@opendirectory.dev/skills 0.1.40 → 0.1.42

package/skills/vc-finder/data/vc_funds.json

@@ -0,0 +1,277 @@
+[
+  {
+    "fund_name": "Y Combinator",
+    "thesis": "We provide seed funding for startups. We invest in deeply technical teams building massive companies across all domains.",
+    "check_size": "$500k",
+    "stage_focus": ["Pre-seed", "Seed"],
+    "industry_tags": ["Generalist", "B2B SaaS", "DevTools", "AI"],
+    "geography_focus": ["Global"],
+    "notable_portfolio": ["Stripe", "Airbnb", "GitLab"],
+    "website": "https://www.ycombinator.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "boldstart ventures",
+    "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"],
+    "industry_tags": ["DevTools", "Infrastructure", "Crypto"],
+    "geography_focus": ["Global", "US"],
+    "notable_portfolio": ["Snyk", "Blockdaemon", "Superhuman"],
+    "website": "https://boldstart.vc",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Heavybit",
+    "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"],
+    "industry_tags": ["DevTools", "Infrastructure", "Open Source"],
+    "geography_focus": ["Global", "US"],
+    "notable_portfolio": ["PagerDuty", "Sanity", "Netlify"],
+    "website": "https://www.heavybit.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Amplify Partners",
+    "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"],
+    "industry_tags": ["DevTools", "Infrastructure", "AI", "Data"],
+    "geography_focus": ["US"],
+    "notable_portfolio": ["Datadog", "OCTO", "dbt Labs"],
+    "website": "https://www.amplifypartners.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "OSS Capital",
+    "thesis": "We exclusively back early-stage founders building Commercial Open Source Software (COSS) companies.",
+    "check_size": "$500k - $2M",
+    "stage_focus": ["Pre-seed", "Seed", "Series A"],
+    "industry_tags": ["Open Source", "DevTools"],
+    "geography_focus": ["Global"],
+    "notable_portfolio": ["Cal.com", "Appsmith", "Hoppscotch"],
+    "website": "https://oss.capital",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Sequoia Capital",
+    "thesis": "We help the daring build legendary companies, from idea to IPO and beyond. Sequoia is an early-stage and growth-stage investor.",
+    "check_size": "$1M - $10M+",
+    "stage_focus": ["Seed", "Series A", "Growth"],
+    "industry_tags": ["Generalist", "Enterprise", "Consumer", "AI"],
+    "geography_focus": ["Global"],
+    "notable_portfolio": ["Apple", "Google", "WhatsApp"],
+    "website": "https://www.sequoiacap.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Andreessen Horowitz (a16z)",
+    "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"],
+    "industry_tags": ["Generalist", "Crypto", "Enterprise", "Consumer", "AI"],
+    "geography_focus": ["Global", "US"],
+    "notable_portfolio": ["Facebook", "Coinbase", "Figma"],
+    "website": "https://a16z.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Point Nine Capital",
+    "thesis": "We are a seed-stage venture capital firm focused on B2B SaaS and B2B marketplaces globally.",
+    "check_size": "$1M - $3M",
+    "stage_focus": ["Seed"],
+    "industry_tags": ["B2B SaaS", "Marketplaces"],
+    "geography_focus": ["Europe", "Global"],
+    "notable_portfolio": ["Zendesk", "Typeform", "Docplanner"],
+    "website": "https://www.pointnine.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Cherry Ventures",
+    "thesis": "We champion founders in Europe from their earliest days. We are generalist seed investors.",
+    "check_size": "$1M - $4M",
+    "stage_focus": ["Pre-seed", "Seed"],
+    "industry_tags": ["Generalist", "Consumer", "B2B SaaS"],
+    "geography_focus": ["Europe"],
+    "notable_portfolio": ["FlixBus", "Auto1 Group", "Forto"],
+    "website": "https://www.cherry.vc",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "First Round Capital",
+    "thesis": "We are the seed-stage firm that builds the most supportive community for founders.",
+    "check_size": "$1M - $4M",
+    "stage_focus": ["Pre-seed", "Seed"],
+    "industry_tags": ["Generalist", "B2B SaaS", "Consumer"],
+    "geography_focus": ["US"],
+    "notable_portfolio": ["Uber", "Notion", "Roblox"],
+    "website": "https://firstround.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Bessemer Venture Partners",
+    "thesis": "BVP helps entrepreneurs lay strong foundations to build and forge long-standing companies.",
+    "check_size": "$1M - $20M+",
+    "stage_focus": ["Seed", "Series A", "Growth"],
+    "industry_tags": ["Generalist", "Enterprise", "Consumer", "FinTech"],
+    "geography_focus": ["Global"],
+    "notable_portfolio": ["LinkedIn", "Twilio", "Shopify"],
+    "website": "https://www.bvp.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Index Ventures",
+    "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"],
+    "industry_tags": ["Generalist", "FinTech", "Consumer", "B2B SaaS"],
+    "geography_focus": ["Europe", "US", "Global"],
+    "notable_portfolio": ["Dropbox", "Slack", "Figma"],
+    "website": "https://www.indexventures.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Lightspeed Venture Partners",
+    "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"],
+    "industry_tags": ["Generalist", "Enterprise", "Consumer", "FinTech"],
+    "geography_focus": ["Global"],
+    "notable_portfolio": ["Snap", "Rippling", "MuleSoft"],
+    "website": "https://lsvp.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Accel",
+    "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"],
+    "industry_tags": ["Generalist", "B2B SaaS", "Consumer", "DevTools"],
+    "geography_focus": ["Global"],
+    "notable_portfolio": ["Facebook", "Atlassian", "Spotify"],
+    "website": "https://www.accel.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Bain Capital Ventures",
+    "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"],
+    "industry_tags": ["Generalist", "Infrastructure", "FinTech", "B2B SaaS"],
+    "geography_focus": ["US", "Global"],
+    "notable_portfolio": ["DocuSign", "SendGrid", "Redis"],
+    "website": "https://www.baincapitalventures.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Greylock Partners",
+    "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"],
+    "industry_tags": ["Enterprise", "Consumer", "Cybersecurity", "AI"],
+    "geography_focus": ["US"],
+    "notable_portfolio": ["Workday", "Palo Alto Networks", "LinkedIn"],
+    "website": "https://greylock.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Unusual Ventures",
+    "thesis": "We provide a breakthrough level of support for early-stage founders building enterprise tech.",
+    "check_size": "$1M - $5M",
+    "stage_focus": ["Pre-seed", "Seed"],
+    "industry_tags": ["Enterprise", "DevTools", "B2B SaaS"],
+    "geography_focus": ["US"],
+    "notable_portfolio": ["Arctic Wolf", "Harness", "Vivun"],
+    "website": "https://www.unusual.vc",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Crane Venture Partners",
+    "thesis": "We back deep tech and enterprise founders in Europe solving hard problems with data and code.",
+    "check_size": "$1M - $4M",
+    "stage_focus": ["Seed"],
+    "industry_tags": ["Enterprise", "DeepTech", "Data", "AI"],
+    "geography_focus": ["Europe"],
+    "notable_portfolio": ["Onfido", "Tessian", "Forto"],
+    "website": "https://crane.vc",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Founder Collective",
+    "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"],
+    "industry_tags": ["Generalist", "Consumer", "B2B SaaS"],
+    "geography_focus": ["US", "Global"],
+    "notable_portfolio": ["Uber", "Airtable", "BuzzFeed"],
+    "website": "https://www.foundercollective.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Benchmark",
+    "thesis": "We are a partnership of equal partners. We back mission-driven founders at the earliest stages and walk beside them for the long haul.",
+    "check_size": "$1M - $10M",
+    "stage_focus": ["Seed", "Series A"],
+    "industry_tags": ["Generalist", "Marketplaces", "Enterprise", "Consumer"],
+    "geography_focus": ["US", "Global"],
+    "notable_portfolio": ["Uber", "Twitter", "eBay", "Snapchat"],
+    "website": "https://www.benchmark.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Accel India",
+    "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"],
+    "industry_tags": ["Generalist", "B2B SaaS", "Consumer", "FinTech", "E-commerce"],
+    "geography_focus": ["India"],
+    "notable_portfolio": ["Flipkart", "Swiggy", "Freshworks"],
+    "website": "https://www.accel.com/india",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Blume Ventures",
+    "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"],
+    "industry_tags": ["Generalist", "B2B SaaS", "Consumer", "DeepTech", "HealthTech"],
+    "geography_focus": ["India"],
+    "notable_portfolio": ["Unacademy", "Purplle", "GreyOrange"],
+    "website": "https://blume.vc",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Elevation Capital",
+    "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"],
+    "industry_tags": ["Generalist", "Consumer", "FinTech", "B2B SaaS", "HealthTech"],
+    "geography_focus": ["India"],
+    "notable_portfolio": ["Paytm", "Swiggy", "Meesho"],
+    "website": "https://elevationcapital.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Peak XV Partners",
+    "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"],
+    "industry_tags": ["Generalist", "Consumer", "FinTech", "B2B SaaS", "DevTools", "AI"],
+    "geography_focus": ["India", "South Asia"],
+    "notable_portfolio": ["Zomato", "Pine Labs", "Cred"],
+    "website": "https://www.peakxv.com",
+    "source": "fund website"
+  },
+  {
+    "fund_name": "Nexus Venture Partners",
+    "thesis": "We are a US-India venture capital firm backing extraordinary founders building product-first companies.",
+    "check_size": "$1M - $10M",
+    "stage_focus": ["Seed", "Series A"],
+    "industry_tags": ["B2B SaaS", "Enterprise", "DevTools", "Consumer"],
+    "geography_focus": ["India", "US"],
+    "notable_portfolio": ["Postman", "Hasura", "Zepto"],
+    "website": "https://nexusvp.com",
+    "source": "fund website"
+  }
+]

package/skills/vc-finder/evals/evals.json

@@ -6,7 +6,6 @@
     "input": {
       "prompt": "Find VCs for my startup: https://linear.app",
       "env": {
-        "GEMINI_API_KEY": "set",
         "TAVILY_API_KEY": "set",
         "FIRECRAWL_API_KEY": "set"
       }
@@ -34,7 +33,6 @@
     "input": {
       "prompt": "Find investors for this consumer app: https://www.bereal.com",
       "env": {
-        "GEMINI_API_KEY": "set",
         "TAVILY_API_KEY": "set",
         "FIRECRAWL_API_KEY": "set"
       }
@@ -53,12 +51,11 @@
   },
   {
     "id": "eval_003",
-    "name": "Description-only input: skips fetch, goes direct to Gemini analysis",
-    "description": "User pastes a product description with no URL. Validates that Steps 3 and 4 are skipped and the skill proceeds directly to Gemini analysis.",
+    "name": "Description-only input: skips fetch, goes direct to AI analysis",
+    "description": "User pastes a product description with no URL. Validates that Steps 3 and 4 are skipped and the skill proceeds directly to AI analysis.",
     "input": {
       "prompt": "Find VCs for my startup. Here's what we do: We build an AI-powered legal contract review tool for in-house legal teams at mid-market companies. Our tool flags risky clauses and suggests standard language. We're pre-seed, 3 months post-launch, no pricing page yet. US-focused.",
       "env": {
-        "GEMINI_API_KEY": "set",
         "TAVILY_API_KEY": "set",
         "FIRECRAWL_API_KEY": "not set"
       }
@@ -67,7 +64,7 @@
       "Detects no URL in the input",
       "Skips Step 3: no fetch attempt is made",
       "Skips Step 4: no regex stage detection from page",
-      "Passes the pasted description directly to Gemini in Step 5",
+      "Passes the pasted description directly to the AI in Step 5",
       "Stage set to 'pre-seed' with high confidence (user stated it explicitly)",
       "Industry taxonomy: software > legaltech > contract review automation",
       "Generates 5 comparable legaltech companies",
@@ -79,47 +76,68 @@
   },
   {
     "id": "eval_004",
-    "name": "GEMINI_API_KEY missing: immediate stop at Step 1",
-    "description": "Validates that the skill stops at Step 1 with exact setup instructions when Gemini key is absent.",
+    "name": "TAVILY_API_KEY missing: immediate stop at Step 1",
+    "description": "Validates that the skill stops at Step 1 with exact setup instructions when Tavily key is absent.",
     "input": {
       "prompt": "Find VCs for https://stripe.com",
       "env": {
-        "GEMINI_API_KEY": "not set",
-        "TAVILY_API_KEY": "set",
+        "TAVILY_API_KEY": "not set",
         "FIRECRAWL_API_KEY": "set"
       }
     },
     "expected_behavior": [
-      "Step 1 detects GEMINI_API_KEY is missing",
+      "Step 1 detects TAVILY_API_KEY is missing",
       "Stops immediately at Step 1",
-      "Tells the user: 'GEMINI_API_KEY is required for product analysis and VC synthesis. Get it at aistudio.google.com. Add it to your .env file.'",
+      "Tells the user: 'TAVILY_API_KEY is required to research VC investments and theses. There is no fallback for this. Get it at app.tavily.com. Free tier: 1000 credits/month (about 125 full runs). Add it to your .env file.'",
       "Does NOT fetch the URL",
       "Does NOT run any Tavily searches",
       "Does NOT attempt any analysis"
     ],
     "expected_output": "Immediate stop at Step 1 with exact error message including the URL to get the key. No partial output generated."
   },
+  {
+    "id": "eval_006",
+    "name": "Curated pre-match: DevTools seed product gets High confidence matches from vc_funds.json",
+    "description": "Validates Step 5b -- that the curated scoring algorithm correctly identifies DevTools-focused seed funds (Heavybit, boldstart, Amplify) as High confidence matches for a developer tool at seed stage, and their portfolio companies appear as seed comparables.",
+    "input": {
+      "prompt": "Find VCs for my startup: https://buildkite.com",
+      "env": {
+        "TAVILY_API_KEY": "set",
+        "FIRECRAWL_API_KEY": "set"
+      }
+    },
+    "expected_behavior": [
+      "Step 5b runs after Step 5",
+      "AI maps taxonomy to extracted_tags including 'DevTools' or 'Infrastructure'",
+      "Scoring produces at least 3 High confidence matches",
+      "Heavybit, boldstart, or Amplify Partners appear in high_medium_matches",
+      "curated_comparables includes portfolio companies like PagerDuty, Snyk, Datadog, or Netlify",
+      "Step 6 uses curated portfolio companies as primary comparables (source_type: curated_portfolio)",
+      "Final output includes a 'Curated Matches (Verified)' section",
+      "Curated VCs in output have source 'verified (fund website)' not a Tavily URL",
+      "No curated VC has fund_overview drawn from AI training knowledge -- thesis field used verbatim"
+    ],
+    "expected_output": "Curated Matches section with 3+ High/Medium DevTools funds, portfolio companies used as Track A comparables, merged output with verified and Tavily-sourced funds."
+  },
   {
     "id": "eval_005",
-    "name": "TAVILY_API_KEY missing: immediate stop at Step 1, no fallback",
-    "description": "Validates that the skill stops at Step 1 when Tavily key is absent, with no fallback path suggested.",
+    "name": "Firecrawl missing, Tavily extract fallback works",
+    "description": "Validates that the skill falls through to Tavily extract when Firecrawl is not set, and completes the full run successfully.",
     "input": {
       "prompt": "Who invests in CI/CD automation startups? https://buildkite.com",
       "env": {
-        "GEMINI_API_KEY": "set",
-        "TAVILY_API_KEY": "not set",
-        "FIRECRAWL_API_KEY": "set"
+        "TAVILY_API_KEY": "set",
+        "FIRECRAWL_API_KEY": "not set"
       }
     },
     "expected_behavior": [
-      "Step 1 detects GEMINI_API_KEY is set",
-      "Step 1 detects TAVILY_API_KEY is missing",
-      "Stops immediately at Step 1",
-      "Tells the user: 'TAVILY_API_KEY is required to research VC investments and theses. There is no fallback for this. Get it at app.tavily.com. Free tier: 1000 credits/month (about 125 full runs). Add it to your .env file.'",
-      "Does NOT fetch the URL",
-      "Does NOT run any Gemini analysis",
-      "Does NOT suggest any workaround"
+      "Step 1 logs FIRECRAWL_API_KEY as not set and continues silently",
+      "Step 3 uses Tavily extract endpoint instead of Firecrawl",
+      "Content is fetched successfully (at least 200 chars)",
+      "Stage detection and AI analysis run normally",
+      "Full two-track VC output produced",
+      "No error about missing Firecrawl key in the final output"
     ],
-    "expected_output": "Immediate stop at Step 1 with exact error message. Does not proceed past setup check."
+    "expected_output": "Full VC list produced using Tavily extract fallback. No degraded output quality relative to Firecrawl path."
   }
 ]

package/skills/vc-finder/scripts/match_funds.py

@@ -0,0 +1,144 @@
+"""
+match_funds.py -- standalone scoring script for vc-finder curated pre-match.
+Scores data/vc_funds.json against a product context and outputs ranked matches.
+
+Usage:
+  python3 scripts/match_funds.py \
+      --tags "DevTools,B2B SaaS" \
+      --stage Seed \
+      --geo US \
+      --output /tmp/vc-curated-matches.json
+
+Available tags:
+  DevTools, Infrastructure, Open Source, B2B SaaS, AI, Data, FinTech, HealthTech,
+  Enterprise, Consumer, Marketplaces, E-commerce, Crypto, DeepTech, Cybersecurity, Generalist
+"""
+
+import argparse
+import json
+import os
+import sys
+
+STAGE_ORDER = {"Pre-seed": 0, "Seed": 1, "Series A": 2, "Growth": 3}
+
+
+def score_fund(fund, context):
+    score = 0
+    fund_tags = fund.get("industry_tags", [])
+    extracted_tags = context.get("extracted_tags", ["Generalist"])
+
+    tag_points = 0
+    matched_tags = []
+    for tag in extracted_tags:
+        if tag in fund_tags:
+            tag_points += 5 if tag == "Generalist" else 20
+            matched_tags.append(tag)
+    tag_points = min(tag_points, 60)
+    score += tag_points
+
+    stage_hint = context.get("stage_hint")
+    fund_stages = fund.get("stage_focus", [])
+    if not stage_hint:
+        score += 10
+    elif fund_stages:
+        if stage_hint in fund_stages:
+            score += 20
+        elif stage_hint in STAGE_ORDER:
+            hint_idx = STAGE_ORDER[stage_hint]
+            if any(f in STAGE_ORDER and abs(STAGE_ORDER[f] - hint_idx) == 1 for f in fund_stages):
+                score += 10
+
+    geo_hint = context.get("geography_hint")
+    fund_geo = fund.get("geography_focus", ["Global"])
+    if not geo_hint or geo_hint == "Global":
+        score += 10
+    elif fund_geo == ["India"] and geo_hint == "US":
+        pass
+    elif geo_hint in fund_geo:
+        score += 20
+    elif "Global" in fund_geo:
+        score += 15
+
+    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)
+    if fund_tags and extracted_tags and 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):
+    if score >= 70:
+        return "High"
+    if score >= 40:
+        return "Medium"
+    return "Low"
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--tags", required=True, help="Comma-separated industry tags")
+    parser.add_argument("--stage", default="", help="Pre-seed / Seed / Series A / Growth")
+    parser.add_argument("--geo", default="", help="US / Europe / India / Global")
+    parser.add_argument("--funds", default="data/vc_funds.json")
+    parser.add_argument("--output", default="/tmp/vc-curated-matches.json")
+    args = parser.parse_args()
+
+    context = {
+        "extracted_tags": [t.strip() for t in args.tags.split(",") if t.strip()],
+        "stage_hint": args.stage or None,
+        "geography_hint": args.geo or None,
+    }
+
+    funds_path = args.funds
+    if not os.path.exists(funds_path):
+        print(f"ERROR: {funds_path} not found", file=sys.stderr)
+        sys.exit(1)
+
+    with open(funds_path) as f:
+        funds = json.load(f)
+
+    scored = []
+    for fund in funds:
+        score, matched_tags = score_fund(fund, context)
+        tier = get_confidence_tier(score)
+        scored.append({
+            "fund_name": fund["fund_name"],
+            "thesis": fund["thesis"],
+            "check_size": fund["check_size"],
+            "stage_focus": fund["stage_focus"],
+            "industry_tags": fund["industry_tags"],
+            "geography_focus": fund["geography_focus"],
+            "notable_portfolio": fund["notable_portfolio"],
+            "website": fund["website"],
+            "source": "verified (fund website)",
+            "score": score,
+            "confidence": tier,
+            "matched_tags": matched_tags,
+        })
+
+    scored.sort(key=lambda x: (-x["score"], x["fund_name"]))
+    relevant = [m for m in scored if m["confidence"] in ("High", "Medium")]
+
+    curated_comparables = []
+    for m in relevant:
+        for company in m.get("notable_portfolio", []):
+            if company not in curated_comparables:
+                curated_comparables.append(company)
+
+    output = {
+        "high_medium_matches": relevant,
+        "curated_comparables": curated_comparables[:6],
+    }
+
+    with open(args.output, "w") as f:
+        json.dump(output, f, indent=2)
+
+    print(f"Curated matches: {len(relevant)} High/Medium confidence funds")
+    for m in relevant[:8]:
+        print(f"  {m['confidence']:6} ({m['score']:3}) {m['fund_name']} | {m['matched_tags']}")
+    print(f"Portfolio seed comparables: {curated_comparables[:6]}")
+
+
+if __name__ == "__main__":
+    main()