Update to Bigdata.com

{
  "name": "bigdata-pre-ipo-analysis",
  "description": "Produce a balanced pre-IPO research note on an upcoming, not-yet-listed company using its S-1/F-1 plus Bigdata.com data. Covers deal structure (price range, shares, greenshoe, implied valuation, underwriters, lock-ups, share classes), two years plus interim financials, business model and funding history, TAM and listed comparables, IPO-window conditions, and 90-day sentiment — closing with bull and bear debates and watch points, never a participate/avoid call. Triggers: \"analyze the IPO of X\", \"S-1 analysis\", \"upcoming listing for X\", \"IPO report on X\", \"should I look at X's IPO\", \"pre-IPO research on X\", \"X IPO valuation\".",
  "included_files": [
    {
      "relative_path": "README.md",
      "size_in_bytes": 1584
    },
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 318
    },
    {
      "relative_path": "assets/bigdata-icon-black.svg",
      "size_in_bytes": 3278
    },
    {
      "relative_path": "assets/report-template.md",
      "size_in_bytes": 5250
    }
  ],
  "skill_md_contents": "---\nname: bigdata-pre-ipo-analysis\ndescription: >\n  Produce a balanced pre-IPO research note on an upcoming, not-yet-listed company using its\n  S-1/F-1 plus Bigdata.com data. Covers deal structure (price range, shares, greenshoe, implied\n  valuation, underwriters, lock-ups, share classes), two years plus interim financials, business\n  model and funding history, TAM and listed comparables, IPO-window conditions, and 90-day\n  sentiment — closing with bull and bear debates and watch points, never a participate/avoid\n  call. Triggers: \"analyze the IPO of X\", \"S-1 analysis\", \"upcoming listing for X\", \"IPO report\n  on X\", \"should I look at X's IPO\", \"pre-IPO research on X\", \"X IPO valuation\".\n---\n\n# Bigdata Pre-IPO Analysis\n\nInstitutional-style research note on an **upcoming** listing. Use Bigdata.com plugin tools plus web search for filings and market data.\n\n**Use this skill when** the company has not yet priced. Not this skill when:\n\n| Request | Use instead |\n|---------|-------------|\n| The company already listed and is trading | Post-IPO day 1 / 14 / 179 / 365 |\n| An established public company's valuation | Valuation snapshot |\n| A recommendation on whether to participate | Nothing — this deliverable is balanced by design |\n\n## Scope rules (non-negotiable)\n\n- **Upcoming IPOs only.** If the company has already listed, say this skill covers pre-listing analysis and offer a post-IPO note instead before proceeding.\n- **Balanced framing only.** Never give a participate/wait/avoid recommendation, price target, or conviction rating. Present bull case, bear case, and watch points; let the reader decide.\n- **No invented data.** If a figure (price range, offer size) is not yet public, write \"not yet disclosed\" rather than estimating. Label every third-party estimate as such.\n\n## Data foundation (plugin tools + web)\n\n| Tool | Purpose | Prerequisite |\n|------|---------|--------------|\n| `bigdata_search` | Company background, IPO window conditions, sentiment | None |\n| `find_securities` | Entity resolution when a tearsheet is needed | None |\n| `bigdata_company_tearsheet` | Financial baseline where the entity is covered | `find_securities` |\n| Web search | S-1/F-1 terms, financials, comparables, recent debuts | None |\n\n**Fallback:** if Bigdata.com tools are unavailable, complete every step with web search alone and note in the footer that sentiment data was limited to public news.\n\n## Workflow\n\n### Step 1 — Clarify the input\n\nCompany name is required. If ambiguous, confirm with the user. Note the expected exchange and geography if known.\n\n### Step 2 — Research (complete BEFORE building the report)\n\nRun searches in this order, one focus and one time period per search. Record source name and date for every material fact as you go.\n\n**a. Filing facts (web).** Latest S-1/F-1/prospectus: price range, shares offered (primary vs secondary), greenshoe, implied valuation, underwriters, expected pricing and listing date, exchange, ticker, use of proceeds, lock-up terms, share-class structure, cornerstone investors.\n\n**b. Financials (web + filing).** Two most recent fiscal years plus the latest interim period: revenue, gross margin, operating income/loss, net income, operating cash flow, FCF, cash and debt.\n\n**c. Company background (`bigdata_search` + web).** Business model, segments, customers, management, funding history and last private-round valuation.\n\n**d. Industry and peers (web).** TAM estimates, competitive set, and 3–6 listed comparables with current EV/Sales, EV/EBITDA, or P/E as applicable.\n\n**e. IPO window (`bigdata_search` + web).** Current IPO market conditions, recent debuts in the same sector, and how they traded in the aftermarket.\n\n**f. Sentiment (Bigdata.com).** News flow and sentiment on the issuer over the last 90 days.\n\n### Step 3 — Build the report\n\nFollow [assets/report-template.md](./assets/report-template.md). Do not start document generation until research is complete.\n\n### Step 4 — Verify before delivering\n\n- Every number traces to a recorded source\n- Internal consistency: implied valuation = price × post-offering shares outstanding\n- All template sections present\n- No recommendation language slipped in (\"we recommend\", \"attractive entry\", \"avoid\")\n\n## Output\n\n- Length: 6–10 pages.\n- Cover: company name, \"Pre-IPO Research Note\", date, \"Prepared with Claude\".\n- Add inline citations `[1]`, `[2]` after every claim from a source, hyperlinked to the document URL. Brand Bigdata.com content exactly \"Bigdata.com\", linked to the `url` from the `bigdata_search` response.\n- Full **Sources** section, then the **Powered by Bigdata.com** line and **Disclaimer**, verbatim.\n- Default format is Markdown; offer PDF, Word (.docx), or presentation output.\n\n## Quality bar\n\nNon-negotiables in every pre-IPO note:\n\n- Deal structure sourced from the filing, not from press summaries\n- \"Not yet disclosed\" used wherever the filing is silent — never an estimate presented as fact\n- Comparables named with their multiples, so the valuation framing is checkable\n- Bull and bear both specific and falsifiable\n- No participate/avoid call, no price target, no conviction rating\n- Facts separated from analysis and implications\n"
}