Smart pipeline analytics that learns from deal outcomes over time — identify patterns, predict risks, and surface coaching opportunities from pipeline data. Use this skill whenever a manager wants pipeline insights beyond basic reporting, when analyzing conversion rates, deal velocity, or stage progression, when someone says "why are we losing deals at stage X", "what's wrong with our pipeline", "pipeline trends", or when building data-driven coaching strategies. Also trigger when someone mentions pipeline health, deal velocity, conversion analysis, or RevOps analytics. This is the layer that turns pipeline data into actionable intelligence.
Analyzes pipeline data to predict deal risks, identify conversion leaks, and generate data-driven coaching strategies.
/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.
Go beyond pipeline reporting into pipeline understanding. Traditional dashboards show you what's happening — this skill tells you why and what to do about it. It learns from your deal outcomes over time, so insights get sharper with each quarter.
A CRM report says: "Your win rate is 22%." Pipeline Intelligence says: "Your win rate is 22%, down from 28% last quarter. The drop is concentrated in deals over $100K where you're competing against CompX. Reps who do multi-threaded discovery have a 35% win rate in the same segment. Here are 3 deals in your current pipeline that match the loss pattern — take action this week."
┌─────────────────────────────────────────────────────────────────┐
│ PIPELINE INTELLIGENCE │
├─────────────────────────────────────────────────────────────────┤
│ ANALYSES │
│ 1. Pipeline Health — Overall assessment with risk flags │
│ 2. Conversion Analysis — Where and why deals stall/drop │
│ 3. Velocity Analysis — What speeds up or slows down deals │
│ 4. Pattern Detection — Correlations between behaviors & wins │
│ 5. Risk Prediction — Which current deals match loss patterns │
│ 6. Coaching Signals — Data-driven coaching priorities │
├─────────────────────────────────────────────────────────────────┤
│ LEARNING │
│ • Updates deal-patterns.md with each analysis │
│ • Predictions improve as more outcomes are logged │
│ • Compares predictions to actuals to calibrate confidence │
├─────────────────────────────────────────────────────────────────┤
│ SUPERCHARGED (when you connect your tools) │
│ + ~~CRM: Full pipeline data, stage progression, deal velocity │
│ + ~~CRM: Rep performance metrics and owner segmentation │
│ + ~~conversation intelligence (Gong): Call activity per deal │
│ + ~~conversation intelligence (Gong): Talk patterns vs outcomes │
│ + ~~conversation intelligence (Gong): Competitor mention trends │
│ + ~~data enrichment (ZoomInfo): Pipeline company enrichment │
│ + ~~data enrichment (ZoomInfo): Tech stack patterns across deals│
│ + ~~data enrichment (Clay): Company signal monitoring │
│ + ~~data enrichment (LinkedIn): Stakeholder movement tracking │
│ + ~~chat: Team deal discussions and escalation signals │
└─────────────────────────────────────────────────────────────────┘
CRITICAL: Before asking the user for a CSV export or manual data, check what MCP tools are available and pull pipeline data directly.
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:
Pull all open deals. Search the deals object type for active pipeline.
dealstage NOT IN closed stages (use get_properties on deals for dealstage to discover stage IDs if needed)dealname, amount, dealstage, closedate, pipeline, hubspot_owner_id, dealtype, createdate, notes_last_contacted, notes_last_updated, num_notes, hs_deal_stage_probability, hs_forecast_amount, hs_projected_amount, num_contacted_notes, hs_lastmodifieddatelimit: 200 and paginate with offset if needed to get all dealscount_total: true (via the search) to know the full pipeline sizePull closed deals for pattern analysis. Search for recently closed deals (won and lost).
closedate in the last 90-180 daysIdentify owners. Use the search_owners tool to map hubspot_owner_id values to actual rep names.
Get stage definitions. Use get_properties on deals for the dealstage property to get all stage names and their order.
From the raw deal data, compute:
amount across won dealscreatedate to closedate for won dealsnotes_last_contacted > 14 days ago, or closedate is past dueCheck if you have access to Gong tools (look for tools prefixed with gong_).
If Gong tools ARE available:
gong_get_call_stats for the analysis period.
gong_search_calls for at-risk deals.
gong_get_call_details on a sample of won vs lost deals.
gong_search_calls with competitor names.
ZoomInfo (check for tools prefixed with zoominfo_):
zoominfo_search_company on open deal companies.
zoominfo_get_tech_stack on won vs lost deal companies.
Clay (check for tools prefixed with clay_):
clay_enrich_company on top pipeline deals.
LinkedIn (check for tools prefixed with linkedin_):
linkedin_get_profile for champions in top deals.
linkedin_search_companies for pipeline companies.
If chat tools are available (slack_search_public, slack_search_public_and_private):
Show the user what you pulled before diving into analysis:
"I pulled [N] open deals worth $[total] from your CRM, plus [N] closed deals from the last [90] days for comparison. Your pipeline has [N] reps across [N] stages. Running analysis now..."
With the raw CRM data in hand, generate the full Pipeline Intelligence Report (format below). Every metric should be computed from actual data, not estimated.
Read memory/deal-patterns.md to compare current patterns against historical insights. Flag if current data confirms or contradicts prior predictions.
After analysis:
memory/deal-patterns.md with new conversion rates, velocity benchmarks, and risk patternsmemory/team.md with per-rep performance data# Pipeline Intelligence Report
**Period:** [Date range]
**Deals Analyzed:** [N]
**Total Pipeline Value:** $[X]
---
## Health Summary
| Metric | Current | Last Period | Trend | Benchmark |
|--------|---------|------------|-------|-----------|
| Win Rate | [X]% | [X]% | ↑↓→ | [Industry avg] |
| Avg Deal Size | $[X] | $[X] | ↑↓→ | |
| Avg Cycle Length | [X] days | [X] days | ↑↓→ | |
| Pipeline Coverage | [X]x | [X]x | ↑↓→ | 3-4x target |
| Stage Conversion (Overall) | [X]% | [X]% | ↑↓→ | |
**Overall Assessment:** [2-3 sentences on pipeline health with the most important insight]
---
## Conversion Funnel
| Stage | Deals | Value | Conversion | Avg Days | Bottleneck? |
|-------|-------|-------|-----------|----------|-------------|
| Qualified | [N] | $[X] | — | — | |
| Discovery | [N] | $[X] | [X]% | [X] | [Yes/No] |
| Demo | [N] | $[X] | [X]% | [X] | [Yes/No] |
| Proposal | [N] | $[X] | [X]% | [X] | [Yes/No] |
| Negotiation | [N] | $[X] | [X]% | [X] | [Yes/No] |
| Closed Won | [N] | $[X] | [X]% | [X] | |
**Biggest Leak:** [Stage] — [X]% of deals and $[X] in value die here
**Root Cause Hypothesis:** [Based on deal patterns and outcomes]
**Recommended Action:** [Specific intervention]
---
## Risk Alerts
Deals that match historical loss patterns:
| Deal | Size | Risk Signal | Confidence | Action |
|------|------|------------|------------|--------|
| [Deal A] | $[X] | [Matches loss pattern: no champion] | [X]% | [What to do] |
| [Deal B] | $[X] | [Risk signal] | [X]% | [Action] |
---
## Pattern Insights
### What Winners Do Differently
1. [Behavior] — Found in [X]% of wins vs [Y]% of losses
2. [Behavior] — [Evidence]
3. [Behavior] — [Evidence]
### Emerging Trends
- [New pattern not previously tracked — flagged for monitoring]
---
## Coaching Priorities
Based on pipeline data, these are the highest-leverage coaching investments:
| Rep | Issue | Evidence | Suggested Coaching |
|-----|-------|---------|-------------------|
| [Rep A] | [Pattern] | [Data] | [Specific coaching conversation] |
| [Rep B] | [Pattern] | [Data] | [Coaching] |
Pipeline Intelligence improves by comparing predictions to actual outcomes:
This creates a flywheel: the more deals flow through the system, the better it gets at identifying risk and opportunity.
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.