Research: Claude skills backed by calculation code
Valuation ratios from supplied fundamentals, DCF valuation with sensitivity, keyword risk-factor summaries of filing text, XBRL fact extraction, and live FRED and SEC EDGAR fetches, plus guidance for earnings and market research that the engines do not perform.
What wealth-research calculates
2 commands, each available in the CLI, as an MCP tool and as a JavaScript import. Every result carries the method it used, the questions it still needs answered and the next steps worth taking.
| Command | What it returns | What it needs |
|---|---|---|
research tear-sheet | Valuation ratios from fundamentals you supply. | financials |
research dcf | Discounted cash flow valuation with a terminal value and a sensitivity grid. | cashFlows, discountRate |
When to use it
- Build a company tear sheet or valuation summary.
- Summarize risk factors in a 10-K or 10-Q.
- Look up the latest value of a FRED series or a company's EDGAR facts.
- Summarize earnings announcements or macro trends.
Requests this pack answers:
- “build a tear sheet”
- “what is this trading at”
- “what is this business worth”
- “build a DCF”
What it does not do
Named here because leaving it out is how an agent ends up asserting something the code never computed.
Guidance only, no engine behind it
- Earnings call and press release summaries
- Market news synthesis and sector outlooks
- Time-series analysis beyond the latest observation (trends, yield-curve spreads, CPI decomposition)
Limits to state with every result
- Ratios are only as current and accurate as the fundamentals supplied.
- The filing summary matches a short keyword list; it is not a reading of the filing.
- Live fetches that fail return
nullvalues with an explanation. Report the data as unavailable; never estimate it. - SEC EDGAR requires
SEC_EDGAR_USER_AGENT(or auserAgentoption) naming your organization and a contact email.
Run it
node bin/wealth-skills.js research tear-sheet --ticker AAPL --financials '{"marketCap":3.25e12,"price":215,"eps":7.3,"revenue":3.8e11,"netIncome":1e11,"freeCashFlow":1.08e11,"dividends":1.18}'The same commands are exposed as MCP tools, so Claude, Claude Code, Codex, Cursor and any other MCP client can call them directly. See the integration guide and the pack itself, skills/wealth-research/SKILL.md.
Catalog coverage
105 resources from the US Wealth Management Capability Catalog map to this pack, 13 of them backed by engine code and the rest cited as guidance or reference.
| Resource | What the pack does with it | Coverage |
|---|---|---|
| FASB US GAAP taxonomy | US financial-reporting taxonomy Reads US GAAP concept values from companyfacts. | partial-engine |
| SEC standard taxonomies | Supported reporting and disclosure taxonomies SEC taxonomy facts through the companyfacts API. | partial-engine |
| FactSet Workstation | Securities research and financial analytics Valuation ratios from supplied fundamentals. | partial-engine |
| AlphaSense | Search and synthesis across investment documents Keyword summary of supplied filing text; no document search. | partial-engine |
| Alpha Vantage | Time series and financial data Latest FRED observation only; no full time series. | partial-engine |
| Financial Modeling Prep | Financial statements and market-data endpoints XBRL facts from SEC companyfacts; no market data endpoints. | partial-engine |
| Financial Datasets API | Financial fundamentals and market data Valuation ratios from supplied fundamentals. | partial-engine |
| Intrinio | Financial statements and securities data SEC XBRL facts and identifier checks; no securities master. | partial-engine |
| FRED API | Macroeconomic time series Latest observation of a FRED macro series. | partial-engine |
| SEC EDGAR APIs | Issuer submissions and structured company facts Live company facts and XBRL value extraction; the submissions API is not used. | partial-engine |
| Anthropic Market Researcher | Sector and peer research Ratios and DCF from supplied data; no peer data. | partial-engine |
| Anthropic Earnings Reviewer | Earnings and model-update drafts Reported XBRL figures and ratios; no model updates. | partial-engine |
| Anthropic Model Builder | Financial model preparation DCF valuation with sensitivities; no three-statement model. | partial-engine |
| Morningstar Direct | Fund research and investment analysis No fund research database. | guidance |
| Bloomberg Terminal | Market data and investment research No market data terminal. | guidance |
| LSEG Workspace | Market intelligence and research desktop No research desktop. | guidance |
| Koyfin | Market dashboards and investment research No market dashboards. | guidance |
| Alpaca Market Data API | Market prices and historical data No price feed. | guidance |
| Databento | Historical and live market-data delivery No market data delivery. | guidance |
| Nasdaq Data Link | Financial and alternative datasets No alternative datasets. | guidance |
| Tiingo | Price and financial data APIs No price or financial data API. | guidance |
| Financial Industry Business Ontology | Financial business concepts and semantic relationships Ontology; not implemented. | standard-reference |
| XBRL 2.1 specification | Business reporting representation Reads SEC JSON derived from XBRL, not XBRL instance documents. | standard-reference |
| Inline XBRL 1.1 specification | Structured financial data embedded in HTML Reads SEC JSON derived from XBRL, not XBRL instance documents. | standard-reference |
| EDGAR Filer Manual | EDGAR submission and validation requirements No EDGAR submission. | standard-reference |
| FinanceHub | Quantitative finance research utilities Quantitative research utilities. | integration-reference |
| FinGPT | Financial language-model research Financial AI and agent research code. | integration-reference |
| FinRobot | Financial-analysis agent workflows Financial AI and agent research code. | integration-reference |
| FinRL | Reinforcement-learning trading experiments Financial AI and agent research code. | integration-reference |
| FinRL-Meta | Financial RL environments and data workflows Financial AI and agent research code. | integration-reference |
| TradingAgents | Multi-agent investment-analysis research Financial AI and agent research code. | integration-reference |
| Microsoft Qlib | Quantitative investment research platform Financial AI and agent research code. | integration-reference |
| Microsoft RD-Agent | Automated research and model-development experiments Financial AI and agent research code. | integration-reference |
| FinMem | Memory-based financial-agent experiments Financial AI and agent research code. | integration-reference |
| FinCon | Financial multi-agent decision-making experiments Financial AI and agent research code. | integration-reference |
| Anthropic financial-services | Financial reference agents, skills and connectors Reference financial agents and skills compared in the capability audit. | integration-reference |
| FinBERT | Financial text sentiment classification Financial NLP model or evaluation benchmark. | integration-reference |
| FinQA | Financial numerical-reasoning benchmark Financial NLP model or evaluation benchmark. | integration-reference |
| ConvFinQA | Conversational financial numerical reasoning Financial NLP model or evaluation benchmark. | integration-reference |
| TAT-QA | Financial table-and-text reasoning benchmark Financial NLP model or evaluation benchmark. | integration-reference |
| FinanceBench | Financial-document question-answering evaluation Financial NLP model or evaluation benchmark. | integration-reference |
| FinNLP | Financial NLP data and workflow utilities Financial NLP model or evaluation benchmark. | integration-reference |
| PIXIU | Financial language-model tasks and benchmarks Financial NLP model or evaluation benchmark. | integration-reference |
| FinBen | Financial LLM benchmark suite Financial NLP model or evaluation benchmark. | integration-reference |
| quantmod | R financial data modeling and charting Financial data or econometrics for research. | integration-reference |
| TTR | R technical trading indicators Financial data or econometrics for research. | integration-reference |
| linearmodels | Panel and asset-pricing econometrics Financial data or econometrics for research. | integration-reference |
| statsmodels | Statistical estimation for financial research Financial data or econometrics for research. | integration-reference |
| Databento Python | Python market-data client Market or financial data client. | integration-reference |
| yfinance | Unofficial Yahoo Finance data access Unofficial price data; unsuitable for client reporting. | integration-reference |
| pandas-datareader | Dataset retrieval into pandas Market or financial data client. | integration-reference |
| fredapi | FRED data access FRED client with full series access. | integration-reference |
| Nasdaq Data Link Python | Nasdaq Data Link client Market or financial data client. | integration-reference |
| OpenBB | Financial-data integration and analytics platform Market or financial data client. | integration-reference |
| FinanceToolkit | Financial ratios and analytics Financial ratio library. | integration-reference |
| edgartools | SEC filings retrieval and analysis SEC filing retrieval or XBRL processing. | integration-reference |
| sec-edgar-downloader | Download SEC filing documents SEC filing retrieval or XBRL processing. | integration-reference |
| sec-parser | SEC-document structure extraction SEC filing retrieval or XBRL processing. | integration-reference |
| sec-cik-mapper | Issuer identifier mapping SEC filing retrieval or XBRL processing. | integration-reference |
| Arelle | XBRL validation and processing SEC filing retrieval or XBRL processing. | integration-reference |
| py-xbrl | XBRL and inline-XBRL parsing SEC filing retrieval or XBRL processing. | integration-reference |
| python-xbrl | XBRL parsing utilities SEC filing retrieval or XBRL processing. | integration-reference |
| OpenEDGAR | EDGAR extraction and analysis framework SEC filing retrieval or XBRL processing. | integration-reference |
| secfsdstools | SEC financial-statement dataset processing SEC filing retrieval or XBRL processing. | integration-reference |
| FINOS Legend Engine | Model-driven data service execution Data modelling or streaming analytics. | integration-reference |
| FINOS Legend Studio | Collaborative financial-data modeling interface Data modelling or streaming analytics. | integration-reference |
| FINOS Perspective | Interactive streaming-data analytics Data modelling or streaming analytics. | integration-reference |
| Mutual Fund Flows and Performance in Rational Markets (Berk and Green, 2004) | Skill, fund flows and capacity Evidence on fund manager skill. | research-reference |
| Measuring Skill in the Mutual Fund Industry (Berk and van Binsbergen, 2015) | Manager value added and skill measurement Evidence on fund manager skill. | research-reference |
| Empirical Asset Pricing via Machine Learning (Gu et al., 2020) | Machine learning for expected-return estimation Machine learning in asset pricing and management. | research-reference |
| Deep Learning in Asset Pricing (Chen et al.) | Neural asset-pricing models Machine learning in asset pricing and management. | research-reference |
| Deep Hedging (Buehler et al.) | Learn hedging with frictions and constraints Machine learning in asset pricing and management. | research-reference |
| A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem | Portfolio policy learning Machine learning in asset pricing and management. | research-reference |
| The Role of Deep Learning in Financial Asset Management: A Systematic Review | Survey financial deep-learning applications Machine learning in asset pricing and management. | research-reference |
| BloombergGPT: A Large Language Model for Finance | Financial-domain language-model training Financial language models, agents and benchmarks. | research-reference |
| FinGPT: Open-Source Financial Large Language Models | Open financial language-model methods Financial language models, agents and benchmarks. | research-reference |
| FinBERT: Financial Sentiment Analysis with Pre-trained Language Models | Financial sentiment modeling Financial language models, agents and benchmarks. | research-reference |
| FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models | Financial-analysis agent architecture Financial language models, agents and benchmarks. | research-reference |
| FinRobot: AI Agent for Equity Research and Valuation with Large Language Models | Equity research and valuation workflows Financial language models, agents and benchmarks. | research-reference |
| TradingAgents: Multi-Agents LLM Financial Trading Framework | Role-based financial-agent research Financial language models, agents and benchmarks. | research-reference |
| FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design | Memory structures for trading agents Financial language models, agents and benchmarks. | research-reference |
| FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making | Agent coordination and feedback Financial language models, agents and benchmarks. | research-reference |
| FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance | RL trading framework and environments Financial language models, agents and benchmarks. | research-reference |
| Qlib: An AI-oriented Quantitative Investment Platform | End-to-end quantitative research tooling Financial language models, agents and benchmarks. | research-reference |
| FinQA: A Dataset of Numerical Reasoning over Financial Data | Numerical reasoning over financial reports Financial language models, agents and benchmarks. | research-reference |
| ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering | Multi-turn financial calculation evaluation Financial language models, agents and benchmarks. | research-reference |
| TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance | Reasoning over tables and narrative Financial language models, agents and benchmarks. | research-reference |
| FinanceBench: A New Benchmark for Financial Question Answering | Evaluate financial-document answering Financial language models, agents and benchmarks. | research-reference |
| PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance | Financial instruction data and evaluation Financial language models, agents and benchmarks. | research-reference |
| FinBen: A Holistic Financial Benchmark for Large Language Models | Broad financial-task evaluation Financial language models, agents and benchmarks. | research-reference |
| FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios | Specialized agents for financial reports Financial language models, agents and benchmarks. | research-reference |
| R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization | Automated factor and model research Financial language models, agents and benchmarks. | research-reference |
| FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative Finance | RL environment and benchmark construction Financial language models, agents and benchmarks. | research-reference |
| Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models | Test headline sentiment and return prediction Financial language models, agents and benchmarks. | research-reference |
| ReAct: Synergizing Reasoning and Acting in Language Models | Interleave reasoning and tool calls Agent design and evaluation research. | research-reference |
| Toolformer: Language Models Can Teach Themselves to Use Tools | Learn tool-use behavior Agent design and evaluation research. | research-reference |
| Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | Ground generation in retrieved sources Agent design and evaluation research. | research-reference |
| AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation | Multi-agent conversation orchestration Agent design and evaluation research. | research-reference |
| Reflexion: Language Agents with Verbal Reinforcement Learning | Feedback-based agent improvement Agent design and evaluation research. | research-reference |
| Self-Refine: Iterative Refinement with Self-Feedback | Iterative output refinement Agent design and evaluation research. | research-reference |
| Lost in the Middle: How Language Models Use Long Contexts | Test sensitivity to evidence position Agent design and evaluation research. | research-reference |
| AgentBench: Evaluating LLMs as Agents | Agent capability evaluation Agent design and evaluation research. | research-reference |
| GAIA: A Benchmark for General AI Assistants | Multi-step assistant evaluation Agent design and evaluation research. | research-reference |
| Large Language Models Cannot Self-Correct Reasoning Yet | Limits of unsupported self-correction Agent design and evaluation research. | research-reference |
| 2026 Investment Company Fact Book (ICI) | US fund industry structure and investor data US fund industry data. | research-reference |
Questions it answers
Build a tear sheet?
Valuation ratios from fundamentals you supply. Run research tear-sheet in the CLI, or call the same tool over MCP. It needs financials. Every ratio comes from these; the library fetches no market data. The result carries the method it used, the data it used, anything still missing and the next steps worth taking, for a licensed professional to review.
What is this business worth?
Discounted cash flow valuation with a terminal value and a sensitivity grid. Run research dcf in the CLI, or call the same tool over MCP. It needs cashFlows and discountRate. The valuation discounts each year of the forecast. The result carries the method it used, the data it used, anything still missing and the next steps worth taking, for a licensed professional to review.
The other skill packs
- Compliance: Automated screen of advisory communications for promissory language and missing standard disclosures, FINRA 2111 suitability and Marketing Rule performance checks, investment adviser registration lookups in SEC IAPD compilation files, and guidance for supervisory review.
- CRM: Meeting transcript parsing into decisions and action items, and CRM task payload construction, plus guidance for meeting preparation.
- Execution: Pre-trade validation (buying power, oversell, short-term gain), order payload construction for Alpaca, Interactive Brokers and FIX 4.4, ISIN/CUSIP/FIGI/LEI check digits and T+1 settlement dates, for human-approved execution.
- Fund operations: Fund administration and wealth operations checks - position reconciliation against the custodian, NAV tie-out with level 3 and stale-price flags, LP capital statement roll-forwards, and month-end close tracking - plus guidance for accounting and regulatory reporting that the engines do not perform..
- Onboarding: Customer Identification Program field checks, application gaps by account type (CIP, beneficial ownership, FINRA 4512, 2090, 2111 and 2165), and onboarding milestone tracking.
- Planning: US retirement and tax planning calculations - tax year 2026 bracket headroom for sizing Roth conversions, required minimum distributions, retirement Monte Carlo with inflation-adjusted withdrawals, capital-loss netting and carryover, and net investment income tax - plus guidance for broader household planning that the engines do not model..
- Portfolio: Portfolio drift monitoring and rebalancing, parametric VaR and expected shortfall, tax-loss harvesting screens with a wash-sale look-back, cost basis by lot, time- and money-weighted returns, Sharpe ratio reliability, and small-universe historical and forward simulations - plus guidance for accounting, attribution and risk-model workflows that the engines do not implement..
- UHNW: Concentrated-stock collar construction with constructive-sale review, and private equity multiple tracking (TVPI, DPI, RVPI), plus guidance for trust, philanthropic and exchange-fund planning that the engines do not model..