Decisions and action items pulled from meeting notes
One command in the CRM pack, available in the CLI, as an MCP tool and as a JavaScript import: crm parse-transcript.
What it needs, and why
Every input is checked before anything is calculated. text is required; the rest refine the answer.
| Input | Required | The question it asks | Why it matters |
|---|---|---|---|
text | yes | What are the meeting notes or transcript? | Extraction runs line by line over the text. |
Requests it answers
- “summarize this client meeting”
- “what did we agree to”
- “turn these notes into tasks”
An agent with this pack loaded picks the command from phrasing like that, asks for whatever input is missing, and reports the figures with the method that produced them.
Run it
node bin/wealth-skills.js crm parse-transcript --text "Client agreed to rebalance into bonds. Advisor will send proposal next week."Limits it inherits from wealth-crm
- 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.
The full pack, its other 0 commands and what it deliberately leaves alone are on the CRM page.