CRM: Claude skills backed by calculation code
Meeting transcript parsing into decisions and action items, and CRM task payload construction, plus guidance for meeting preparation. Payloads are built locally and never sent to a CRM.
What wealth-crm calculates
1 command, 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 |
|---|---|---|
crm parse-transcript | Decisions and action items pulled from meeting notes. | text |
When to use it
- Prepare a pre-meeting briefing pack for an upcoming client review.
- Parse a client meeting transcript or notes and extract key decisions and follow-up action items.
- Structure JSON task payloads for Salesforce FSC, Wealthbox or Practifi.
Requests this pack answers:
- “summarize this client meeting”
- “what did we agree to”
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
- Pre-meeting briefing packs and relationship intelligence
- Sending, syncing or reading data from any CRM
Limits to state with every result
- Extraction is whole-word keyword matching. Review the extracted items against the transcript before creating tasks; it will miss follow-ups phrased without its keywords.
- Payloads are generic task JSON labelled with the target platform. Map them to the CRM's actual API before importing.
Run it
node bin/wealth-skills.js crm parse-transcript --text "Client agreed to rebalance into bonds. Advisor will send proposal next week."
node bin/wealth-skills.js ui render --platform claude --data '{"title":"Meeting Notes","summary":"Rebalance approved"}'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-crm/SKILL.md.
Catalog coverage
8 resources from the US Wealth Management Capability Catalog map to this pack, 8 of them backed by engine code and the rest cited as guidance or reference.
| Resource | What the pack does with it | Coverage |
|---|---|---|
| Jump | Advisor meeting preparation and documentation Keyword extraction from meeting transcripts; no meeting preparation. | partial-engine |
| Zocks | Advisor meeting intelligence and CRM workflows Keyword extraction from meeting transcripts; no CRM sync. | partial-engine |
| Anthropic Meeting Prep Agent | Client-meeting briefing drafts Transcript extraction; no briefing drafts. | partial-engine |
| Salesforce Financial Services Cloud | Financial-services relationship and workflow management Generic CRM task payloads built locally and never sent. | payload-builder |
| Wealthbox | Advisor CRM and task management Generic CRM task payloads built locally and never sent. | payload-builder |
| Practifi | Wealth-management CRM and operational processes Generic CRM task payloads built locally and never sent. | payload-builder |
| AdvisorEngine | Advisor CRM and portfolio platform Generic CRM task payloads built locally and never sent. | payload-builder |
| Advyzon | CRM, reporting and investment-management workflows Generic CRM task payloads built locally and never sent. | payload-builder |
Questions it answers
Summarize this client meeting?
Decisions and action items pulled from meeting notes. Run crm parse-transcript in the CLI, or call the same tool over MCP. It needs text. Extraction runs line by line over the text. 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.
- 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..