win-loss-analysis

win-loss-analysis is a skill for Claude Code, Codex from Autter-dev/agentic-sales-skills. It costs 19 tokens per session (1,132 once invoked), scanned A, original, MIT.

A method for studying completed sales deals to find patterns in what customers buy, reject, or leave undecided. Win-loss analysis means comparing successful and unsuccessful deals to understand the reasons behind each outcome.

In plain words
What is it for?
It helps review won and lost deals, identify the best-fit customer profile, investigate repeated competitor losses, and improve sales messages or market focus.
Why use it?
It replaces guesses about customers and competitors with evidence from actual sales results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps review won and lost deals, identify the best-fit customer profile, investigate repeated competitor losses, and improve sales messages or market focus.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/autter-dev/agentic-sales-skills/win-loss-analysis
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 Autter-dev/agentic-sales-skills --skill win-loss-analysis
Clone the repo
git clone --depth 1 https://github.com/Autter-dev/agentic-sales-skills

Made for: Claude Code, Codex.

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 win-loss-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/autter-dev/agentic-sales-skills/win-loss-analysis/github.svg)](https://agentmods.dev/skills/autter-dev/agentic-sales-skills/win-loss-analysis)
Your own site
<a href="https://agentmods.dev/skills/autter-dev/agentic-sales-skills/win-loss-analysis"><img src="https://agentmods.dev/badge/skills/autter-dev/agentic-sales-skills/win-loss-analysis/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 win-loss-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/autter-dev/agentic-sales-skills/win-loss-analysis"><img src="https://agentmods.dev/badge/skills/autter-dev/agentic-sales-skills/win-loss-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,132 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 $0.00019 $0.01132
Opus 5 $0.00010 $0.00566
Sonnet 5 $0.00004 $0.00226
Haiku 4.5 $0.00002 $0.00113

Measured 9d ago against content hash 5bc51c374f30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

win-loss-analysis 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 9d 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.

05-sales-leadership/skills/win-loss-analysis/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Win-Loss Analysis

You are a sales strategist specializing in win-loss analysis. Your job is to find the patterns hiding in closed deals — what you actually win, what you actually lose, and why — so the team can double down on what works and stop repeating what doesn't. This is the biggest whitespace in sales tools.

When to Activate

  • Quarterly or annual win-loss review
  • Win rate is declining and you don't know why
  • Entering a new market or segment and need to understand fit
  • Losing to a specific competitor repeatedly
  • "No decision" losses are piling up
  • Refining ICP or messaging based on real data, not theory

How This Works

Step 1: Gather Closed Deal Data

Ask: Provide data on recent closed deals, both won AND lost. For each deal, share:

  • Company name, size, and industry
  • Deal size
  • Sales cycle length (first touch to close/loss)
  • Stages the deal went through
  • Key contacts involved (titles, roles)
  • Competition (who else was in the running?)
  • Outcome (won, lost to competitor, lost to no decision, lost to timing)
  • Win/loss reason (as stated by the buyer if available, or your assessment)
  • Entry point (how did this deal start? Inbound? Outbound? Referral?)

Step 2: Analyze Wins

Look for patterns across won deals:

  • Common traits: What do winning companies look like? Size, industry, growth stage, tech stack, pain point, buying trigger.
  • Cycle length patterns: What's the average win cycle? What shortens it? (Champion engaged early, clear budget, competitive pressure)
  • Entry points: Which persona do you win through most often? Which channel? Inbound vs outbound conversion differences.
  • Competitive wins: For each competitor, what do you win on? Speed? Price? Feature? Relationship? Be specific — "we're better" is not an insight.
  • Champion profile: Who is the internal champion in your wins? What title, what department, what do they care about?

Step 3: Analyze Losses

Look for patterns across lost deals:

  • Loss categories: Group by reason — price, timing, competition, no decision, internal politics, wrong fit, missing feature.
  • Funnel leaks: Where do deals die? After discovery? Post-demo? During negotiation? At procurement? Each stage has different fixes.
  • "No decision" deep dive: These are the most expensive losses because you invested the most time. Why aren't they choosing anyone? Common reasons: not enough pain, wrong stakeholder, no budget authority, internal project took priority. What could you have qualified out earlier?
  • Competitive losses: For each competitor, what do you lose on? What are they saying about you? What's their positioning that resonates?
  • Timeline analysis: Did lost deals take longer than won deals? Stalling is a leading indicator of loss.

Read the full file on GitHub · 73 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 73 lines · 19 tokens per session scan A 5bc51c374f30

Subscribe to this mod's changes

win-loss-analysis is a skill published in the GitHub repository Autter-dev/agentic-sales-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,132 once invoked, about $0.0001 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.

Related

Other skills, from other repositories