Update to Bigdata.com

{
  "name": "bigdata-variant-perception",
  "description": "State explicitly where your view on a public company differs from consensus, using Bigdata.com data. Establishes the consensus baseline from estimates and sell-side posture, applies the EPIC filter to candidate differentiators, frames the view on FaVeS (fundamentals, valuation, sentiment), and states the variant view as a specific, falsifiable claim with a time horizon — plus what the market is missing, why the mispricing persists, the evidence for the view, and what would disprove it. Triggers: \"variant perception on X\", \"where do I differ from consensus on X\", \"what is the market missing on X\", \"non-consensus view on X\", \"what's priced in versus reality for X\", \"contrarian case for X\".",
  "included_files": [
    {
      "relative_path": "README.md",
      "size_in_bytes": 1636
    },
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 349
    },
    {
      "relative_path": "assets/bigdata-icon-black.svg",
      "size_in_bytes": 3278
    },
    {
      "relative_path": "assets/report-template.md",
      "size_in_bytes": 4381
    },
    {
      "relative_path": "references/epic-framework.md",
      "size_in_bytes": 7472
    },
    {
      "relative_path": "references/faves-framework.md",
      "size_in_bytes": 6061
    },
    {
      "relative_path": "references/reverse-dcf.md",
      "size_in_bytes": 7752
    },
    {
      "relative_path": "references/thesis-construction.md",
      "size_in_bytes": 9072
    },
    {
      "relative_path": "scripts/reverse_dcf.py",
      "size_in_bytes": 15034
    }
  ],
  "skill_md_contents": "---\nname: bigdata-variant-perception\ndescription: >\n  State explicitly where your view on a public company differs from consensus, using Bigdata.com\n  data. Establishes the consensus baseline from estimates and sell-side posture, applies the\n  EPIC filter to candidate differentiators, frames the view on FaVeS (fundamentals, valuation,\n  sentiment), and states the variant view as a specific, falsifiable claim with a time horizon —\n  plus what the market is missing, why the mispricing persists, the evidence for the view, and\n  what would disprove it. Triggers: \"variant perception on X\", \"where do I differ from\n  consensus on X\", \"what is the market missing on X\", \"non-consensus view on X\",\n  \"what's priced in versus reality for X\", \"contrarian case for X\".\n---\n\n# Bigdata Variant Perception\n\nThe discipline of saying exactly where you differ from consensus — and how you'd know you were wrong. Use Bigdata.com plugin tools for every fact.\n\n**Use this skill when** the consensus gap *is* the deliverable. Not this skill when:\n\n| Request | Use instead |\n|---------|-------------|\n| Full thesis with recommendation and conviction | Investment memo |\n| Absolute valuation | Valuation snapshot |\n| Outcomes weighted by probability | Scenario analysis |\n| A fast view with no consensus framing | Quick take |\n\n**A variant perception is not a bull case.** Agreeing with consensus more enthusiastically is not a variant view. If you cannot name a specific number, timing, or outcome where you differ, the honest answer is that you have no variant perception on this name — say so.\n\n## Data foundation (plugin tools)\n\n| Tool | Purpose | Prerequisite |\n|------|---------|--------------|\n| `find_securities` | Resolve company name → RavenPack `entity_id` | None |\n| `bigdata_company_tearsheet` | Consensus estimates, multiples, sentiment, positioning | `find_securities` |\n| `bigdata_search` | Sell-side posture, the live debate, evidence for and against | None |\n\nIf the company name is ambiguous after `find_securities`, ask:\n\n> \"I found multiple companies named [X]. Did you mean [Company A] in [Industry] or [Company B] in [Industry]?\"\n\n## Workflow\n\n### Step 1 — Establish the consensus baseline\n\nYou cannot differ from a consensus you have not written down. From the tearsheet and search, capture:\n\n- Consensus revenue, EPS, and margin estimates for the next 1–2 years\n- Mean price target and the high/low range\n- Rating distribution and recent revision direction\n- What the current multiple implies (reverse-DCF reasoning — [references/reverse-dcf.md](./references/reverse-dcf.md))\n\nSearch: \"[Company] analyst estimates consensus outlook\", \"[Company] price target upgrades downgrades\".\n\n### Step 2 — Apply the EPIC filter\n\nFor each candidate differentiator, run all four tests:\n\n| Test | Question | Pass criteria |\n|------|----------|---------------|\n| **E**ffect | Is it material? | ~10% change moves intrinsic value meaningfully |\n| **P**redictability | Can you forecast it? | You have an analytical or informational edge, not a guess |\n| **I**ndependence | Does consensus get it wrong? | The market systematically misjudges this |\n| **C**onsensus gap | Is there a gap? | Your forecast differs meaningfully and specifically |\n\nOnly factors passing all four qualify. Detail: [references/epic-framework.md](./references/epic-framework.md).\n\n### Step 3 — Frame on FaVeS\n\n- **Fundamentals** — which 2–3 KPIs drive value, and where your forecast differs from the consensus line item\n- **Valuation** — what multiple the quality and growth justify, versus what is being applied\n- **Sentiment** — what is priced in behaviorally: positioning, flows, short interest, sell-side posture\n\nDetail: [references/faves-framework.md](./references/faves-framework.md).\n\n### Step 4 — State the variant view\n\nWrite it as a **specific, falsifiable claim with a time horizon**:\n\n> \"Consensus models [X]% [metric] in [period]; we expect [Y]% because [mechanism], which would imply [$Z] of [revenue/EBIT/value] versus the [$W] embedded in the current price.\"\n\nVague directional statements (\"we're more optimistic than the street\") fail this deliverable.\n\n### Step 5 — Why the mispricing persists\n\nA gap that anyone could see would already be closed. Name the structural reason it survives: disclosure gaps, time-horizon mismatch, index or mandate constraints, coverage gaps, complexity, recency bias after a shock, or a segment that reporting obscures. Methodology: [references/thesis-construction.md](./references/thesis-construction.md).\n\n### Step 6 — Evidence and disconfirmation\n\n- **Evidence for:** the specific data points, each cited\n- **What would disprove it:** observable, dated, and specific — if nothing could disprove the view, it is not a research claim\n- **Time horizon:** when the gap should close, and what closes it\n\nRun [scripts/reverse_dcf.py](./scripts/reverse_dcf.py) only if the user explicitly wants scripted implied-growth math.\n\n## Output\n\nFollow [assets/report-template.md](./assets/report-template.md) exactly — section order, tables, sources, and footer.\n\n- Add inline citations `[1]`, `[2]` immediately after claims, hyperlinked to the document URL.\n- Every deliverable ends with the **Powered by Bigdata.com** line and the **Disclaimer**, verbatim.\n- Default format is Markdown; offer a Word (.docx) version if useful.\n\n## Quality bar\n\nNon-negotiables:\n\n- Consensus baseline **written down** with numbers before any differing view is stated\n- EPIC run on each candidate; only all-four passes qualify\n- The variant view is specific, quantified, and carries a time horizon\n- A structural reason the mispricing persists — otherwise the gap probably isn't real\n- Disconfirming evidence named and observable\n- Honesty about the null result: if nothing passes EPIC, say there is no variant perception here\n"
}