Deal Scoring Engine
Overview
The Deal Scoring Engine skill provides automated, consistent evaluation of investment opportunities against defined criteria. It generates composite scores based on thesis alignment, market opportunity, team quality, and business traction to support pipeline prioritization and investment decisions.
Capabilities
Thesis Alignment Scoring
- Match opportunities against fund investment thesis
- Sector, stage, and geography fit assessment
- Strategic priority alignment scoring
- Anti-thesis and exclusion criteria flagging
Market Opportunity Assessment
- TAM/SAM/SOM scoring based on market data
- Market growth rate and timing assessment
- Competitive intensity evaluation
- Regulatory and macro environment scoring
Team Evaluation Scoring
- Founder background and experience assessment
- Domain expertise and market knowledge scoring
- Team completeness and capability gaps
- Track record and references scoring
Traction and Metrics Scoring
- Revenue and growth rate benchmarking
- Unit economics (LTV/CAC, margins) scoring
- Engagement and retention metrics assessment
- Capital efficiency and burn rate evaluation
Composite Score Generation
- Weighted composite scoring with configurable weights
- Stage-appropriate scoring models (seed vs. growth)
- Sector-specific scoring adjustments
- Historical score calibration against outcomes
Usage
Score New Deal
Input: Company data, metrics, team information
Process: Apply scoring models across dimensions
Output: Composite score, dimension scores, flags, recommendations
Configure Scoring Model
Input: Scoring criteria, weights, thresholds
Process: Update scoring model parameters
Output: Configured scoring model, validation results
Benchmark Against Portfolio
Input: Deal scores, portfolio company scores
Process: Compare against portfolio at similar stage
Output: Relative ranking, percentile position, comparisons
Calibrate Model
Input: Historical deals and outcomes
Process: Analyze predictive accuracy, adjust weights
Output: Calibration report, recommended adjustments
Scoring Dimensions
| Dimension |
Weight Range |
Key Factors |
| Thesis Fit |
15-25% |
Sector, stage, geography, strategy |
| Market |
20-30% |
TAM, growth, competition, timing |
| Team |
25-35% |
Experience, domain, completeness |
| Traction |
20-30% |
Revenue, growth, unit economics |
Integration Points
- Deal Flow Tracker: Embed scores in pipeline management
- Proactive Deal Sourcing: Score for outreach prioritization
- IC Memo Generator: Include scores in investment memos
- Market Sizer: Feed market data into scoring
Best Practices
- Calibrate scoring models quarterly against outcomes
- Use stage-appropriate models (early vs. late stage)
- Document override decisions when departing from scores
- Maintain transparency on scoring methodology
- Avoid over-reliance on scores for complex decisions
1---2name: deal-scoring-engine3description: Automated deal scoring based on thesis alignment, market size, team, and traction metrics4---5
6# Deal Scoring Engine
7
8## Overview
9
10The Deal Scoring Engine skill provides automated, consistent evaluation of investment opportunities against defined criteria. It generates composite scores based on thesis alignment, market opportunity, team quality, and business traction to support pipeline prioritization and investment decisions.
11
12## Capabilities
13
14### Thesis Alignment Scoring
15- Match opportunities against fund investment thesis
16- Sector, stage, and geography fit assessment
17- Strategic priority alignment scoring
18- Anti-thesis and exclusion criteria flagging
19
20### Market Opportunity Assessment
21- TAM/SAM/SOM scoring based on market data
22- Market growth rate and timing assessment
23- Competitive intensity evaluation
24- Regulatory and macro environment scoring
25
26### Team Evaluation Scoring
27- Founder background and experience assessment
28- Domain expertise and market knowledge scoring
29- Team completeness and capability gaps
30- Track record and references scoring
31
32### Traction and Metrics Scoring
33- Revenue and growth rate benchmarking
34- Unit economics (LTV/CAC, margins) scoring
35- Engagement and retention metrics assessment
36- Capital efficiency and burn rate evaluation
37
38### Composite Score Generation
39- Weighted composite scoring with configurable weights
40- Stage-appropriate scoring models (seed vs. growth)
41- Sector-specific scoring adjustments
42- Historical score calibration against outcomes
43
44## Usage
45
46### Score New Deal
47```
48Input: Company data, metrics, team information
49Process: Apply scoring models across dimensions
50Output: Composite score, dimension scores, flags, recommendations
51```
52
53### Configure Scoring Model
54```
55Input: Scoring criteria, weights, thresholds
56Process: Update scoring model parameters
57Output: Configured scoring model, validation results
58```
59
60### Benchmark Against Portfolio
61```
62Input: Deal scores, portfolio company scores
63Process: Compare against portfolio at similar stage
64Output: Relative ranking, percentile position, comparisons
65```
66
67### Calibrate Model
68```
69Input: Historical deals and outcomes
70Process: Analyze predictive accuracy, adjust weights
71Output: Calibration report, recommended adjustments
72```
73
74## Scoring Dimensions
75
76| Dimension | Weight Range | Key Factors |
77|-----------|--------------|-------------|
78| Thesis Fit | 15-25% | Sector, stage, geography, strategy |
79| Market | 20-30% | TAM, growth, competition, timing |
80| Team | 25-35% | Experience, domain, completeness |
81| Traction | 20-30% | Revenue, growth, unit economics |
82
83## Integration Points
84
85- **Deal Flow Tracker**: Embed scores in pipeline management
86- **Proactive Deal Sourcing**: Score for outreach prioritization
87- **IC Memo Generator**: Include scores in investment memos
88- **Market Sizer**: Feed market data into scoring
89
90## Best Practices
91
921. Calibrate scoring models quarterly against outcomes
932. Use stage-appropriate models (early vs. late stage)
943. Document override decisions when departing from scores
954. Maintain transparency on scoring methodology
965. Avoid over-reliance on scores for complex decisions
a5c-ai