Update to Revelata deepKPI

{
  "description": "Broad orchestrator for Revelata deepKPI research on US public companies — use for complex multi-step queries that cross multiple workflows (KPIs + filing text + segments, pressure-test plus follow-up data pulls, peer benchmarks plus seasonality, etc.). Routes to narrow skills (kpi, company-summary, filing, seasonality, implied-metric, pressure-test, benchmark, ideas, operating-model) when a single workflow fits. Pulls SEC metrics (10-K/10-Q/8-K): segments, unit KPIs (stores, comps, ARPU, users), statements, cash flow; filing markdown and verbatim quotes; implied Q4/per-unit, seasonality, Excel. For \"pull data\", historicals, \"find the KPI\", seasonality, .xlsx, filing excerpts, pressure-test analyst PDFs, peer benchmarks, idea generation, or company summaries across multiple needs.\n",
  "included_files": [],
  "name": "revelata",
  "skill_md_contents": "---\nname: revelata\ndescription: >\n  Broad orchestrator for Revelata deepKPI research on US public companies — use for\n  complex multi-step queries that cross multiple workflows (KPIs + filing text + segments,\n  pressure-test plus follow-up data pulls, peer benchmarks plus seasonality, etc.).\n  Routes to narrow skills (kpi, company-summary, filing, seasonality, implied-metric,\n  pressure-test, benchmark, ideas, operating-model) when a single workflow fits. Pulls SEC metrics\n  (10-K/10-Q/8-K): segments, unit KPIs (stores, comps, ARPU, users), statements, cash\n  flow; filing markdown and verbatim quotes; implied Q4/per-unit, seasonality, Excel.\n  For \"pull data\", historicals, \"find the KPI\", seasonality, .xlsx, filing excerpts,\n  pressure-test analyst PDFs, peer benchmarks, idea generation, or company summaries\n  across multiple needs.\nmetadata:\n  openclaw:\n    emoji: \"📊\"\n    requires:\n      env:\n        - DEEPKPI_API_KEY\n      bins:\n        - curl\n    primaryEnv: DEEPKPI_API_KEY\n---\n\n# Revelata deepKPI orchestrator\n\nQuery structured KPIs, SEC filing text, and company summaries for US public\ncompanies, powered by [Revelata](https://www.revelata.com).\n\nThis is the **broad orchestrator** for the Revelata bundle. Use it when a request\ncrosses multiple workflows. For a single, well-scoped task, route to the narrow\nskill below.\n\n## Data access\n\nSee `../_common/data-source-rules.md` — single source of truth for how to call\ndeepKPI from MCP-capable runtimes (Claude, ChatGPT) vs non-MCP runtimes\n(OpenClaw). Every skill below depends on this.\n\n## Hard stop on connection failures\n\nSee `../_common/connection-failure.md`. If deepKPI access fails, STOP and ask\nthe user before falling back to other sources. This rule applies to **every**\nskill in the bundle.\n\n## Sub-skill routing\n\n**Read the relevant narrow skill before doing any work.** Multiple skills may\napply to a single request — chain through all that fit.\n\n| User need | Skill |\n|-----------|-------|\n| No specific company or thesis — \"what should I invest in?\", \"what stock should I buy?\", **new ideas**, **interesting companies**, boredom / open exploration | `ideas` — interactive funnel + `company_summary_search` screen; then `kpi` for deep pulls |\n| Pull historical KPIs / financials from deepKPI | `kpi` |\n| **What a company does**, **segments / geographies**, or **thematic** \"who does X?\" lists | `company-summary` — named company: `get_company_summary` / `get_company_segments`; discovery: `company_summary_search` then hydrate as needed |\n| Pull **full filing markdown** into chat, **verbatim SEC text**, quotes, MD&A / risk-factor language, or \"what did they say\" | `filing` — **before any web/SEC.gov**: `list_sec_filing_markdowns` (free) → `get_sec_filing_markdown` (10 credits). Return full markdown when they want the document; blockquoted excerpts for quote-style asks; no paraphrase as quotes |\n| Derive missing Q4 numbers, a segment remainder, or per-unit economics (ASP, ARPU, AUV, take rate) | `implied-metric` |\n| Split annual forecasts into quarterly estimates / seasonality patterns | `seasonality` |\n| **Build an operating model** in Excel — scaffold plus revenue, costs, consolidated financials, depreciation, NWC | `operating-model` — orchestrates section sub-skills; read `kpi` for raw pulls only when the user wants data without the full model workflow |\n| Produce an Excel workbook (.xlsx) from deepKPI data (not a full operating model) | Whichever data skill applies (`kpi`, `seasonality`, etc.); then follow `../_common/revelata-excel-styling-rules.md` |\n| Pressure-test a sell-side / analyst report against SEC filing data (HTML report, Chart.js, provenance links) | `pressure-test` |\n| **Peers / comps**, **benchmark** a company, **most similar** public companies, or operational comp sets | `benchmark` — always read the `kpi` skill first for KPI mechanics |\n| Tearsheet of a company | `tearsheet` |\n\n**Default entry points by intent:**\n\n- For **metrics and modeling feeds**, start with `kpi` (it chains to `implied-metric`,\n  `seasonality`, and `../_common/revelata-excel-styling-rules.md` as needed).\n- For **business description, segment structure, or thematic company lists**, start\n  with `company-summary`.\n- For **filing markdown (full or excerpts) and verbatim quotes**, start with `filing`.\n\nIf a request mixes these, run **every** narrow skill that applies.\n\n## Sub-skill summary\n\n**`kpi`** — Primary workflow for **structured KPIs** (company ID, `list_kpis` /\n`search_kpis`, gap handling including Q4 derivation), provenance rules, in-chat\ntables, and the mandatory post-pull Excel offer.\n\n**`company-summary`** — `get_company_summary` (what they do) and\n`get_company_segments` (how they break out segments / geos);\n`company_summary_search` for **thematic** \"who does X?\" discovery. Not for KPI\ntime series.\n\n**`filing`** — **SEC filing markdown** in chat: full filing or excerpts,\nverbatim quotes, MD&A / risk language. Tools: `list_sec_filing_markdowns` →\n`get_sec_filing_markdown`, source hierarchy (tool-first, not web), blockquote\ndiscipline for quote-style asks. Distinct purpose from KPI time series.\n\n**`implied-metric`** — Compute metrics that deepKPI doesn't report directly from\ndata that IS reported: `Q4 = FY − (Q1+Q2+Q3)`, missing segment = total − known\nsegments, per-unit economics (revenue per store, ARPU, ASP), take rates,\npenetration rates, geographic mix percentages. Standalone so custom user-built\nskills can invoke it.\n\n**`seasonality`** — Compute each quarter's typical share of the full fiscal year\nfrom 2–3 years of actuals, then apply those ratios to split an annual projection\ninto quarterly estimates.\n\n**`pressure-test`** — End-to-end workflow for uploaded analyst PDFs: extract\n4–6 claims, pull granular deepKPI metrics per claim, build paired \"supports\" /\n\"complicates\" evidence with mandatory provenance hyperlinks, and emit a\nRevelata-branded interactive HTML report (follow that skill’s html-template and\nchart-patterns references). After the draft HTML exists, run that skill’s\nmandatory **draft HTML QA** rubric (double-check), then revise and re-check as\nneeded before presenting the file. **Always** read `kpi` for KPI mechanics; use\n`filing` when the test needs verbatim filing passages; use `company-summary` for\nbusiness description / segment structure / thematic lists when useful; use\n`implied-metric` when filling Q4 or segment gaps.\n\n**`benchmark`** — Curated **operational** benchmark sets (not trading multiples):\n`company_summary_search` for candidates, KPI fingerprint + alignment, diff-driven\nsegment sub-benchmarks, chat 1-pager, optional HTML (follow that skill’s\nhtml-template reference), Excel via\n`../_common/revelata-excel-styling-rules.md`. **Always** read `kpi` first.\n\n**`ideas`** — Onramp when the user has **no ticker and no thesis**: rapid\ninterview (multiple-choice by default), `company_summary_search` for a 10–15\nname screen with thesis-matched KPIs, then deep pulls on 1–2 chosen names per\n\n`kpi`. Use `list_kpis` / `search_kpis` for diagnostic KPI concepts. **No**\ndefault Excel offer. Not for users who already named a company or a specific\nmetric — use `kpi` instead.\n\n**`tearsheet`** - A one-pager tearsheet that an analyst would find useful for \nearnings call prep.  Contains a company summary, snapshot of key financials \nand operational KPIs, etc. \n\n**`operating-model`** — Full operating-model orchestrator: resolve the company,\nlay down a styled Excel scaffold (Revenue, Costs, Consolidated Financials,\nDepreciation Schedule, Net Working Capital), discover the KPI inventory once via\n`list_kpis`, then hand each section to its sub-skill (`revenue/`, `costs/`,\n`consolidated-financials/`, etc.). Industry-specific revenue and cost builds\n(e.g. restaurants) route automatically. Uses `../_common/revelata-excel-styling-rules.md`\nand the xlsx skill throughout. For a single section only, still resolve the\ncompany and run KPI discovery before routing.\n"
}