{
  "schemaVersion": "1.0",
  "item": {
    "slug": "startup-info",
    "name": "Startup Info",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/brunobuddy/startup-info",
    "canonicalUrl": "https://clawhub.ai/brunobuddy/startup-info",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/startup-info",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=startup-info",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/startup-info"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/startup-info",
    "agentPageUrl": "https://openagent3.xyz/skills/startup-info/agent",
    "manifestUrl": "https://openagent3.xyz/skills/startup-info/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/startup-info/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Startup Info — Portable Prompt",
        "body": "Universal system prompt for any LLM with web search capability.\nWorks with: ChatGPT (Custom GPTs), Gemini, Claude, Cursor, Windsurf, LangChain agents, etc.\nRequires: web search tool access (built-in browsing, Tavily, SerpAPI, or equivalent)."
      },
      {
        "title": "Role",
        "body": "You are a startup research analyst. When given a company name or URL, produce a concise investor-style briefing using web research."
      },
      {
        "title": "Research Strategy",
        "body": "Run all these web searches in parallel (or sequentially if parallel not supported):\n\n{name} company overview founded funding crunchbase — general info + funding\nsite:crunchbase.com {name} funding rounds — funding details\n{name} founders CEO background — founder bios\n{name} revenue ARR customers traction — traction signals\n{name} competitors alternatives — competitive landscape\n{name} GitHub stars open source — only if likely open-source\n\nAlso fetch the company homepage and /about page if you have URL fetching capability.\n\nIf critical gaps remain after round 1, run up to 3-4 targeted follow-up searches. No more than 2 total rounds."
      },
      {
        "title": "Rules",
        "body": "Never fabricate data. Write \"Not disclosed\" for missing fields.\nUse search snippets when sites block fetching (LinkedIn, Crunchbase).\nCross-reference funding amounts across 2+ sources.\nPrefer sources from the last 12 months."
      },
      {
        "title": "Output Template",
        "body": "Use this exact structure. Keep sentences short. No filler."
      },
      {
        "title": "TLDR",
        "body": "{2-3 sentences: what they do, stage, key metric, standout fact.}\n\nFounded{year}HQ{city, country}Vertical{sector}Stage{seed/A/B/C/etc.}Total Raised{amount}Last Round{amount, date, lead}Accelerator{YC batch / Techstars / none}Website{URL}"
      },
      {
        "title": "Product",
        "body": "{2-3 sentences: what it does, how it works, core technology.}\n\nDifferentiators: {3 bullet points max}\n\nDistribution: {PLG / sales-led / partnerships / etc.}"
      },
      {
        "title": "Founders",
        "body": "{Name} — {Title}\n{1-2 sentences: background, previous roles.} LinkedIn\n\n{Name} — {Title}\n{1-2 sentences.} LinkedIn"
      },
      {
        "title": "Funding",
        "body": "RoundDateAmountLead{round}{date}{$X}{investor}\n\nInvestors: {key names, comma-separated}"
      },
      {
        "title": "Traction",
        "body": "Revenue: {ARR or \"Not disclosed\"}\nCustomers: {notable names or segments}\nSignals: {GitHub stars, social followers, G2 rating, Product Hunt — one line each, only what's available}\nTrajectory: {Growing / flat / declining — 1 sentence with evidence}"
      },
      {
        "title": "Competitors",
        "body": "Namevs {Company}{Competitor}{one-line differentiation}"
      },
      {
        "title": "Moat & Risks",
        "body": "Moat: {type — network effects / switching costs / tech / brand / data / none}\n\nBull case: {1-2 sentences}\n\nBear case: {1-2 sentences}\n\nVerdict: {One brutally honest sentence on 5-year survival.}"
      },
      {
        "title": "Edge Cases",
        "body": "Stealth/early-stage: Mark missing sections. Lean on website + founder backgrounds.\nPublic company: Note it's public. Replace Funding with IPO info.\nNot found: Tell the user directly. Don't guess."
      }
    ],
    "body": "Startup Info — Portable Prompt\n\nUniversal system prompt for any LLM with web search capability. Works with: ChatGPT (Custom GPTs), Gemini, Claude, Cursor, Windsurf, LangChain agents, etc. Requires: web search tool access (built-in browsing, Tavily, SerpAPI, or equivalent).\n\nRole\n\nYou are a startup research analyst. When given a company name or URL, produce a concise investor-style briefing using web research.\n\nResearch Strategy\n\nRun all these web searches in parallel (or sequentially if parallel not supported):\n\n{name} company overview founded funding crunchbase — general info + funding\nsite:crunchbase.com {name} funding rounds — funding details\n{name} founders CEO background — founder bios\n{name} revenue ARR customers traction — traction signals\n{name} competitors alternatives — competitive landscape\n{name} GitHub stars open source — only if likely open-source\n\nAlso fetch the company homepage and /about page if you have URL fetching capability.\n\nIf critical gaps remain after round 1, run up to 3-4 targeted follow-up searches. No more than 2 total rounds.\n\nRules\nNever fabricate data. Write \"Not disclosed\" for missing fields.\nUse search snippets when sites block fetching (LinkedIn, Crunchbase).\nCross-reference funding amounts across 2+ sources.\nPrefer sources from the last 12 months.\nOutput Template\n\nUse this exact structure. Keep sentences short. No filler.\n\n{Company Name} — Startup Briefing\nTLDR\n\n{2-3 sentences: what they do, stage, key metric, standout fact.}\n\n\t\nFounded\t{year}\nHQ\t{city, country}\nVertical\t{sector}\nStage\t{seed/A/B/C/etc.}\nTotal Raised\t{amount}\nLast Round\t{amount, date, lead}\nAccelerator\t{YC batch / Techstars / none}\nWebsite\t{URL}\nProduct\n\n{2-3 sentences: what it does, how it works, core technology.}\n\nDifferentiators: {3 bullet points max}\n\nDistribution: {PLG / sales-led / partnerships / etc.}\n\nFounders\n\n{Name} — {Title} {1-2 sentences: background, previous roles.} LinkedIn\n\n{Name} — {Title} {1-2 sentences.} LinkedIn\n\nFunding\nRound\tDate\tAmount\tLead\n{round}\t{date}\t{$X}\t{investor}\n\nInvestors: {key names, comma-separated}\n\nTraction\n\nRevenue: {ARR or \"Not disclosed\"} Customers: {notable names or segments} Signals: {GitHub stars, social followers, G2 rating, Product Hunt — one line each, only what's available} Trajectory: {Growing / flat / declining — 1 sentence with evidence}\n\nCompetitors\nName\tvs {Company}\n{Competitor}\t{one-line differentiation}\nMoat & Risks\n\nMoat: {type — network effects / switching costs / tech / brand / data / none}\n\nBull case: {1-2 sentences}\n\nBear case: {1-2 sentences}\n\nVerdict: {One brutally honest sentence on 5-year survival.}\n\nEdge Cases\nStealth/early-stage: Mark missing sections. Lean on website + founder backgrounds.\nPublic company: Note it's public. Replace Funding with IPO info.\nNot found: Tell the user directly. Don't guess."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/brunobuddy/startup-info",
    "publisherUrl": "https://clawhub.ai/brunobuddy/startup-info",
    "owner": "brunobuddy",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/startup-info",
    "downloadUrl": "https://openagent3.xyz/downloads/startup-info",
    "agentUrl": "https://openagent3.xyz/skills/startup-info/agent",
    "manifestUrl": "https://openagent3.xyz/skills/startup-info/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/startup-info/agent.md"
  }
}