Compliance: Claude skills backed by calculation code
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. BrokerCheck research stays manual.
What wealth-compliance calculates
4 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 |
|---|---|---|
compliance scan | Keyword and pattern screen of a communication before principal review. | text |
compliance lookup | Investment adviser registration and disclosure lookup in an SEC IAPD compilation file, by CRD or name. | feedPath, crd |
compliance suitability | Customer-specific and quantitative suitability checks under FINRA 2111, with the profile gaps that prevent a view. | profile, recommendation |
compliance performance-ad | Checks advertised performance against the SEC Marketing Rule’s performance provisions, 206(4)-1(d). | ad |
When to use it
Requests this pack answers:
- “is this email compliant”
- “can we send this to clients”
- “is this adviser registered”
- “look up this CRD”
- “is this suitable for the client”
- “Reg BI care check”
- “can we show this performance”
- “marketing rule check”
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
- FINRA BrokerCheck research (manual, per FINRA terms of use)
- Disclosure details and Form ADV brochures (on the IAPD site)
- Communication surveillance and archiving (Smarsh, Global Relay)
- Supervisory logging and FINRA Rule 3110 review workflows
- Marketing Rule provisions beyond performance (testimonials, endorsements, third-party ratings)
Limits to state with every result
- The screen is pattern matching. It does not understand negation, judge whether a communication is fair and balanced, or review performance presentations.
- Passing the screen is not approval. Retail communications still need review by a registered principal.
Run it
node bin/wealth-skills.js compliance scan --text "We offer a guaranteed 15% return with past performance."
node bin/wealth-skills.js compliance lookup --feed tests/fixtures/iapd/sec-firms.xml --crd 900002 --as-of 2026-09-13The 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-compliance/SKILL.md.
Catalog coverage
51 resources from the US Wealth Management Capability Catalog map to this pack, 14 of them backed by engine code and the rest cited as guidance or reference.
| Resource | What the pack does with it | Coverage |
|---|---|---|
| FINRA 2111 Suitability | Suitability rule and applicability boundaries Customer-specific and quantitative suitability; reasonable-basis suitability needs human judgment. | partial-engine |
| FINRA 2210 Communications with the Public | Public communication standards Pattern screen for promissory language and disclosures; not a principal review. | partial-engine |
| Regulation Best Interest adopting release | Broker-dealer retail recommendation standard Care-obligation suitability checks; disclosure and conflict obligations are guidance. | partial-engine |
| Investment adviser conduct interpretation | SEC interpretation of adviser fiduciary conduct Best-interest fit checks; the duty of loyalty is guidance. | partial-engine |
| Adviser marketing rule 206(4)-1 | Investment-adviser advertising requirements Performance provisions of paragraph (d) only; testimonials, endorsements and ratings are not checked. | partial-engine |
| Model Context Protocol specification | Agent-to-tool message and authorization contracts stdio JSON-RPC server with tools/list and tools/call; no resources, prompts or HTTP transport. | partial-engine |
| JSON Schema 2020-12 | Structured input and output validation Tool input schemas are published and validated for required fields, types and enums; not full JSON Schema. | partial-engine |
| Smarsh | Communication retention and supervision Pattern screen of communications; no archiving or retention. | partial-engine |
| Global Relay | Communications archiving and surveillance Pattern screen of communications; no archiving or retention. | partial-engine |
| Behavox | Communication surveillance and conduct risk Keyword screen; no behavioral surveillance. | partial-engine |
| Nasdaq SMARTS | Trade surveillance Turnover and cost-equity indicators against firm limits; no market-abuse surveillance. | partial-engine |
| ACA ComplianceAlpha | Compliance workflows and oversight Communication, suitability and performance-advertising checks; no workflow platform. | partial-engine |
| Comply | Regulatory compliance and employee monitoring Communication and advertising checks; no employee monitoring. | partial-engine |
| SEC IAPD | Investment-adviser registration and disclosure research Registration status, notice filings, state registrations, employers, exams and disclosure flags from the SEC IAPD compilation files the operator downloads. Disclosure details and Form ADV brochures stay on the IAPD site. | partial-engine |
| NICE Actimize | Financial-crime and compliance analytics No financial-crime analytics. | guidance |
| FINRA BrokerCheck | Broker and firm registration research Manual check only: FINRA terms of use prohibit automated access and use with AI tools. The IAPD lookup covers the adviser side of dual registrants; broker-dealer registration still needs BrokerCheck. | guidance |
| Form ADV | Investment-adviser disclosures Disclosure document; guidance only. | standard-reference |
| Form CRS instructions | Relationship-summary disclosure instructions Disclosure document; guidance only. | standard-reference |
| FINRA 3110 Supervision | Supervisory systems and procedures Supervisory requirement; guidance only. | standard-reference |
| FINRA 3120 Supervisory Control System | Supervisory testing and control procedures Supervisory requirement; guidance only. | standard-reference |
| FINRA 3130 Annual Certification | Compliance and supervision certification Supervisory requirement; guidance only. | standard-reference |
| FINRA 2214 Investment Analysis Tools | Investment-analysis tool communications The projection tools here are investment analysis tools; required disclosures are guidance. | standard-reference |
| FINRA 3260 Discretionary Accounts | Discretionary account authorization and review Discretionary account requirement; guidance only. | standard-reference |
| FINRA 2341 Investment Company Securities | Investment-company distribution rules Distribution rule; guidance only. | standard-reference |
| FINRA 4370 Business Continuity Plans | Business continuity planning Operational requirement; guidance only. | standard-reference |
| FINRA 2231 Customer Account Statements | Account-statement requirements Operational requirement; guidance only. | standard-reference |
| FINRA 4530 Reporting Requirements | Regulatory event reporting Regulatory reporting; guidance only. | standard-reference |
| Adviser compliance rule 206(4)-7 | Adviser compliance policies and review Compliance program rule; guidance only. | standard-reference |
| Adviser books and records rule 204-2 | Investment-adviser recordkeeping Audit metadata supports but does not satisfy recordkeeping. | standard-reference |
| Broker-dealer records rule 17a-4 | Broker-dealer record preservation Audit metadata supports but does not satisfy recordkeeping. | standard-reference |
| Regulation S-P | Financial-information privacy and safeguards Privacy rule; guidance only. | standard-reference |
| CFA Institute Asset Manager Code | Asset-manager conduct principles Conduct code; guidance only. | standard-reference |
| NIST AI Risk Management Framework | AI-risk governance framework Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| NIST Generative AI Profile | Generative-AI risk considerations Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| NIST Cybersecurity Framework 2.0 | Cybersecurity outcomes and risk management Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| NIST SP 800-53 Rev. 5 | Security and privacy control catalog Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| NIST SP 800-207 | Zero-trust architecture guidance Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| OAuth 2.0 RFC 6749 | Delegated authorization protocol Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| OpenID Connect Core 1.0 | Identity claims and authentication protocol Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| Agent2Agent protocol | Agent collaboration and task interfaces Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| OpenAPI specification | Machine-readable API contracts Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| CloudEvents specification | Event metadata interoperability Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| OpenTelemetry specification | Telemetry and tracing interfaces Governance, security or interface standard for agents using the packs; guidance only. | standard-reference |
| W3C PROV-O | Provenance representation Audit metadata records provenance informally; not PROV-O. | standard-reference |
| Artificial Intelligence in the Securities Industry (FINRA, 2020) | Broker-dealer AI use cases and governance AI governance in financial services. | research-reference |
| Artificial Intelligence in Financial Services (US Treasury, 2024) | Financial-sector AI adoption and risk themes AI governance in financial services. | research-reference |
| Managing Artificial Intelligence-Specific Cybersecurity Risks in the Financial Services Sector (US Treasury, 2024) | AI and financial-sector cybersecurity AI governance in financial services. | research-reference |
| The Financial Stability Implications of Artificial Intelligence (FSB, 2024) | Systemic implications of financial AI AI governance in financial services. | research-reference |
| Artificial Intelligence and Machine Learning in Financial Services (FSB, 2017) | Financial AI market developments and stability AI governance in financial services. | research-reference |
| The Use of Artificial Intelligence and Machine Learning by Market Intermediaries and Asset Managers (IOSCO, 2021) | Intermediary and asset-manager AI governance AI governance in financial services. | research-reference |
| Artificial Intelligence in Asset Management (CFA Institute Research Foundation) | Asset-management ML methods and adoption AI governance in financial services. | research-reference |
Questions it answers
Is this email compliant?
Keyword and pattern screen of a communication before principal review. Run compliance scan in the CLI, or call the same tool over MCP. It needs text. The screen runs over the wording as it would be sent. 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.
Is this adviser registered?
Investment adviser registration and disclosure lookup in an SEC IAPD compilation file, by CRD or name. Run compliance lookup in the CLI, or call the same tool over MCP. It needs feedPath and crd. Lookups run on the official SEC bulk file on disk; nothing is scraped. 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.
Is this suitable for the client?
Customer-specific and quantitative suitability checks under FINRA 2111, with the profile gaps that prevent a view. Run compliance suitability in the CLI, or call the same tool over MCP. It needs profile and recommendation. FINRA 2111 names these nine factors. 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.
Can we show this performance?
Checks advertised performance against the SEC Marketing Rule’s performance provisions, 206(4)-1(d). Run compliance performance-ad in the CLI, or call the same tool over MCP. It needs ad. Each triggers different conditions. 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
- 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..
- Research: 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..
- 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..