Analyze won and lost deals to identify patterns, improve win rates, and refine sales strategy. Use this skill whenever a rep or manager wants to understand why deals were won or lost, identify trends in pipeline outcomes, review deal performance over time, says "why did we lose that deal", "analyze our win rate", "what do our wins have in common", "post-mortem on this deal", or when conducting quarterly business reviews. Also trigger when someone uploads CRM export data for deal analysis, or when building training materials based on historical deal outcomes.
Analyzes won and lost deals to identify patterns, improve win rates, and refine sales strategy.
/plugin marketplace add https://www.claudepluginhub.com/api/plugins/jbalbu01-sales-enablement-2/marketplace.json/plugin install jbalbu01-sales-enablement-2@cpd-jbalbu01-sales-enablement-2This skill inherits all available tools. When active, it can use any tool Claude has access to.
Turn deal outcomes into actionable insights. Understanding why you win and lose is the fastest way to improve your sales process, coaching, and competitive strategy. This isn't about blame — it's about patterns.
Most teams track win rate as a number but don't systematically learn from it. Win/loss analysis reveals:
┌─────────────────────────────────────────────────────────────────┐
│ WIN/LOSS ANALYSIS │
├─────────────────────────────────────────────────────────────────┤
│ MODES │
│ 1. Single Deal — Post-mortem on one specific deal │
│ 2. Batch Analysis — Analyze a set of deals from CSV/CRM │
│ 3. Pattern Finder — Identify trends across wins and losses │
│ 4. Competitive Insight — Win/loss rates by competitor │
│ 5. Rep Performance — Analysis by rep (for managers) │
├─────────────────────────────────────────────────────────────────┤
│ INPUT OPTIONS │
│ • Describe a deal and what happened │
│ • Upload a CSV export from your CRM │
│ • Paste deal notes or CRM data │
│ • Connect CRM for automatic data pull │
├─────────────────────────────────────────────────────────────────┤
│ SUPERCHARGED (when you connect your tools) │
│ + ~~CRM: Won/lost deal data with all properties │
│ + ~~CRM: Contact roles and company profiles per deal │
│ + ~~CRM: Stage progression timing and conversion rates │
│ + ~~CRM: Rep performance comparison across deals │
│ + ~~conversation intelligence (Gong): Call transcripts for deals│
│ + ~~conversation intelligence (Gong): Talk ratios and topics │
│ + ~~conversation intelligence (Gong): Competitor mentions │
│ + ~~data enrichment (ZoomInfo): Company data for lost prospects │
│ + ~~data enrichment (LinkedIn): Champion job changes post-loss │
│ + ~~chat: Internal deal discussion and feedback │
└─────────────────────────────────────────────────────────────────┘
CRITICAL: Before asking the user to describe a deal or provide CSV data, check what MCP tools are available and pull deal data automatically. Data-driven win/loss analysis beats anecdotal recall every time.
Check if you have access to CRM tools (look for tools containing search_crm_objects, get_crm_objects, or similar).
If CRM tools ARE available:
For Single Deal Post-Mortem:
deals for the company/deal name.
dealname, amount, dealstage, closedate, createdate, pipeline, hubspot_owner_id, dealtype, description, hs_deal_stage_probability, closed_lost_reason, closed_won_reason, notes_last_contacted, num_notesfirstname, lastname, jobtitle, email, phone, company, lifecyclestagename, domain, industry, numberofemployees, annualrevenue, description, founded_yearcreatedate to closedate, time spent in each stage if stage history available.For Batch Analysis / Pattern Finder:
deals for Closed Won and Closed Lost stages in the target period.
dealname, amount, dealstage, closedate, createdate, pipeline, hubspot_owner_id, dealtype, description, closed_lost_reason, closed_won_reasonclosed_lost_reason)hubspot_owner_id + search_owners to compute per-rep win rates.
For Competitive Insight:
description or custom competitor field.Check if you have access to Gong tools (look for tools prefixed with gong_).
If Gong tools ARE available:
For Single Deal Post-Mortem:
gong_search_calls with the company name and deal date range.gong_get_transcript on key calls (first discovery, demo, negotiation).gong_get_call_details for:
For Batch Analysis:
gong_get_call_stats.gong_get_call_details on 5-10 calls from top performers vs bottom:
ZoomInfo (if available):
zoominfo_search_company to get current data on lost prospect companies.
LinkedIn (if available):
linkedin_search_leads to see if your champion at lost deals has changed jobs.
linkedin_search_companies for recent news, hiring trends.If chat tools are available (slack_search_public, slack_search_public_and_private):
"I pulled [N] closed deals from the last [period] — [N] won ($[X] total) and [N] lost ($[X] total), for a [X]% win rate. Top loss reasons: [reason 1] ([N] deals), [reason 2] ([N] deals). I found [N] Gong calls across these deals. Per CRM, [Rep A] has the highest win rate at [X]% and [Rep B] the lowest at [X]%. Running the full analysis now..."
After the auto-pull, ask ONLY for what the tools couldn't provide:
Build using ALL evidence. Cite sources throughout: "Per CRM:", "Per Gong (call 1/15):", "Per ZoomInfo:", "Per LinkedIn:", "Per Slack:", "User reported:"
memory/deal-patterns.md with newly identified win and loss patternsmemory/competitors.md with competitive win/loss datamemory/team.md with rep-specific patterns from the analysismemory/changelog.mdTell me everything about the deal:
# Deal Post-Mortem: [Company Name]
**Outcome:** [Won / Lost / No Decision]
**Deal Size:** $[amount]
**Sales Cycle:** [Duration]
**Competitor:** [Who you competed against]
**Rep:** [Name]
---
## Timeline
| Date | Event | Impact |
|------|-------|--------|
| [Date] | [First meeting] | [Initial impression] |
| [Date] | [Key event] | [Positive/negative turning point] |
| [Date] | [Decision] | [Outcome] |
---
## What Went Right
1. [Strength — with specific evidence]
2. [Strength]
## What Went Wrong
1. [Issue — with specific evidence and what could have been done differently]
2. [Issue]
## Root Cause Analysis
**Primary reason for [win/loss]:** [The single biggest factor]
**Contributing factors:**
- [Factor 1]
- [Factor 2]
---
## Qualification Assessment (Retroactive)
| MEDDIC Criterion | Score at Close | Should Have Been |
|-----------------|---------------|-----------------|
| Metrics | [0-5] | [0-5] |
| Economic Buyer | [0-5] | [0-5] |
| Decision Criteria | [0-5] | [0-5] |
| Decision Process | [0-5] | [0-5] |
| Identify Pain | [0-5] | [0-5] |
| Champion | [0-5] | [0-5] |
---
## Lessons Learned
1. **[Lesson]** — [How to apply this to future deals]
2. **[Lesson]** — [Application]
3. **[Lesson]** — [Application]
## If You Could Replay This Deal
[Specific advice on what to do differently, starting from the first interaction]
When analyzing multiple deals (from CSV upload or description):
# Win/Loss Analysis: [Period or Description]
**Deals Analyzed:** [Count]
**Win Rate:** [X]%
**Average Deal Size:** $[X] (Won) / $[X] (Lost)
**Average Cycle Length:** [X] days (Won) / [X] days (Lost)
---
## Win Patterns
Deals you won share these characteristics:
1. **[Pattern]** — Found in [X]% of wins vs [Y]% of losses
2. **[Pattern]** — [Evidence]
3. **[Pattern]** — [Evidence]
## Loss Patterns
Deals you lost share these characteristics:
1. **[Pattern]** — Found in [X]% of losses
2. **[Pattern]** — [Evidence]
3. **[Pattern]** — [Evidence]
## Competitive Breakdown
| Competitor | Deals | Wins | Losses | Win Rate | Key Differentiator |
|-----------|-------|------|--------|----------|-------------------|
| [Comp A] | [N] | [N] | [N] | [X]% | [Why you win/lose] |
| [Comp B] | [N] | [N] | [N] | [X]% | [Why you win/lose] |
| No Competitor | [N] | [N] | [N] | [X]% | [Status quo] |
## Stage Analysis
| Stage | Deals Entering | Conversion | Avg Time | Bottleneck? |
|-------|---------------|------------|----------|-------------|
| Discovery | [N] | [X]% | [Days] | [Yes/No] |
| Demo | [N] | [X]% | [Days] | [Yes/No] |
| Proposal | [N] | [X]% | [Days] | [Yes/No] |
| Negotiation | [N] | [X]% | [Days] | [Yes/No] |
| Closed | [N] | — | — | — |
---
## Recommendations
### Quick Wins (This Quarter)
1. [Actionable recommendation with expected impact]
2. [Recommendation]
### Strategic Changes (Next Quarter)
1. [Larger initiative based on patterns]
2. [Initiative]
### Enablement Gaps
1. [Training or tool need identified from analysis]
2. [Gap]
If uploading a CRM export, the more fields the better. Useful columns include:
I'll work with whatever columns you have.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.