Deal Evaluate Skill

Automated dealflow evaluation pipeline with anti-bias MoE layer and True Potential Council for IASV investment decisions.

Invocation

cd /path/to/pipeline/Deals/CompanyName/
/deal-evaluate

Auto-discovers materials in the folder, extracts company name, uses web search to fill gaps.

/deal-evaluate --company "CompanyName" --website "https://company.com"
/deal-evaluate --quick-screen
/deal-evaluate --rerun-council

Minimum input: A folder with any company materials. Enhanced with: Pitch deck, meeting notes, data room materials, founder LinkedIn URLs, deal terms.

Execution Steps

Step 1: Quick Screen

Check thesis fit against IASV criteria (stage, check size, geography, sector, valuation). Output: PASS (stop) | INVESTIGATE | DEEP-DIVE.

Step 2: Parallel Deep Analysis

Execute four research streams in parallel:

Market researcher:

1. WebSearch "{company_name} TAM market size", "{sector} market size 2025 forecast"
2. Cross-reference with industry reports (Gartner, Statista, Grand View Research)
3. Calculate SAM (geographic/segment filter on TAM) and SOM (realistic capture at current stage)
4. Output: market size table (TAM/SAM/SOM with sources), growth rate, key tailwinds/headwinds

Biographical researcher:

1. WebSearch "{founder_name}" LinkedIn, then WebFetch their LinkedIn profile URL
2. Verify each claimed role: WebSearch "{founder_name}" "{previous_company}" for press/announcements
3. Check for prior exits: WebSearch "{founder_name}" acquisition OR exit OR sold
4. Red flag scan: WebSearch "{founder_name}" lawsuit OR fraud OR controversy
5. Output: founder profile with verified/unverified claims flagged

Competitive analyst:

1. WebSearch "{company_name}" competitors, "{product_category}" startups 2025 2026
2. Check Crunchbase/PitchBook: WebSearch "{competitor_name}" funding raised
3. Map positioning: price point, target segment, key differentiator per competitor
4. Output: competitive landscape table (5+ competitors) with moat assessment

VC analyst:

1. Extract unit economics from deck/materials: CAC, LTV, gross margin, burn rate
2. Valuation benchmarking: WebSearch "{sector}" seed valuation 2025 2026 median
3. Build three scenarios using company's growth rate as base:
   • Bear: 50% of stated growth, 2x churn
   • Base: stated metrics hold
   • Bull: stated growth + expansion into adjacent segment
4. Output: financial summary with scenario table at 12/24/36 months

Step 2.5: True Potential Council (Ed's Framework)

Three weighted dimensions: Defensibility (0.35), Market Velocity (0.35), Expansion (0.30). Produces True Potential Score (1-5) with TAM calibration and wedge classification.

Full council prompts and scoring rubrics: See TRUE-POTENTIAL-COUNCIL.md

Step 3: Anti-Bias MoE Layer

Four council members challenge the thesis: Skeptical Judge, Conservative Analyst, Devil's Advocate, Value Investor. Each scores on /100 scale with a vote (INVEST/INVESTIGATE/PASS). Consensus = weighted average.

Full MoE prompts and thresholds: See ANTI-BIAS-MOE.md

Step 4: Synthesis & Output

Generate ONE consolidated investment memo (15-20 pages): Executive Summary, Company Overview, Team Assessment, Market Analysis, Competitive Landscape, Financial Analysis, True Potential Assessment, Anti-Bias Council Review, Scorecard, Recommendation, Sources.

Do NOT create separate files for individual analysis phases.

Step 5: Arithmetic Verification (MANDATORY)

Seven-point checklist: scorecard math, TPS arithmetic, header-body reconciliation, scale consistency, no ad-hoc adjustments, signal validation, base-score-only headers.

Full verification checklist: See VERIFICATION-CHECKLIST.md

IASV Scorecard

Signal thresholds: 3.8-5.0 = INVEST | 2.8-3.7 = INVESTIGATE | Below 2.8 = PASS

Output Artifacts

Primary: tracks/F-Dealflow/pipeline/Deals/{Company}/{COMPANY}-EVALUATION.md

Secondary (optional): tracks/F-Dealflow/pipeline/summaries/{company}-summary.yaml — Notion-compatible YAML for pipeline database.

Scoring Rubric: See tracks/F-Dealflow/templates/IASV-SCORING-RUBRIC.md

Completion Checklist

• Quick screen completed with clear signal
• All 4 parallel analyses completed with 3+ sources for market, 2+ for founders
• Bear/base/bull scenarios modeled
• True Potential Score calculated with TAM calibration
• Anti-bias council consensus generated with all 7 skeptical questions answered
• ONE consolidated evaluation document generated with final signal + confidence
• Step 5 arithmetic verification passed — all 7 checks confirmed

Failure Handling