anthropics / financial-services

Core financial modeling and analysis tools: DCF, comps, LBO, 3-statement models, competitive analysis, and deck QC

Investment banking productivity tools: client and market insights, deck creation, financial analysis, and transaction management

Equity research tools: earnings analysis, initiating coverage reports, and research workflows

Private equity deal sourcing and workflow tools: company discovery, CRM integration, and founder outreach

Fund administration and finance ops skills: GL reconciliation, break tracing, accruals, roll-forwards, variance commentary, NAV tie-out

Operational workflows: KYC document parsing and rules-grid evaluation

Comps, precedents, LBO to a branded pitch deck, end to end

Sector or theme to industry overview, competitive landscape, peer comps, and ideas shortlist

Earnings call and filings to model update to note draft

Briefing pack before every client meeting

DCF, LBO, 3-statement, comps - live in Excel

Finds breaks, traces root cause, routes for sign-off

Parses onboarding docs, runs the rules engine, flags gaps

Ingests GP packages, runs valuation template, stages LP reporting

Accruals, roll-forwards, variance commentary

Audits pre-generated LP statements before distribution

Price bonds, analyze yield curves, evaluate FX carry trades, value options, and build macro dashboards using LSEG financial data and analytics.

S&P Global - Financial data and analytics skills including company tearsheets, earnings previews, and transaction summaries

Provision direct cloud access (Vertex AI, Bedrock, Azure AI Foundry, or LLM gateway) for the Claude Office add-in. Generates the customized add-in manifest, walks through Azure admin consent, and writes per-user config via Microsoft Graph extension attributes.

Check one thing against one connected system on behalf of the compliance skill — who a testimonial's author is to the firm (client status, relationships, conflicts), or whether a specific factual claim holds up against connected portfolio data. Dispatched once per lookup so multiple authors or multiple claims resolve concurrently instead of one after another.

Scan one piece of client-facing content against the Marketing Rule's seven general prohibitions and the specific content rules (performance, testimonials, third-party ratings, promissory language, fiduciary/antifraud, Reg BI), and return the flagged passages with rule, severity, and reasoning. Finds and cites; does not reword, draft disclosures, or redraft.

Run the seven data-sanity checks over one household's holdings and performance data before any drift or tax figure is computed from it — temporal, magnitude, aggregation, reconciliation, completeness, staleness, duplication. Returns a flag list naming which downstream figure each problem contaminates.

Pull one system's data for one already-identified household and return it as a filled field schema. Dispatched once per source by a skill that needs several systems read at once — email, CRM, portfolio platform, planning platform — so the reads happen concurrently instead of one after another.

Read one account statement, export, or screenshot and return its accounts and holdings as a normalized record, with every unreadable field marked rather than guessed and every computed figure marked as inferred. Dispatched once per file by prospect-intake so a pile of statements is read concurrently instead of one after another.

Compare what a household's estate plan intends against how its accounts are actually titled and beneficiaried, row by row, and return a comparison table plus categorized mismatches. Reports unmatched items on both sides rather than dropping them.

Processes an earnings event end to end — reads the call transcript and filings, updates the coverage model, and drafts the post-earnings note. Use when a covered name reports; for a single name interactively, or fanned out across a coverage list as a managed agent.

Reconciles general ledger to subledger across asset classes for a trade date — finds breaks, traces root cause, and routes the exception report for sign-off. Use for daily or month-end recon runs; not for journal-entry posting (use month-end-closer for that).

Parses an onboarding document packet, runs the firm's KYC/AML rules engine, screens against sanctions and PEP lists, and flags gaps for escalation. Use for new-client onboarding or periodic refresh — not for transaction monitoring.

Produces sector or thematic market research — industry overview, competitive landscape, trading-comps spread of the peer set, and a thematic ideas shortlist — packaged as a research note with optional slides. Use when an analyst or PM asks for a primer on a sector or theme; not for single-name coverage updates (use earnings-reviewer for that).

Builds a briefing pack before a client or prospect meeting — relationship history from CRM, holdings and recent activity, market context, and a suggested agenda. Use ahead of any client meeting; pairs with a calendar event.

Builds DCF, LBO, three-statement, and trading-comps models live in Excel from a ticker and assumption set. Use when you need a clean model from scratch — not for updating an existing coverage model (use earnings-reviewer for that).

Runs the month-end close for an entity — accruals, roll-forwards, and variance commentary — and stages the close package for controller sign-off. Use for period-end close; not for daily reconciliation (use gl-reconciler for that).

End-to-end investment banking pitch agent. Given a target company and a strategic situation (e.g., "exploring strategic alternatives"), autonomously pulls comps and precedents from market data, builds a DCF and football-field valuation in Excel, and generates a branded pitch deck on the bank's PowerPoint template.

Audits a batch of pre-generated LP capital-account statements against the fund NAV pack before distribution — ties out balances, allocations, and fees, and flags discrepancies. Use as the final check before statements go out.

Ingests GP valuation packages for a fund, runs them through the valuation template, and stages LP reporting. Use for quarter-end portfolio valuation review — not for deal-time underwriting (use model-builder for that).