Pm Win Loss Analysis logo

Pm Win Loss Analysis

Community
julianoczkowski
pm-win-loss-analysis

Run a Pragmatic Institute Win/Loss analysis — understand why recent evaluators did or did not buy and the steps they took in their buying process. Use when a PM says "why did we win/lose", "win-loss", "why do deals slip", "churn reasons", "why did they pick the competitor", or "interview a lost prospect". Enforces the rule that win/loss is run by an objective party not involved in the sale, and evaluates the buying PROCESS, not the salespeople. Produces a Win/Loss Interview Guide and a Win/Loss Findings Report as a Markdown or Word .docx artifact.

Overview

Publisherjulianoczkowski
Repositoryproduct-manager
Skill namepm-win-loss-analysis
Stars
51
Forks
7
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by julianoczkowski on GitHub. Read the source before you install it.

Installation

Install the Pm Win Loss Analysis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/julianoczkowski/product-manager/tree/main/skills/pm-win-loss-analysis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/julianoczkowski/product-manager.git /tmp/product-manager
mkdir -p .claude/skills
cp -r /tmp/product-manager/skills/pm-win-loss-analysis .claude/skills/pm-win-loss-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pm Win Loss Analysis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pm Win Loss Analysis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pm Win Loss Analysis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Win/Loss Analysis (Framework: Market → Win/Loss Analysis)

Rule: Win/loss should be done by someone not involved in that sales effort. You are evaluating the buying process, not the salespeople. Build a champion in sales leadership to get access, and reassure everyone you're studying how the market buys. Ideally the product team owns win/loss. See ../pm-copilot/references/framework.md.

Ranking scales (use verbatim)

  • Perception / quality (most questions): rank 1–6, where 1 = Poor, 6 = Excellent, NA = Not Applicable. (Site-visit value: 1 = Low, 6 = High.)
  • Price / value: rank 1–5, where 1 = Lower, 3 = On Par, 5 = Higher, plus "No Response."
  • Conclusion perception: rank 1–6, 1 = Poor, 6 = Excellent.

The interview guide — 8 sections (~49 questions)

1. Customer Information — Company name, address, and a contacts table (Name / Title / Phone / Email).

2. Engagement Background — Did you know of us before initial contact? (Y/N) If so, how? Prior perception of company / products & services / support (1–6). How was initial contact made? (Unsolicited RFI / Unsolicited RFP / Cold Call / Channel Lead / Web). Who made contact, and when?

3. Marketing — Which informational tools did you use? (corporate & product brochures, website, white papers, analyst reports, trade magazines, technical papers…). Rate corporate literature / product literature / website (1–6) with comments.

4. Site Visits — Did you visit customer/reference sites? (Y/N) How many live-product sites? Which sites, and rate each. Overall value of the site visits (1–6).

5. RFI/RFP Process — Was the proposal well written? Presented well visually? Did it reflect understanding of your requirements? Meet functional / implementation / support requirements? What would have made it more compelling? (each 1–6 + comments)

6. Buying Decision — What were you using before? Extent of each contact's involvement (made final decision / voted / recommended). Who else was involved (Name / Title / Role)? What were you originally looking for, and what were your selection criteria? Did our sales team understand your needs? How did you build the vendor list? Final ranking of vendors (1st/2nd/3rd)? Did you use an outside consultant? Key factors that compelled the choice. Where were we strongest / weakest? Was there a clear point where we were winning or losing? Most important criteria in choosing the winner. Winner's major strengths over the loser. Expected business benefits. What would it have taken to change the outcome?

7. Price/Value — Price/value of products vs. other vendors (1–5). Price/value of services (1–5). What feature from another vendor should we add?

8. Conclusion — Current perception of company / products / services / support (1–6). Would you consider doing business with us in the future? (Y/N + why). Would you recommend us to others? (Y/N + why). General comments.

Interview the user (batch questions)

  1. Are these wins, losses, or both — and which deals/accounts?
  2. Who will conduct the interviews? (must be someone not on that sales effort — confirm objectivity)
  3. What do you already know about each deal (competitors, criteria, outcome)?
  4. Do you want the full guide, or a short version focused on a few key questions?

Artifact templates

Win/Loss Interview Guide

markdown
# Win/Loss Interview Guide — <company / deal>

**Company:** <company>  ·  **Feature / Product:** <name>
**Author (interviewer — objective, not on the sale):** <author>  ·  **Date created:** <date>
**Scales:** perception 1–6 (1=Poor, 6=Excellent, NA) · price/value 1–5 (1=Lower, 3=On Par, 5=Higher)

## 1. Customer Information
| Contact | Title | Phone | Email |
| :-- | :-- | :-- | :-- |

## 2. Engagement Background
- Did you know of us before initial contact? (Y/N) — how?
- Prior perception: company ___ / products & services ___ / support ___ (1–6)
- How/when was initial contact made? By whom?

## 3. Marketing   ## 4. Site Visits   ## 5. RFI/RFP Process
<questions per section above, each with rating + comments>

## 6. Buying Decision
- Selection criteria; who was involved; vendor ranking; where we were strongest/weakest;
  what would have changed the outcome.

## 7. Price/Value      ## 8. Conclusion
- Price/value ratings; future consideration (Y/N); would recommend (Y/N); general comments.

Win/Loss Findings Report (after interviews)

markdown
# Win/Loss Findings — <segment / period>

**Company:** <company>  ·  **Feature / Product:** <name>
**Author:** <author>  ·  **Date created:** <date>
**Interviews:** <n wins, n losses>  ·  **Conducted by:** <objective party>

## Why we won / why we lost (patterns)
<themes across interviews, with counts>

## The buying process (steps evaluators took)
<stages, decision-makers, criteria, tools used>

## Competitor strengths & our gaps
| Competitor | Where they beat us | Evidence (# interviews) |
| :-- | :-- | ---: |

## What would have changed the outcome
<the single biggest levers, quoted>

## Recommendations
- Product / positioning / sales-enablement actions, prioritized.

Deliver the artifact

Follow ../pm-copilot/references/artifact-output.md: ask Markdown or .docx, write the .md, convert to .docx on request via your environment's native document-creation capability. Then offer the next stage: feed the patterns into pm-market-problems validation or sharpen your pm-positioning.

Frequently asked questions

What does the Pm Win Loss Analysis AI skill do?

Run a Pragmatic Institute Win/Loss analysis — understand why recent evaluators did or did not buy and the steps they took in their buying process. Use when a PM says "why did we win/lose", "win-loss", "why do deals slip", "churn reasons", "why did they pick the competitor", or "interview a lost prospect". Enforces the rule that win/loss is run by an objective party not involved in the sale, and evaluates the buying PROCESS, not the salespeople. Produces a Win/Loss Interview Guide and a Win/Loss Findings Report as a Markdown or Word .docx artifact.

Why use Pm Win Loss Analysis on TypingMind?

Because you install it once and use it with any model. Pm Win Loss Analysis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pm Win Loss Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/julianoczkowski/product-manager/tree/main/skills/pm-win-loss-analysis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pm Win Loss Analysis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pm Win Loss Analysis?

As many as you like. As long as a model supports skills, you can use Pm Win Loss Analysis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pm Win Loss Analysis AI skill free?

Yes. It is published on GitHub by julianoczkowski under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇