Agent skill

Win Loss Analysis

by growthack88 in growthack88/growth-marketing-os

Win/loss analysis for B2B SaaS. An agent skill from growthack88/growth-marketing-os.

MITAuto-check passedMarketing & SEO

Install Win Loss Analysis

skills CLI
$ npx skills add growthack88/growth-marketing-os --skill win-loss-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install growthack88/growth-marketing-os win-loss-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/growthack88/growth-marketing-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/community/win-loss .claude/skills/win-loss-analysis && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
win-loss-analysis
GitHub stars
116
Token cost
~2.5k tokens
SKILL.md length
1,014 words
Files
8 (incl. references)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Win/loss analysis for B2B SaaS. An agent skill from growthack88/growth-marketing-os.

  • Works in 3 steps: Transcript processing — classify… → Pattern aggregation — group by outcome,… → Insight synthesis — state pattern,…
  • Tasks that involve Meeting notes and agendas
  • SKILL.md covers Claude Code triggers, Input requirements, Process and Core frameworks, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Win Loss Analysis is an agent skill from growthack88/growth-marketing-os. Win/loss analysis for B2B SaaS. Analyzes sales call transcripts across 6 dimensions (product, messaging, GTM/sales, pricing, competition, customer context) to extract why deals are won, lost, retained, or churned. Produces aggregate patterns with verbatim-quote evidence, frequency counts, confidence levels, and strategic recommendations. Includes process steps, output template, quality checklist, extraction patterns, and a worked 5-transcript example.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/auto-update.md`, `references/example-analysis.md` and `references/extraction-patterns.md`).

It sits in Marketing & SEO, covering Meeting notes and agendas, Go-to-market strategy and Multi-tenancy. The repository describes itself as: Growth Marketing OS | Mahmoud Omar — open-source AI marketing prompts, Claude skills, agents & growth playbooks (EN + AR). The licence is MIT.

When your agent uses it

  • Tasks that involve Meeting notes and agendas
  • Tasks that involve Go-to-market strategy
  • Tasks that involve Multi-tenancy

Example prompts

  • “/win-loss-analysis”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Transcript processing — classify outcome, identify speakers, extract customer context, pull verbatim quotes for the 6 dimensions
  2. Pattern aggregation — group by outcome, count frequency, rank patterns (3+ mentions), cross-reference by ICP/competitor/persona
  3. Insight synthesis — state pattern, provide evidence with frequency + confidence, identify opportunity, generate executive summary

What it can do on your machine

Read from SKILL.md and the folder at commit c6b55c7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Win Loss Analysis loads about 2.5k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 118 tokens; SKILL.md has 1,014 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~118
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from growthack88/growth-marketing-os at commit c6b55c7, republished under its MIT licence (© growthack88). 1,014 words, ~2,537 tokens.

Download SKILL.mdSave it as .claude/skills/win-loss-analysis/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
win-loss-analysis
description
Win/loss analysis for B2B SaaS. Analyzes sales call transcripts across 6 dimensions (product, messaging, GTM/sales, pricing, competition, customer context) to extract why deals are won, lost, retained, or churned. Produces aggregate patterns with verbatim-quote evidence, frequency counts, confidence levels, and strategic recommendations. Includes process steps, output template, quality checklist, extraction patterns, and a worked 5-transcript example.
version
2.0
author
genesys-growth
last_updated
2026-06-08
<!--
COMMUNITY SKILL — included under its original MIT license.
Source: https://github.com/matteotitta/genesys-skills by Matteo Titta (MIT).
License text: ../LICENSE-genesys-skills.txt
Curated into Growth Marketing OS by Mahmoud Omar (mahmoudomar.com) — this file
is NOT original work by the repo author; see /skills/community/README.md.
-->

Win/loss analysis

Analyze sales call transcripts to extract actionable insights on why deals are won, lost, retained, or churned. Cross-reference findings with ICP, firmographics, and competitive context to produce strategic recommendations.

Knowledge type: win-loss-analysis Maturity on first run: emergent → validated after team review


Claude Code triggers

Invoke when user says:

  • "Win/loss analysis"
  • "Analyze sales calls"
  • "Why did we win/lose"
  • "Churn analysis"
  • "Retention analysis"
  • "Sales call insights"
  • "Deal outcome patterns"
  • "Customer feedback synthesis"
  • "Analyze these transcripts"
  • "What patterns in our sales calls"

Do NOT invoke when:

  • User wants general transcript analysis → use a generic transcript skill
  • User wants competitor research → use competitor-research
  • User wants a single customer interview write-up → use a transcript skill
  • User wants sales enablement assets → use a sales-enablement skill

Input requirements

Required
InputDescriptionSource
TranscriptsSales call transcripts with customer name and outcomeUser provides
OutcomeWin/Loss/Retention/Churn for each callUser specifies or infer
Optional (improve quality)
InputHow it helps
Website URL per customerFirmographics cross-reference
Product/ICP documentDefine in-scope product capabilities
Market/GTM documentPositioning and competitive landscape
Sales notes columnAdditional context (stage, deal size)
Competitor namesPre-identify competitors to watch for
Validation

Before proceeding: at least one transcript provided; outcome known or inferable from transcript; customer name identifiable.

If inputs are missing: ask the user for transcripts. Clarify if outcome should be inferred from transcript signals.

Transcript intake — normalize, redact, bind to evidence

Transcripts arrive in many shapes (Gong, Fireflies, Otter, Grain, Zoom/Avoma VTT, SRT, recorder JSON, or plain pasted text). Before Phase 1, normalize whatever you're handed into one shape — speaker-attributed turns with timestamps where present. Two rules apply to every transcript before analysis:

  • Redact PII first. Mask end-client names, emails, and account numbers before processing; keep roles, company, and deal context. (Load-bearing for regulated industries.)
  • Bind every claim to evidence. Every extracted pattern cites a verbatim quote plus the speaker; normalized, speaker-attributed turns make that attribution reliable.

Process

The analysis runs in 3 phases. Read references/process.md for the full step-by-step (4 transcript-processing steps, 4 aggregation steps, 4 synthesis steps, plus per-phase checkpoints and the process flowchart).

Phase summary:

  1. Transcript processing — classify outcome, identify speakers, extract customer context, pull verbatim quotes for the 6 dimensions
  2. Pattern aggregation — group by outcome, count frequency, rank patterns (3+ mentions), cross-reference by ICP/competitor/persona
  3. Insight synthesis — state pattern, provide evidence with frequency + confidence, identify opportunity, generate executive summary

Core frameworks

Analysis modes
ModeWhen to useOutput
Single callDeep analysis of one transcriptFull insight extraction per dimension
Batch analysisMultiple transcripts (3-20 calls)Aggregated patterns with frequency counts
Comparison matrixWin vs. loss OR retention vs. churnSide-by-side pattern comparison

Default to batch analysis mode when multiple transcripts are provided.

6 analysis dimensions
#DimensionWin signalsLoss signals
1Product"Exactly what we need," feature praised"Missing [feature]," "Doesn't do [X]"
2Messaging"Now I understand why this matters""What does it actually do?"
3GTM/Sales"You really understand our problem""Demo didn't address our needs"
4Pricing"Fair price," "good value""Too expensive," "over budget"
5Competition"Chose you over [competitor]""Going with [competitor]"
6Customer context"Need this now," deadline-driven"No rush," "maybe next year"
Confidence scoring
LevelDefinitionWhen to apply
High3+ calls with consistent patternClear recurring theme
Medium2 calls or inferred from strong signalsEmerging pattern
LowSingle mention or indirect referencePossible outlier
Outcome classification
OutcomeDefinitionKey signals
WinDeal closed, contract signed"We're moving forward," pricing confirmed
LossDeal lost to competitor or no-decision"Going with [competitor]," "Not right now"
RetentionExisting customer renewing/expandingRenewal discussion, expansion
ChurnExisting customer leaving/reducingCancellation, "not getting value"

Show full SKILL.md (412 more words)Show less

Output

Produce a single win/loss report markdown file. Template + iteration prompts library: references/output-format.md.

Pre-delivery quality checklist + worked example + anti-examples: references/quality.md.

Auto-update protocol (feedback signals, pattern detection, skill-update template): references/auto-update.md.


Anti-hallucination guardrails

  1. Quote verbatim. All insights must trace to specific transcript quotes.
  2. Never invent patterns. If a pattern appears in only one call, label it "Single mention — pattern unconfirmed."
  3. State frequency. Always note how many calls support each finding (e.g., "4 of 7 calls").
  4. Acknowledge gaps. If a dimension has no data, mark "Not discussed in transcripts."
  5. Distinguish roles. Tag who said what — prospect vs. sales rep vs. champion.

Gotchas

  • Correlation as causation. Reports "deals with longer sales cycles were lost" as if cycle length caused the loss → always distinguish patterns from causes. Use "associated with" not "caused by".
  • Small sample bias. Draws conclusions from 2-3 deals instead of waiting for sufficient data → flag sample size prominently. Minimum 5 wins and 5 losses for reliable patterns.
  • Missing verbatim quotes. Summarizes what buyers said instead of extracting exact quotes → verbatim quotes are the primary deliverable. Summaries are secondary.
  • Single-dimension analysis. Only looks at win/loss by competitor, missing dimensions like deal size, ICP segment, or sales cycle stage → cross-tabulate across at least 3 dimensions.
  • Conflates product feedback with sales insights. Mixes "they wanted feature X" with "they didn't trust our team" → separate product gaps from sales execution issues. They feed into different downstream work.

Integration with other skills

SkillRelationshipUsage
transcript analysisRelatedUse for general transcripts, not sales calls
sales enablementDownstreamFeed insights into battlecards and objection handlers
product messagingDownstreamUpdate messaging based on win patterns
competitor researchRelatedCross-reference competitor mentions

Reference files

FilePurpose
references/process.mdFull 3-phase step-by-step + flowchart
references/output-format.mdWin/loss report template + iteration prompts
references/quality.mdPre-delivery checklist + worked example + anti-examples
references/auto-update.mdFeedback signal detection + pattern rules
references/extraction-patterns.mdSignal patterns for each dimension
references/output-template.mdLegacy report template (kept for reference)
references/example-analysis.mdWorked example with 5 transcripts

Data integration

Level: 0 — Context (heavy pulls)

If you run win/loss inside a connected environment, pull transcripts and deal context fresh:

SourceWhat to pullWhen
Meeting recorder (Granola, Gong, Fireflies, etc.)Sales call transcripts and deal discussionsAlways
Team chat (Slack, etc.)Deal discussion threads and competitive intelAlways

Fallback (no integrations): user-provided call transcripts or recordings; manual deal review notes.


Changelog

VersionDateChanges
2.02026-01-16Refactored to v2.0 template: structured phases, evidence-ready insights, iteration prompts, auto-update rules
1.0PreviousInitial skill creation with 6 dimensions

© growthack88, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in skills/community/win-loss of growthack88/growth-marketing-os.

  • SKILL.md
  • references/auto-update.md
  • references/example-analysis.md
  • references/extraction-patterns.md
  • references/output-format.md
  • references/output-template.md
  • references/process.md
  • references/quality.md

Open the folder on GitHubat commit c6b55c7

Compare with similar skills

Win Loss Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Win Loss Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Win Loss Analysis this skillgrowthack88/growth-marketing-os116—~2.5kAutomated safety check: PassMIT
Gingiris B2b GrowthGingiris-1031/Competitor-analysis-tool110—~1.2kAutomated safety check: PassNone
Marketing PlanNexus-JPF/note-companion8705 repos~5.2kAutomated safety check: PassMIT
Revenue Centric Designheliocosta-dev/revenue-centric-design740—~1.6kAutomated safety check: PassCustom licence
Startup Designferdinandobons/startup-skill1.2k—~8.1kAutomated safety check: PassMIT
Jaredrhod Marketingjaredrhod/ai-marketing-skills282—~584Automated safety check: PassCC-BY-SA-4.0

Similar skills

  • Gingiris B2b Growth

    Gingiris-1031/Competitor-analysis-tool

    🇺🇸 B2B SaaS Growth — PLG vs SLG Playbook — Diagnose whether your problem is distribution, pricing, or PMF.

    110 GitHub stars~1.2k tokensUpdated today
    Marketing & SEOAuto-check passed
  • Marketing Plan

    Nexus-JPF/note-companion

    When the user needs a comprehensive marketing plan for a client, a company they advise, or their own product.

    870 GitHub starsUsed in 5 repos~5.2k tokens
    Marketing & SEOAuto-check passed
  • Revenue Centric Design

    heliocosta-dev/revenue-centric-design

    Playbook for designing SaaS and startup products that convert, retain, and monetize — landing pages & CRO, checkout & forms, onboarding/activation, churn reduction, pricing psychology, dashboards…

    740 GitHub stars~1.6k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Startup Design

    ferdinandobons/startup-skill

    Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.

    1.2k GitHub stars~8.1k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Jaredrhod Marketing

    jaredrhod/ai-marketing-skills

    Run any marketing task the way jaredrhod actually runs it. An agent skill from jaredrhod/ai-marketing-skills.

    282 GitHub stars~584 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Linkedin Employee Advocacy

    sergebulaev/linkedin-skills

    Stand up and run a LinkedIn employee advocacy program for a marketing or sales team.

    4.4k GitHub starsUsed in 1 repo~1.5k tokens
    Marketing & SEOAuto-check passed

More from growthack88/growth-marketing-os

All 13 skills in this repo
  • Mena Ads

    growthack88/growth-marketing-os

    MENA Ads Command Center — a complete paid-ads operating system for the Arab world (Egypt, KSA, UAE, GCC, Levant, North Africa) and global accounts.

    116 GitHub stars~2.5k tokensUpdated 6 days ago
    Auto-check passed
  • Arabic Copy Localizer

    growthack88/growth-marketing-os

    Marketing copy localization skill that converts English marketing copy (ads, landing pages, emails, CTAs) into native Egyptian Arabic عامية — or GCC dialect on request — with natural English…

    116 GitHub stars~1k tokensUpdated 6 days ago
    Auto-check passed
  • Benchmark Analyst

    growthack88/growth-marketing-os

    Marketing benchmark triage skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check passed
  • Cod Operations Analyst

    growthack88/growth-marketing-os

    COD (cash-on-delivery) e-commerce operations skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.3k tokensUpdated 6 days ago
    Auto-check passed
  • Conversion Copywriter

    growthack88/growth-marketing-os

    Direct-response copywriting skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.4k tokensUpdated 6 days ago
    Auto-check passed
  • Funnel Decomposition Analyst

    growthack88/growth-marketing-os

    Senior performance analyst skill that answers "why did sales drop (or jump)?" using rigorous funnel decomposition.

    116 GitHub stars~861 tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Win Loss Analysis

What does Win Loss Analysis do?

Win/loss analysis for B2B SaaS. An agent skill from growthack88/growth-marketing-os. Win Loss Analysis is an agent skill from growthack88/growth-marketing-os. Win/loss analysis for B2B SaaS.

When should I use Win Loss Analysis?

Win Loss Analysis fits situations like: tasks that involve Meeting notes and agendas; tasks that involve Go-to-market strategy; tasks that involve Multi-tenancy.

How do I install Win Loss Analysis in Claude Code?

Run `npx skills add growthack88/growth-marketing-os --skill win-loss-analysis -a claude-code`. Or copy the skill folder (skills/community/win-loss in growthack88/growth-marketing-os) into .claude/skills/win-loss-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Win Loss Analysis in Codex?

Run `npx skills add growthack88/growth-marketing-os --skill win-loss-analysis -a codex`. Or copy the skill folder (skills/community/win-loss in growthack88/growth-marketing-os) into .agents/skills/win-loss-analysis in your project. Codex loads it when a task matches its description.

Can I use Win Loss Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add growthack88/growth-marketing-os --skill win-loss-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/win-loss-analysis, .gemini/skills/win-loss-analysis, .github/skills/win-loss-analysis and .opencode/skills/win-loss-analysis in your project.

What does Win Loss Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Win Loss Analysis is instructions for the agent only.

Does Win Loss Analysis access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Win Loss Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Win Loss Analysis use?

Win Loss Analysis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Win Loss Analysis use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.

What are the alternatives to Win Loss Analysis?

Skills that share tags, products or a category with Win Loss Analysis: Gingiris B2b Growth (Gingiris-1031/Competitor-analysis-tool, 110 stars), Marketing Plan (Nexus-JPF/note-companion, 870 stars), Revenue Centric Design (heliocosta-dev/revenue-centric-design, 740 stars) and Startup Design (ferdinandobons/startup-skill, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Win Loss Analysis?

growthack88 (a GitHub user) maintains it in growthack88/growth-marketing-os, which has 116 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 2, 2026.

Source: growthack88/growth-marketing-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.