ReddRadar
Agent skill
deal-scoring-engine
Automated deal scoring based on thesis alignment, market size, team, and traction metrics
Install this agent skill to your Project
npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/domains/business/venture-capital/skills/deal-scoring-engine
Metadata
Additional technical details for this skill
- domain
- business
- skill id
- vc-skill-003
- specialization
- venture-capital
SKILL.md
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
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
a5c-ai/babysitter
gsd-tools
Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).
a5c-ai/babysitter
model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
a5c-ai/babysitter
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
a5c-ai/babysitter
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
a5c-ai/babysitter
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
a5c-ai/babysitter
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.
Didn't find tool you were looking for?