@opendirectory.dev/skills 0.1.39 → 0.1.41

package/skills/vc-curated-match/evals/fintech-india-preseed.md

@@ -0,0 +1,142 @@
+# VC Curated Match Report
+
+**Product:** A payment infrastructure API for e-commerce businesses in India
+**URL:** https://example-fintech.in
+**Extracted Tags:** Data, E-commerce, FinTech, Infrastructure
+**Stage:** Pre-seed
+**Geography:** India
+**Generated:** 2026-04-23
+
+---
+
+## Top VC Matches
+
+---
+## 1. Accel India — High Confidence
+
+**Thesis:** We partner with exceptional founders from inception through all phases of private company growth in the Indian ecosystem.
+**Check Size:** $1M - $15M
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** India
+**Notable Portfolio:** Flipkart, Swiggy, Freshworks
+**Website:** https://www.accel.com/india
+**Match Score:** 70/100
+**Why this match:** This fund focuses on E-commerce, FinTech which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 2. Bain Capital Ventures — Medium Confidence
+
+**Thesis:** From seed to growth, we back founders building legendary infrastructure, fintech, application, and commerce companies.
+**Check Size:** $1M - $50M+
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** US, Global
+**Notable Portfolio:** DocuSign, SendGrid, Redis
+**Website:** https://www.baincapitalventures.com
+**Match Score:** 65/100
+**Why this match:** This fund focuses on FinTech, Infrastructure which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 3. Amplify Partners — Medium Confidence
+
+**Thesis:** We invest in technical founders building the next generation of IT infrastructure, developer tools, and data platforms.
+**Check Size:** $2M - $8M
+**Stage Focus:** Seed, Series A
+**Geography:** US
+**Notable Portfolio:** Datadog, OCTO, dbt Labs
+**Website:** https://www.amplifypartners.com
+**Match Score:** 50/100
+**Why this match:** This fund focuses on Data, Infrastructure which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 4. boldstart ventures — Medium Confidence
+
+**Thesis:** Day one partner for developer first, crypto, and SaaS founders. We love deeply technical founders solving hard infrastructure problems.
+**Check Size:** $1M - $3M
+**Stage Focus:** Pre-seed, Seed
+**Geography:** Global, US
+**Notable Portfolio:** Snyk, Blockdaemon, Superhuman
+**Website:** https://boldstart.vc
+**Match Score:** 40/100
+**Why this match:** This fund focuses on Infrastructure which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 5. Elevation Capital — Low Confidence
+
+**Thesis:** We partner with visionary founders in India across early stages to help them build category-defining businesses.
+**Check Size:** $1M - $10M
+**Stage Focus:** Seed, Series A
+**Geography:** India
+**Notable Portfolio:** Paytm, Swiggy, Meesho
+**Website:** https://elevationcapital.com
+**Match Score:** 35/100
+**Why this match:** This fund focuses on FinTech which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 6. Peak XV Partners — Low Confidence
+
+**Thesis:** Formerly Sequoia India & SEA, we partner with founders across early, growth, and public stages to build enduring companies.
+**Check Size:** $1M - $20M+
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** India, South Asia
+**Notable Portfolio:** Zomato, Pine Labs, Cred
+**Website:** https://www.peakxv.com
+**Match Score:** 35/100
+**Why this match:** This fund focuses on FinTech which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 7. Bessemer Venture Partners — Low Confidence
+
+**Thesis:** BVP helps entrepreneurs lay strong foundations to build and forge long-standing companies.
+**Check Size:** $1M - $20M+
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** Global
+**Notable Portfolio:** LinkedIn, Twilio, Shopify
+**Website:** https://www.bvp.com
+**Match Score:** 30/100
+**Why this match:** This fund focuses on FinTech which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 8. Heavybit — Low Confidence
+
+**Thesis:** The leading investor in developer-first startups. We help technical founders launch, gain traction, and build enterprise-ready companies.
+**Check Size:** $1M - $5M
+**Stage Focus:** Seed, Series A
+**Geography:** Global, US
+**Notable Portfolio:** PagerDuty, Sanity, Netlify
+**Website:** https://www.heavybit.com
+**Match Score:** 30/100
+**Why this match:** This fund focuses on Infrastructure which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 9. Index Ventures — Low Confidence
+
+**Thesis:** We back the best and most ambitious entrepreneurs across all stages to build category-defining businesses.
+**Check Size:** $1M - $20M+
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** Europe, US, Global
+**Notable Portfolio:** Dropbox, Slack, Figma
+**Website:** https://www.indexventures.com
+**Match Score:** 30/100
+**Why this match:** This fund focuses on FinTech which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+## 10. Lightspeed Venture Partners — Low Confidence
+
+**Thesis:** We invest globally in enterprise, consumer, and health founders who are shaping the future.
+**Check Size:** $1M - $25M+
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** Global
+**Notable Portfolio:** Snap, Rippling, MuleSoft
+**Website:** https://lsvp.com
+**Match Score:** 30/100
+**Why this match:** This fund focuses on FinTech which aligns with your product's identified sector(s). They are active at your target stage (Pre-seed) and correspond to your geography focus (India).
+
+---
+
+## Assumptions & Limitations
+
+- Dataset contains 25 funds verified as of 2026-04-23
+- Fund theses and portfolios change over time. Verify directly at each fund's website before outreach.
+- This tool matches based on public thesis data only. It does not reflect current deployment status or fund availability.
+- Matches are a starting point for research, not financial advice.
+- Low-confidence matches are included because no stronger sector-specific matches were found.

package/skills/vc-curated-match/evals/varnan-seed.md

@@ -0,0 +1,141 @@
+# VC Curated Match Report
+
+**Product:** Varnan is a GTM distribution platform for AI startups. It helps founders automate outreach across LinkedIn, email, and s...
+**URL:** https://varnan.tech
+**Extracted Tags:** AI, B2B SaaS, Consumer
+**Stage:** Seed
+**Geography:** Global
+**Generated:** 2026-04-23
+
+---
+
+## Top VC Matches
+
+---
+## 1. Peak XV Partners — High Confidence
+
+**Thesis:** Formerly Sequoia India & SEA, we partner with founders across early, growth, and public stages to build enduring companies.
+**Check Size:** $1M - $20M+
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** India, South Asia
+**Notable Portfolio:** Zomato, Pine Labs, Cred
+**Website:** https://www.peakxv.com
+**Match Score:** 90/100
+**Why this match:** This fund focuses on AI, B2B SaaS, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 2. Accel — High Confidence
+
+**Thesis:** We partner with exceptional founders from inception through all phases of private company growth.
+**Check Size:** $1M - $20M+
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** Global
+**Notable Portfolio:** Facebook, Atlassian, Spotify
+**Website:** https://www.accel.com
+**Match Score:** 70/100
+**Why this match:** This fund focuses on B2B SaaS, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 3. Accel India — High Confidence
+
+**Thesis:** We partner with exceptional founders from inception through all phases of private company growth in the Indian ecosystem.
+**Check Size:** $1M - $15M
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** India
+**Notable Portfolio:** Flipkart, Swiggy, Freshworks
+**Website:** https://www.accel.com/india
+**Match Score:** 70/100
+**Why this match:** This fund focuses on B2B SaaS, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 4. Andreessen Horowitz (a16z) — High Confidence
+
+**Thesis:** We invest in software eating the world. We back bold entrepreneurs building the future through technology.
+**Check Size:** $1M - $50M+
+**Stage Focus:** Seed, Series A, Growth
+**Geography:** Global, US
+**Notable Portfolio:** Facebook, Coinbase, Figma
+**Website:** https://a16z.com
+**Match Score:** 70/100
+**Why this match:** This fund focuses on AI, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 5. Blume Ventures — High Confidence
+
+**Thesis:** We are a seed and pre-seed venture fund that backs startups with both funding and active mentoring.
+**Check Size:** $500k - $3M
+**Stage Focus:** Pre-seed, Seed
+**Geography:** India
+**Notable Portfolio:** Unacademy, Purplle, GreyOrange
+**Website:** https://blume.vc
+**Match Score:** 70/100
+**Why this match:** This fund focuses on B2B SaaS, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 6. Cherry Ventures — High Confidence
+
+**Thesis:** We champion founders in Europe from their earliest days. We are generalist seed investors.
+**Check Size:** $1M - $4M
+**Stage Focus:** Pre-seed, Seed
+**Geography:** Europe
+**Notable Portfolio:** FlixBus, Auto1 Group, Forto
+**Website:** https://www.cherry.vc
+**Match Score:** 70/100
+**Why this match:** This fund focuses on B2B SaaS, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 7. Elevation Capital — High Confidence
+
+**Thesis:** We partner with visionary founders in India across early stages to help them build category-defining businesses.
+**Check Size:** $1M - $10M
+**Stage Focus:** Seed, Series A
+**Geography:** India
+**Notable Portfolio:** Paytm, Swiggy, Meesho
+**Website:** https://elevationcapital.com
+**Match Score:** 70/100
+**Why this match:** This fund focuses on B2B SaaS, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 8. First Round Capital — High Confidence
+
+**Thesis:** We are the seed-stage firm that builds the most supportive community for founders.
+**Check Size:** $1M - $4M
+**Stage Focus:** Pre-seed, Seed
+**Geography:** US
+**Notable Portfolio:** Uber, Notion, Roblox
+**Website:** https://firstround.com
+**Match Score:** 70/100
+**Why this match:** This fund focuses on B2B SaaS, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 9. Founder Collective — High Confidence
+
+**Thesis:** We are a seed-stage venture capital fund, built by founders, for founders. We back weird, wonderful, and wild startups.
+**Check Size:** $500k - $2M
+**Stage Focus:** Seed
+**Geography:** US, Global
+**Notable Portfolio:** Uber, Airtable, BuzzFeed
+**Website:** https://www.foundercollective.com
+**Match Score:** 70/100
+**Why this match:** This fund focuses on B2B SaaS, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+## 10. Greylock Partners — High Confidence
+
+**Thesis:** We partner with early-stage founders to build enterprise and consumer software companies that define new categories.
+**Check Size:** $1M - $10M
+**Stage Focus:** Seed, Series A
+**Geography:** US
+**Notable Portfolio:** Workday, Palo Alto Networks, LinkedIn
+**Website:** https://greylock.com
+**Match Score:** 70/100
+**Why this match:** This fund focuses on AI, Consumer which aligns with your product's identified sector(s). They are active at your target stage (Seed) and correspond to your geography focus (Global).
+
+---
+
+## Assumptions & Limitations
+
+- Dataset contains 25 funds verified as of 2026-04-23
+- Fund theses and portfolios change over time. Verify directly at each fund's website before outreach.
+- This tool matches based on public thesis data only. It does not reflect current deployment status or fund availability.
+- Matches are a starting point for research, not financial advice.

package/skills/vc-curated-match/scripts/fetch_product_context.py

@@ -0,0 +1,80 @@
+import re
+from typing import Dict, List, Optional
+
+TAXONOMY = {
+    "AI": ["ai", "artificial intelligence", "machine learning", "ml", "llm", "large language model", "generative ai", "gen ai", "ai-powered", "ai powered", "neural network", "nlp", "natural language processing", "deep learning"],
+    "DevTools": ["developer tools", "devtools", "coding", "programming", "software development", "sdk", "developer", "developers", "engineering team", "software engineer", "for engineers", "cli", "terminal", "command line", "command-line", "command line tool"],
+    "B2B SaaS": ["saas", "b2b", "enterprise software", "business software", "subscription software", "automation", "workflow", "productivity", "b2b software", "automate"],
+    "Open Source": ["open source", "open-source", "coss", "github", "public repo"],
+    "FinTech": ["fintech", "financial", "payment", "banking"],
+    "Crypto": ["crypto", "blockchain", "bitcoin", "ethereum", "web3", "wallet"],
+    "HealthTech": ["healthtech", "healthcare", "medical", "biotech", "wellness"],
+    "Consumer": ["consumer", "b2c", "app", "social media", "social platform", "gaming", "lifestyle"],
+    "DeepTech": ["deeptech", "robotics", "quantum", "hard tech", "science"],
+    "Infrastructure": ["infrastructure", "infra", "cloud", "backend", "hosting", "database"],
+    "Cybersecurity": ["security", "cybersecurity", "privacy", "protection", "firewall"],
+    "Marketplaces": ["marketplace", "multi-sided", "brokerage", "two-sided market", "buyer and seller"],
+    "E-commerce": ["e-commerce", "ecommerce", "shopping", "retail", "online store"],
+    "Enterprise": ["enterprise", "corporate", "large scale"],
+    "Data": ["data", "api", "rest", "graphql", "interface"]
+}
+
+from urllib.parse import urlparse
+
+def get_geography_from_url(url: str) -> str:
+    """Infer geography from URL TLD."""
+    if not url:
+        return "Global"
+    
+    try:
+        # Prepend scheme if missing for proper parsing
+        if not url.startswith(('http://', 'https://')):
+            url = 'https://' + url
+            
+        hostname = urlparse(url).hostname or ""
+        if hostname.endswith(".in"):
+            return "India"
+        if hostname.endswith(".uk") or hostname.endswith(".co.uk"):
+            return "Europe"
+        if hostname.endswith(".eu"):
+            return "Europe"
+        if hostname.endswith(".de") or hostname.endswith(".fr") or hostname.endswith(".nl"):
+            return "Europe"
+    except Exception:
+        pass
+    
+    return "Global"
+
+def extract_tags(description: str, url: str) -> List[str]:
+    """Match keywords in description and URL against taxonomy."""
+    text = f"{description} {url}".lower()
+    extracted = []
+    
+    for tag, keywords in TAXONOMY.items():
+        for kw in keywords:
+            if re.search(r'\b' + re.escape(kw) + r'\b', text):
+                extracted.append(tag)
+                break
+                
+    if not extracted:
+        return ["Generalist"]
+    
+    return sorted(list(set(extracted)))
+
+def get_product_context(description: str, url: str, stage: Optional[str] = None, geography: Optional[str] = None) -> Dict:
+    """Entry point for parsing product context."""
+    return {
+        "description": description,
+        "url": url,
+        "extracted_tags": extract_tags(description, url),
+        "stage_hint": stage,
+        "geography_hint": geography if geography else get_geography_from_url(url)
+    }
+
+if __name__ == "__main__":
+    # Quick CLI test
+    import sys
+    if len(sys.argv) > 1:
+        desc = sys.argv[1]
+        url = sys.argv[2] if len(sys.argv) > 2 else ""
+        print(get_product_context(desc, url))

package/skills/vc-curated-match/scripts/generate_report.py

@@ -0,0 +1,111 @@
+import datetime
+import json
+import os
+from typing import List, Dict
+
+def _generate_rationale(matched_tags: List[str], product_context: Dict) -> str:
+    """Generate deterministic rationale based ONLY on matched data."""
+    if not matched_tags or matched_tags == ["Generalist"]:
+        return "No direct tag overlap. Included as a generalist fund active at your target stage."
+    
+    tags_str = ", ".join(matched_tags)
+    stage = product_context.get("stage_hint") or "applicable"
+    geo = product_context.get("geography_hint") or "Global"
+    
+    return f"This fund focuses on {tags_str} which aligns with your product's identified sector(s). They are active at your target stage ({stage}) and correspond to your geography focus ({geo})."
+
+def generate_report(matches: List[Dict], product_context: Dict) -> str:
+    """Convert matched VC data into a formatted Markdown report."""
+    today = datetime.date.today().strftime("%Y-%m-%d")
+    
+    # Calculate total funds for the assumptions section
+    try:
+        data_path = os.path.join(os.path.dirname(__file__), "..", "data", "vc_funds.json")
+        with open(data_path, "r", encoding="utf-8") as f:
+            total_funds = len(json.load(f))
+    except Exception:
+        total_funds = 25 # Fallback if file isn't accessible
+    
+    # Handle empty edge case
+    if not matches:
+        return f"""# VC Curated Match Report
+
+No matches found. Try broadening your description.
+
+---
+
+## Assumptions & Limitations
+
+- Dataset contains {total_funds} funds verified as of {today}
+- Fund theses and portfolios change over time. Verify directly at each fund's website before outreach.
+- This tool matches based on public thesis data only. It does not reflect current deployment status or fund availability.
+- Matches are a starting point for research, not financial advice."""
+
+    # Header block
+    desc = product_context.get("description", "").replace("[", "\\[").replace("]", "\\]")
+    if len(desc) > 120:
+        desc = desc[:120] + "..."
+        
+    url = product_context.get("url", "").replace("[", "\\[").replace("]", "\\]")
+    tags = ", ".join(product_context.get("extracted_tags", []))
+    stage = product_context.get("stage_hint") or "Not specified"
+    geo = product_context.get("geography_hint") or "Global"
+
+    lines = [
+        "# VC Curated Match Report",
+        "",
+        f"**Product:** {desc}",
+        f"**URL:** {url}",
+        f"**Extracted Tags:** {tags}",
+        f"**Stage:** {stage}",
+        f"**Geography:** {geo}",
+        f"**Generated:** {today}",
+        "",
+        "---",
+        "",
+        "## Top VC Matches"
+    ]
+    
+    has_low_confidence = False
+    
+    # Matches block
+    for rank, match in enumerate(matches, 1):
+        fund = match.get("fund", {})
+        conf = match.get("confidence", "Low")
+        score = match.get("score", 0)
+        matched_tags = match.get("matched_tags", [])
+        
+        if conf == "Low":
+            has_low_confidence = True
+            
+        lines.append("")
+        lines.append("---")
+        lines.append(f"## {rank}. {fund.get('fund_name', 'Unknown Fund')} — {conf} Confidence")
+        lines.append("")
+        lines.append(f"**Thesis:** {fund.get('thesis', '')}")
+        lines.append(f"**Check Size:** {fund.get('check_size', '')}")
+        lines.append(f"**Stage Focus:** {', '.join(fund.get('stage_focus', []))}")
+        lines.append(f"**Geography:** {', '.join(fund.get('geography_focus', []))}")
+        lines.append(f"**Notable Portfolio:** {', '.join(fund.get('notable_portfolio', []))}")
+        
+        if fund.get("website"):
+            lines.append(f"**Website:** {fund['website']}")
+            
+        lines.append(f"**Match Score:** {score}/100")
+        lines.append(f"**Why this match:** {_generate_rationale(matched_tags, product_context)}")
+
+    # Footer block
+    lines.append("")
+    lines.append("---")
+    lines.append("")
+    lines.append("## Assumptions & Limitations")
+    lines.append("")
+    lines.append(f"- Dataset contains {total_funds} funds verified as of {today}")
+    lines.append("- Fund theses and portfolios change over time. Verify directly at each fund's website before outreach.")
+    lines.append("- This tool matches based on public thesis data only. It does not reflect current deployment status or fund availability.")
+    lines.append("- Matches are a starting point for research, not financial advice.")
+    
+    if has_low_confidence:
+        lines.append("- Low-confidence matches are included because no stronger sector-specific matches were found.")
+
+    return "\n".join(lines)

package/skills/vc-curated-match/scripts/match_vcs.py

@@ -0,0 +1,127 @@
+import json
+import os
+from typing import List, Dict, Tuple
+
+def load_funds(data_path: str) -> List[Dict]:
+    """Load data/vc_funds.json"""
+    if not os.path.exists(data_path):
+        raise FileNotFoundError(f"Dataset not found at {data_path}")
+    with open(data_path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+def score_fund(fund: Dict, product_context: Dict) -> Tuple[int, List[str]]:
+    """Score a single fund based on overlap with product context."""
+    score = 0
+    
+    # 1. Tag Overlap (max 60 points)
+    fund_tags = fund.get("industry_tags", [])
+    extracted_tags = product_context.get("extracted_tags", [])
+    if not extracted_tags:
+        extracted_tags = ["Generalist"]
+        
+    tag_points = 0
+    matched_tags = []
+    
+    for tag in extracted_tags:
+        if tag in fund_tags:
+            if tag == "Generalist":
+                tag_points += 5
+            else:
+                tag_points += 20
+            matched_tags.append(tag)
+            
+    tag_points = min(tag_points, 60)
+    score += tag_points
+    
+    # 2. Stage Match (max 20 points)
+    stage_points = 0
+    stage_hint = product_context.get("stage_hint")
+    fund_stages = fund.get("stage_focus", [])
+    
+    STAGE_ORDER = {"Pre-seed": 0, "Seed": 1, "Series A": 2, "Growth": 3}
+    
+    if not stage_hint:
+        stage_points = 10
+    elif not fund_stages:
+        pass # skip stage scoring
+    else:
+        if stage_hint in fund_stages:
+            stage_points = 20
+        else:
+            is_adjacent = False
+            if stage_hint in STAGE_ORDER:
+                hint_idx = STAGE_ORDER[stage_hint]
+                for f_stage in fund_stages:
+                    if f_stage in STAGE_ORDER and abs(STAGE_ORDER[f_stage] - hint_idx) == 1:
+                        is_adjacent = True
+                        break
+            if is_adjacent:
+                stage_points = 10
+
+    score += stage_points
+    
+    # 3. Geography Match (max 20 points)
+    geo_points = 0
+    geo_hint = product_context.get("geography_hint")
+    fund_geo = fund.get("geography_focus", [])
+    if not fund_geo:
+        fund_geo = ["Global"]
+        
+    if not geo_hint or geo_hint == "Global":
+        geo_points = 10
+    elif fund_geo == ["India"] and geo_hint == "US":
+        geo_points = 0
+    elif geo_hint in fund_geo:
+        geo_points = 20
+    elif "Global" in fund_geo:
+        geo_points = 15
+        
+    score += geo_points
+    
+    # 4. Final Penalties
+    # Heuristic 1: India-only funds in US searches penalty
+    if geo_hint == "US" and "India" in fund_geo and "US" not in fund_geo and "Global" not in fund_geo:
+        score = max(0, score - 30)
+        
+    # Heuristic 2: Primary focus mismatch 
+    if fund_tags and extracted_tags:
+        if fund_tags[0] not in extracted_tags and tag_points <= 20:
+            score = max(0, score - 15)
+    
+    return score, matched_tags
+
+def get_confidence_tier(score: int) -> str:
+    """Return High/Medium/Low based on score."""
+    if score >= 70:
+        return "High"
+    if score >= 40:
+        return "Medium"
+    return "Low"
+
+def match_vcs(product_context: Dict, data_path: str = "data/vc_funds.json") -> List[Dict]:
+    """Score all funds and return prioritized matches."""
+    funds = load_funds(data_path)
+    scored_funds = []
+    
+    for fund in funds:
+        score, matched_tags = score_fund(fund, product_context)
+        scored_funds.append({
+            "fund": fund,
+            "score": score,
+            "confidence": get_confidence_tier(score),
+            "matched_tags": matched_tags
+        })
+        
+    scored_funds.sort(key=lambda x: (-x["score"], x["fund"].get("fund_name", "")))
+    
+    if all(f["score"] == 0 for f in scored_funds):
+        generalists = [f for f in funds if "Generalist" in f.get("industry_tags", [])][:5]
+        return [{
+            "fund": g,
+            "score": 0,
+            "confidence": "Low",
+            "matched_tags": ["Generalist"],
+            "warning": "No strong matches found. Showing generalist funds only."
+        } for g in generalists]
+        
+    return scored_funds[:10]