calendar and call recorder in Claude

    Turn on the Claude connectors for the tools your team uses. The more it can read, the better the read. The CRM is the one it can’t do without. No CRM connector? Drop in a CSV export of won and lost deals.

  3. Step 3: Run it, then save the summary

    Once the skills are added, type the prompt below in Claude. (In a Claude without the skills, the same words just get a generic answer.) It’s a deep read: about 15 to 30 minutes, with progress shown after each pass. At the end it offers to save a short summary, arrows-win-loss.md, that the other Sales Skills use, and to run again at the start of every quarter.

    With the skills added, type in Claude

    Run my Arrows win-loss analysis

What’s in the report

One page to share, the same win-loss template every run, so anyone who has seen one knows where to look. Every finding comes with counts on wins and on losses, and each row opens to the deals behind it.

  1. 1

    The header

    Win rate, won and lost deals, where most losses end, and the median days to win next to the days to lose.

  2. 2

    Three things to change this quarter

    The changes most likely to raise the win rate, each with the evidence and numbered steps someone could follow.

  3. 3

    The moves that win

    The 3 to 5 things that happen on wins and not on losses, counted on both sides, plus the noise: steps every deal gets that don’t decide anything.

  4. 4

    Who wins

    Win rate by segment, such as team size, lead source, industry, the buyer’s current tools, and existing vs. new customers, against the overall rate.

  5. 5

    Where and why deals die

    The stage and timing where losses happen, and the real loss reasons from reading the deals next to what the CRM says, plus how many losses have no reason at all.

  6. 6

    The buying group

    Which roles were involved on wins and who was missing on losses.

  7. 7

    Methodology

    Which parts of the team’s methodology (MEDDPICC, SPICED, BANT or its own) were known by each stage on wins vs. losses, and which predict a win.

  8. 8

    By rep

    For leaders: each rep’s win rate and cycle, and what the top rep does that the others don’t, with counts for both.

  9. 9

    Profile check and open questions

    Where the written sales process and the deals disagree, and what’s still unresolved, like wins that later cancelled.

How it decides what wins and what loses

A wrong pattern teaches the whole team the wrong lesson, so every number traces to real deals.

RuleWhat it means
Both sides, alwaysA move counts only when it’s checked on wins and on losses, like “9 of 11 wins, 3 of 20 losses.” One checked on wins alone doesn’t count.
Clean the sample firstTest records, no-shows and research or stray bookings are left out and counted separately, not treated as losses.
Current motion firstIf the product, pricing or motion changed during the period, it computes before and after separately, so old wins aren’t compared with new losses.
Watch for hindsightOnly what existed before the close date counts, and results of a deal going well, like “contract sent,” aren’t treated as moves.
Early signal, not a ruleFewer than 5 deals on either side of a comparison is called early signal, with what would confirm it.
Real reasons, not the dropdownEach lost deal it reads gets one main reason from its calls and email, compared with the CRM’s loss reason, including reasons the CRM hides under another label.
Predicts a winA methodology element predicts a win when wins had it at least 25 points more often than losses.
  • It reads every closed deal by the numbers, then about 25 wins, 25 losses and 10 stalled open deals end to end, with their calls and email.
  • It’s read only. It never changes the CRM or sends anything, and it describes the work, never the person, so the page is safe to share with the team.
  • Run “Build my sales profile” once first (about 5 to 10 minutes) and it uses your own stages and methodology. Without a profile it still runs, with stages straight from the CRM.

Use it in your quarterly review

  1. 1

    Run it at the start of the quarter and share the page before the team meeting.

  2. 2

    Spend the meeting on the three changes, not on the win rate.

  3. 3

    Turn the moves that win into plays, then check the next run for what changed.

When you want more than a report

A report tells you what’s wrong. Arrows lets you act on it.

  • During the review, a leader talks an action into a deal, and Arrows queues it on the deal’s gameplan.
  • Arrows runs your team’s Agentic Playbook on every deal, without anyone typing a prompt.
  • Reps review and send the drafts it prepares: follow-ups and CRM updates.
  • Next week, you can see whether it got done.

Arrows is its own product, not part of Claude. Your team can keep using Claude alongside it.

Agent kickoff

Every tool. Every deal. No prompts.

An Agent Architect connects your stack and sets what Arrows can do in each tool. Then Arrows does the follow-through on every deal, and your reps approve what matters.

Book an agent kickoff

Win-loss analysis: common questions

What is a win-loss analysis?

A win-loss analysis looks at closed deals to find out why a team wins and why it loses. A useful one counts each pattern on both sides, wins and losses, and checks the real loss reason from the deal’s calls and email against what the CRM recorded.

What should a win-loss analysis template include?

The win rate and cycle, the changes to make this quarter, the moves seen on wins and not on losses (with counts for both), win rate by segment, where and why deals die next to the CRM’s loss reasons, who was in the buying group, which methodology elements predict a win, and a view by rep for leaders. That’s the template this skill fills in every run.

Is there a free win-loss analysis template for Claude?

Yes. The Arrows win-loss analysis is a free Claude skill that fills in the same win-loss template from your own CRM, calls and email every time it runs. Add the free Arrows Sales Skills to Claude first (connector at skills.arrows.to), then type “Run my Arrows win-loss analysis.” There’s no signup and no email gate.

Do I need to install anything to use it?

Yes, the skills themselves. Add the free Arrows Sales Skills to Claude first: in Claude Desktop, go to Settings, then Connectors, add a custom connector with the URL https://skills.arrows.to, and restart Claude. Or upload the skill file from GitHub under Settings, then Skills. Without the skills, typing “Run my Arrows win-loss analysis” only gets a generic answer, not this report. Then connect your CRM, email and call recorder so it has deals to read.

How many closed deals do you need for a win-loss analysis?

It looks back 12 months, and goes back to 24 if that gives fewer than 40 closed deals. With fewer than 10, it skips win vs. loss comparisons and describes what the closed deals have in common. Any pattern with fewer than 5 deals on a side is labelled early signal.

How long does a win-loss analysis take?

About 15 to 30 minutes in Claude. It reads in passes and shows progress as it goes, with no questions before the report unless the scope is truly unclear.

Does it change anything in our CRM?

No. It’s read only. The only thing it saves is a short summary file, arrows-win-loss.md, and only if you say yes. That file leaves out buyer names, buyer companies and exact amounts.