home / skills / onewave-ai / claude-skills / deal-momentum-analyzer

deal-momentum-analyzer skill

safe

This skill analyzes deal momentum by evaluating email response times, meetings, and stakeholder engagement to predict close probability and provide actionable

npx playbooks add skill onewave-ai/claude-skills --skill deal-momentum-analyzer

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

1.4 KB

---
name: deal-momentum-analyzer
description: Score deal velocity based on email response times, meeting frequency, and stakeholder engagement. Predict which deals will close vs stall.
---

# Deal Momentum Analyzer
Score deal velocity based on email response times, meeting frequency, and stakeholder engagement. Predict which deals will close vs stall.

## Instructions

You are an expert at sales analytics and deal forecasting. Analyze deal engagement patterns, calculate momentum scores, and predict close probability with action recommendations.

### Output Format

```markdown
# Deal Momentum Analyzer Output

**Generated**: {timestamp}

---

## Results

[Your formatted output here]

---

## Recommendations

[Actionable next steps]

```

### Best Practices

1. **Be Specific**: Focus on concrete, actionable outputs
2. **Use Templates**: Provide copy-paste ready formats
3. **Include Examples**: Show real-world usage
4. **Add Context**: Explain why recommendations matter
5. **Stay Current**: Use latest best practices for sales

### Common Use Cases

**Trigger Phrases**:
- "Help me with [use case]"
- "Generate [output type]"
- "Create [deliverable]"

**Example Request**:
> "[Sample user request here]"

**Response Approach**:
1. Understand user's context and goals
2. Generate comprehensive output
3. Provide actionable recommendations
4. Include examples and templates
5. Suggest next steps

Remember: Focus on delivering value quickly and clearly!

Overview

This skill scores deal velocity by analyzing email response times, meeting frequency, and stakeholder engagement to predict which opportunities will close or stall. It combines temporal patterns and engagement signals into a concise momentum score and clear, prioritized recommendations for sales reps and managers.

How this skill works

The analyzer ingests interaction logs (emails, calendar invites, meeting notes, and participant lists) and computes metrics such as mean response lag, meeting cadence, attendee diversity, and engagement depth. These metrics feed a trained model that outputs a momentum score and probability of close, plus driving factors and next-step actions.

When to use it

Prioritizing pipeline reviews to focus on deals most likely to close this quarter
Coaching reps with evidence-based actions to revive stalled opportunities
Allocating SDR/AE time based on deal urgency and likelihood
Generating executive summaries of pipeline health for weekly forecasting
Triggering automated outreach when engagement drops below thresholds

Best practices

Feed complete interaction histories including timestamps and attendee roles for accurate scoring
Regularly calibrate thresholds to your sales cycle length and deal size
Combine score outputs with CRM deal stage and recent activity notes for context
Surface the top 2–3 actionable recommendations rather than long lists
Use the momentum score as a decision input, not the sole decision-maker

Example use cases

Run a weekly pipeline sweep to surface top 10 deals by momentum score for close coaching
Trigger an automated re-engagement email when response time exceeds a predefined SLA
Coach an AE with a tailored script and meeting objective when stakeholder engagement is low
Flag large deals with declining meeting cadence for immediate leadership review
Create a forecast adjustment report showing predicted closes and needed interventions

FAQ

What data sources are required?

Email timestamps, calendar events, meeting participants, and any logged engagement notes are the core inputs. More behavioral signals improve accuracy.

How reliable is the predicted close probability?

Predictions are probabilistic and depend on data completeness and model calibration. Use the score to prioritize action and combine it with qualitative insights.