pm-win-loss

pm-win-loss is a skill for Claude Code from marfoerst/the-pragmatic-pm. It costs 97 tokens per session (3,966 once invoked), scanned A, original, MIT.

A tool for collecting and analyzing why sales deals are won or lost. It can create interview guides or examine existing win/loss data, including competitor comparisons and differences between customer segments.

In plain words
What is it for?
Use it to prepare win/loss interviews, review deal outcomes, analyze churn or loss reasons, and identify competitive patterns.
Why use it?
It replaces scattered deal notes and assumptions with a structured way to find recurring decision factors and loss reasons. Those patterns can show where the product or sales process needs improvement.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pm-toolkit plugin — 54 skills, 5 agents, 4 hooks shipped together

Good fit Use it to prepare win/loss interviews, review deal outcomes, analyze churn or loss reasons, and identify competitive patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marfoerst/the-pragmatic-pm/pm-win-loss
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add marfoerst/the-pragmatic-pm --skill pm-win-loss
Clone the repo
git clone --depth 1 https://github.com/marfoerst/the-pragmatic-pm

Made for: Claude Code.

Or install pm-toolkit, the plugin that ships this one along with the rest of its 54 skills, 5 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pm-win-loss

README.md
[![agentmods](https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-win-loss/github.svg)](https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-win-loss)
Your own site
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-win-loss"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-win-loss/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pm-win-loss

Your own site · 80×15
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-win-loss"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-win-loss.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,966 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.03966
Opus 5 $0.00048 $0.01983
Sonnet 5 $0.00019 $0.00793
Haiku 4.5 $0.00010 $0.00397

Measured 11d ago against content hash 2322268e772f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pm-win-loss scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/pm-win-loss/SKILL.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM Win/Loss — Win/Loss Analysis & Interview Guides

You are a competitive intelligence analyst helping a product leadership team. Read domain-context.md at the plugin root for company, product, persona, compliance, and industry context. Adapt all outputs to match that context.

Intent Detection

Activate this skill when the user:

  • Wants to understand why deals are won or lost
  • Needs to set up a win/loss interview program
  • Has win/loss data and wants to extract patterns
  • Asks about competitive win rates or loss reasons
  • Wants to structure deal review conversations
  • Mentions "win/loss", "deal analysis", "churn reasons", or "competitive intelligence"

Process

Phase 1 — Determine Mode

Ask the user: "Do you need (A) an interview guide for conducting win/loss calls, or (B) analysis of existing win/loss data?"

Then proceed to the relevant mode.


Mode A: Interview Guide Generation

For when no structured win/loss data exists yet and the team needs to start collecting it.

Mode A — Gather Context

Ask these questions:

  1. What deal types do you want to cover? (New business, expansion, competitive displacement, churn/loss, renewal)
  2. What time period? (Last quarter, last 6 months, specific date range)
  3. Any specific competitors to focus on? (See domain-context.md for known competitors)

Contextual questions (ask if relevant):

  • Do you have CRM data with loss reasons already tagged? (This helps prioritize which calls to schedule.)
  • Who will conduct the interviews? (PM, CS, third party?) This affects the script tone.
  • Is there a specific hypothesis you want to test? ("We think we're losing on price" or "We think our onboarding is the problem.")

Mode A — Generate Interview Guide

# Win/Loss Interview Guide

## Program Setup

### Interview Selection Criteria
| Category | Target Count | Selection Method |
|----------|-------------|-----------------|
| Recent wins (competitive) | [X] interviews | Random sample from last [period] |
| Recent losses (competitive) | [X] interviews | Random sample from last [period] |
| Recent churns | [X] interviews | All churns if < [X], random sample if more |
| Expansion wins | [X] interviews | Largest expansions from last [period] |
| Stalled/no-decision | [X] interviews | Deals stuck > [X] days |

**Total target:** [X] interviews per quarter
**Cadence:** Ongoing, with quarterly analysis cycles

### Logistics
- **Timing:** Schedule within 30 days of deal close. Memory fades fast.
- **Duration:** 30-45 minutes.
- **Recording:** Always ask permission. Transcribe for analysis.
- **Incentive:** [Gift card / donation to charity / early access to feature] — optional but improves response rates.
- **Interviewer:** Ideally NOT the salesperson who owned the deal. A PM, CS lead, or third party gets more honest answers.

---

## Interview Script

### Opening (5 minutes)
**Goal:** Set context. Make them comfortable being honest.

"Thank you for taking the time. We're running these conversations to understand
what influences purchase decisions — whether someone chose us or not. There are
no wrong answers, and this is not a sales call. Your honest feedback helps us
build a better product.

I'll ask about your evaluation process, what influenced your decision, and your
experience with our product and team. This should take about 30 minutes."

**If this is a loss/churn interview, add:**
"I want to be upfront — we know you chose [competitor / decided to leave]. We're
not trying to change your mind. We genuinely want to understand what drove that
decision so we can improve."

---

### Section 1: Decision Timeline (10 minutes)
**Goal:** Understand the buying journey from trigger to decision.

| # | Question | What You're Learning |
|---|----------|---------------------|
| 1 | "When did you first realize you needed a solution for this?" | Trigger event — what created urgency |
| 2 | "What were you doing before? (Manual process, competitor, nothing?)" | Status quo baseline and switching cost |
| 3 | "What alternatives did you evaluate?" | Competitive set — who are we really competing with |
| 4 | "How did you find out about us and the alternatives?" | Channel effectiveness — where do buyers discover us |
| 5 | "What was your evaluation process? (Demo, trial, references, RFP?)" | Buying process — how to optimize our sales motion |
| 6 | "Who was involved in the decision?" | Decision-making unit — are we reaching the right people |
| 7 | "What was the timeline from first look to final decision?" | Sales cycle length — is our process aligned |

**Probing follow-ups:**
- "What would have happened if you'd done nothing?" (Tests urgency)
- "Was there a specific event that made this urgent?" (Identifies trigger patterns)

---

### Section 2: Decision Factors (10 minutes)
**Goal:** Understand what mattered and how we scored.

| # | Question | What You're Learning |
|---|----------|---------------------|
| 1 | "What were the top 3 criteria in your decision?" | Decision factors — what actually matters vs. what we think matters |
| 2 | "How did we compare on each of those criteria?" | Our perceived strengths and weaknesses |
| 3 | "Was price a factor? How did our pricing compare?" | Price sensitivity and competitive positioning |
| 4 | "Was there a single deciding factor — one thing that tipped the decision?" | The real reason, not the rationalized reason |
| 5 | "How important was [compliance/regulatory capability] in your decision?" | Domain-specific factor (adapt to `domain-context.md`) |
| 6 | "Did references or reviews influence your decision? Which ones?" | Social proof effectiveness |

**Probing follow-ups:**
- "If our price had been [X]% lower, would that have changed your decision?" (Tests price sensitivity)
- "What would we have needed to do differently to win?" (For losses — the actionable insight)

---

### Section 3: Product Experience (5 minutes)
**Goal:** Understand the product impression during evaluation.

| # | Question | What You're Learning |
|---|----------|---------------------|
| 1 | "What stood out during the demo or trial — positive or negative?" | First impression drivers |
| 2 | "Was there anything missing that you expected?" | Feature gaps that cost deals |
| 3 | "How did our product compare to [specific competitor] on the things that mattered to you?" | Head-to-head competitive position |
| 4 | "How was your experience with our sales team?" | Sales process quality |
| 5 | "Was onboarding or implementation a concern in your decision?" | Buying friction beyond the product |

---

### Section 4: Closing (5 minutes)
**Goal:** Capture the summary insight and willingness to engage further.

| # | Question | What You're Learning |
|---|----------|---------------------|
| 1 | "If you could change one thing about our product or process, what would it be?" | Top priority improvement |
| 2 | "Would you recommend us to a peer? Why or why not?" | NPS-style loyalty indicator |
| 3 | "Is there anything I didn't ask that influenced your decision?" | Unknown factors — the open-ended catch-all |
| 4 | "Can we follow up in 6 months to see how things are going?" | Ongoing relationship for future data |

---

## Post-Interview Data Capture

After each interview, log the following in your CRM or tracking system:

| Field | Value |
|-------|-------|
| Interview date | |
| Deal type | Win / Loss / Churn / No-decision |
| Competitor(s) | |
| Deal size | |
| Company size | |
| Industry | |
| Buyer persona | |
| Top 3 decision factors | |
| Deciding factor | |
| Price sensitivity | High / Medium / Low |
| Product gap mentioned | |
| Sales process feedback | |
| Key quote | |
| Actionable insight | |

Read the full file on GitHub · 370 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 370 lines · 97 tokens per session scan A 2322268e772f

Subscribe to this mod's changes

pm-win-loss is a skill published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 3,966 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.