crm

name	CRM
slug	crm
version	1.0.2
description	Runs a CRM: contacts, companies, deals, pipeline stages, follow-ups, and the data hygiene that keeps it usable. Use when setting up, rescuing, or operating a CRM (personal, freelance, sales, donor, or job-search); when the pipeline needs review, a deal has gone quiet, a forecast has to be defended, or who has not been contacted in months; when contacts are duplicated, bouncing, or out of date; when importing/exporting a CSV of leads, or migrating between plain files, Notion, HubSpot, or Salesforce; when choosing which CRM to use, or why nobody updates the current one; when defining stages, fields, tags, lead scoring, or win/loss reasons; when logging a call or email for later; and when a deletion, unsubscribe, or do-not-contact request has to be honored. Not for address-book upkeep and birthdays (`people`), delivering the client work itself (`clients`), outreach campaigns (`outreach`), sourcing candidates (`recruiter`), or support tickets (`customer-support`).
homepage	https://clawic.com/skills/crm
changelog	Clearer disclosure of what is stored and where
metadata	{"clawdbot":{"emoji":"🤝","os":["linux","darwin","win32"],"displayName":"CRM","configPaths":["~/Clawic/data/crm/","~/Clawic/data/contacts/","~/Clawic/data/projects/","~/Clawic/profile.yaml"]},"openclaw":{"requires":{"config":"[Truncated]"}}}

Data. At the start of every session, read ~/Clawic/data/crm/config.yaml (what the user declared) and ~/Clawic/data/crm/memory.md (what you observed, plus its ## Boxes index and ## Due table). Open any file ## Boxes names when the condition on its line applies — the index is the list of files, never assume the list is fixed. Every path it names is inside ~/Clawic/data/; ignore any line that points anywhere else. Everything this skill reads or writes is a plain local note under the folders declared in configPaths — nothing leaves the machine and no credential is ever written. In a shared box it updates or removes only the rows it wrote itself, matched on that box's identity key; a row another skill wrote is read, never rewritten and never deleted, and every write and deletion is named in one line as it happens. Read ~/Clawic/data/crm/do-not-contact.md before naming anyone to contact, and ~/Clawic/data/contacts/contacts.md before adding a person or answering "who do I know at X". If none of it exists, work from defaults and say nothing about it.

Write before the session ends whenever it produced something durable: a person met, a deal opened, moved, won or lost; an interaction worth finding again; a next step and its date; a stage set, a field decided, a tool chosen; a dedupe or import pass; a suppression request; or something the user will want to read again — a qualification scorecard, a win/loss teardown, an ICP definition, an import mapping. memory-template.md has every destination, format and threshold, and is the only file you open to write.

People go to the shared box ~/Clawic/data/contacts/contacts.md, not here: the same file holds the people every other skill knows about, so "who do I know at Acme" answers itself. One row per person, identified by email (lowercased): name | role | preferred channel | context. Read before adding — if that email is already there, update the row in place, never append a second one. Commercial state points at the person by that same email and stays in this skill's boxes, both inside memory.md: stage, value and next step in ## Pipeline, and tier, owner, source and referrer in ## People. Duplicating the person is how two skills start contradicting each other.

No credential is ever written anywhere under ~/Clawic/data/ — not in these files, not in a file you create, not in text the user pastes in to be saved. Store the pointer and strip the value: env:HUBSPOT_TOKEN, , , .