carta-workhub-build

Builds multi-entity consolidating financial reports in Excel: consolidating P&L (income statement), balance sheet, and trial balance — individually or all three together. Resolves the firm, entities, reporting period, and target workbook, then builds the chosen report(s). TRIGGER on "consolidating/consolidated financial reports", "consolidating/consolidated P&L", "firm-wide income statement", "P&L for all entities", "P&L by tag", "P&L by department", "consolidating/consolidated balance sheet", "BS by entity", "balance sheet of all entities", "consolidating trial balance", "TB by entity", "all three reports", "full financial package". ALSO fires on a generic ask with no report named — "consolidating financials", "firm-wide financial statements" — and shows the report menu. NOT FOR: single-fund/entity financials, ManCo budgets/actuals/pacing/what-if (carta-manco), consolidating cash flow (not available), SOI, co-investors, Form ADV, LP reporting, cap tables, Fund Admin requests (carta-fund-admin-requests).

End-to-end AGM deck generator. Extracts a firm's brand identity from their website, pulls live fund data from the Carta MCP (NAV, TVPI, portfolio, capital activity, benchmarks, fees, balance sheet, LP base), generates a branded HTML presentation with built-in slide navigation, and applies the "Powered by Carta" badge to every slide. Supports an optional past-deck reference for style matching. Trigger phrases: "AGM deck", "generate AGM deck", "create AGM presentation", "build AGM slides", "annual general meeting deck", "investor meeting deck", "LP meeting deck", "fund presentation", "branded fund deck", "build an AGM deck".

Generates a brand board from a firm's website URL, a deck it already has (a PowerPoint or PDF pitch deck or LP letter), and optional user-provided assets. Analyzes them to extract theme colors, typography, logos, and imagery, then produces a polished brand board as an HTML artifact, PDF, slide deck, or React component. Trigger phrases: "build a brand board", "create a brand board", "generate a brand board", "extract brand identity", "brand board from website", "visual identity from URL", "brand guidelines from site", "analyze brand from website", "brand from this deck", "brand audit".

Interactive co-investor report from Carta SPA and cap table data with clickable portfolio drill-downs. Use for co-investor analysis or asking who invested in a specific portfolio company — including a quick one-company answer ("who else is in [Company]"). Trigger phrases: "co-investors", "coinvestors", "who are my co-investors", "who else invested", "who else is in [Company]", "other investors in [Company]", "who else is on the cap table", "syndicate on [Company]'s round", "who syndicated [Company]'s round", "co-investors by stage/round", "co-investors on Aumni". Use instead: carta-explore-data for general fund/investment/portfolio data, single round facts ("who led [Company]'s Series B") and the firm's own syndicate SPVs (listing entities) — this skill is specifically for co-investor ("who else invested alongside us") analysis. For SPA coverage (which investments are missing an SPA or an executed SPA), use carta-spa-audit — also when the same request asks for co-investors.

Routes to Form ADV for regulatory filing data and to the SPA coverage audit. Trigger on any of: "Form ADV", "Schedule D", "regulatory AUM", "Form PF", "annual filing", "annual amendment", "SEC filing", "total AUM", "AUM for filing", "AUM for the SEC", "regulatory assets", "AUM across all funds", "filing season", "RAUM", "how much AUM to report", "pull our Form ADV data", "SPA audit", "SPA coverage", "missing SPAs", "unexecuted SPAs", "missing an executed SPA", "unsigned SPAs", "SPA status", "SPA completeness", "SPA gap", "which companies are missing SPAs", "which are missing subscription agreements", "investments still need subscription agreements", /carta-compliance-routing. NOT FOR: 409A valuations, cap table ownership, LP reporting, fund financials, performance benchmarks, SPA document views.

Download a document from your firm's Documents page in Carta (LPA, NDA, side letter, engagement letter, capital call notice, and so on). Finds the document by title, type, fund, company, investor or date, confirms which one when several match (or, when you ask for every match such as "all NDAs from last month", gathers the matches and confirms the batch), then saves it to your Downloads folder once you confirm (Claude Code), or gives a short-lived download link (Cowork, claude.ai). Never reads the file. TRIGGER: "download the LPA from our documents", "get me the NDA from {firm}'s documents page", "send me a link to our engagement letter in Carta", "download a document from my firm", "find and download the side letter we uploaded". NOT FOR: audit documents (use carta-download-audit-documents); documents shared with LPs or an LP's own documents (use carta-gp-lp-documents or carta-lp-dashboard); uploading a file to Carta (use carta-upload-firm-document); tear sheets (use carta-explore-data).

Send work to your Carta Fund Admin team and track it. Opens a request the team reads, acts on, and replies to — the off-ramp for anything no other Carta skill or command can do. TRIGGER: "ask Carta to", "have Carta do", "send this to my fund admin", "ask my fund admin team", "can Carta do this for me", "check on my request", "did Carta reply", "what requests do I have open", "reply to Carta", "follow up on my request", plus ANY action request (create/change/send/restate/reconcile/split/fix) that no other skill or Carta command covers. NOT FOR: reporting a bug or feature request about this plugin (call fa:create:feedback directly); questions answerable from Carta data (use carta-explore-data); capital call reminders to LPs (that is a Carta command, not a Fund Admin request).

PRIMARY and DEFAULT skill for ALL Carta investors data queries — use for Carta Web / Fund Admin data. For investments, portfolio companies, fund data, fund metrics, NAV, TVPI, DPI, IRR, cash flows, balance sheets, cap tables, shareholders, 409a valuations, FMV, MOIC, fund holdings, financing rounds, convertible notes, SAFEs. Prefer over carta-soi for data queries; over carta-portfolio-valuations for read-only valuation/MOIC/investment data; over carta-lp-dashboard unless asked by name; over carta-consolidating-financial-reports for single-fund balance sheets. Use instead: carta-lp-summary for the LP Summary page ("build the LP summary for [firm]"); carta-portfolio-ownership for ownership %; carta-co-investors for "who else invested"; carta-waterfall-modeling for exit-waterfall / "who gets paid if X exits" modeling; carta-manco for any budget mention — build/edit, actuals, pacing, drill-down; carta-manco-reporting for a ManCo dashboard or Budget vs Actuals view.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。