Schmoozing — Data skill for Claude Code
From a pocketful of cards to pipeline.
How to install Schmoozing
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open catrinmdonnelly/schmoozing and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Schmoozing does
From a pocketful of cards to pipeline. A Claude Code skill that turns business card photos into researched CRM records.
Alternatives in Data
- Skill Production Pipeline — Claude-skills — Effective: 2026-03-07 Applies to ALL new skills, improvements, and deployments 5.3k ★
- Ars Full — ARS full pipeline — research → write → review → revise → finalize 4.5k ★
- Osint Employees — Gather employee names + email patterns for password spray prep 4.5k ★
README
Schmoozing
**Turn a pile of business cards into a researched pipeline.**
You have just got back from an event with a pocket full of cards. Now comes the tedious bit: typing them in, finding the right company, filling in the gaps, and deciding who is actually worth pursuing.
Schmoozing does it in one pass.
Photograph the cards. We will turn them into pipeline.
It reads the details, checks them against independent sources, researches the person and the business, and adds a clean, useful record to your CRM, with a verdict and a next action where it can.
So instead of a stack of cards waiting to be processed, you have a pipeline ready to work.
Install
/plugin marketplace add catrinmdonnelly/schmoozing
/plugin install schmoozing@schmoozing
Or drop it in as a plain skill:
git clone https://github.com/catrinmdonnelly/schmoozing ~/.claude/skills/schmoozing
Then photograph a card and say **"scan this card"**.
Needs Python 3, which every Mac has. `gspread` and `google-auth` only if you send them to a Google Sheet.
What happens to each card
- It reads the card. Claude reads the image directly, so there is no OCR library and the photo is not uploaded anywhere. It copes with two-sided cards, QR codes, bilingual cards, generic inboxes, and the difference between a trading name and a registered one.
- It checks you have not met them before. Searching your existing contacts first stops the same person going in three times across a year of events, and stops you emailing someone you archived last year.
- It checks the card against reality. Phone against the company's own website, email domain against DNS, name spelling against the companies register, job title against their profile. A card is a printed claim, often years old.
- It researches the business. What they sell and how an order actually reaches them, evidence of size and ownership, recent news, the person's LinkedIn.
- It gives a verdict. Against your definit
Related Skills
Memex
Open-source, local-first AI journal app for iOS and Android. Capture text, photos, and voice — AI agents organ
Vbcs Export Data
Export a business object's data records from a standalone VBCS instance
Content Factory
Claude Code skill: pipeline from topic to researched blog-post PR
Pipeline Reviewer
Analyze CRM pipeline data to identify risks, recommend actions, and generate a weekly pipeline summary.
Greenscape Reactivation Agent
For the About field (350 char limit). My pick: AI-drafted, human-approved re-engagement pipeline for a landsca
Jobs New
The one daily command. A Python driver runs the whole pipeline in a fixed order — validate → fetch → enrich →
Related Agents
Codex Artist
Image-generation subagent. Use PROACTIVELY whenever a task needs image files — generating or editing icons, lo
Transaction Processor
Use when the user needs to import, categorise, or process transaction data from bank or credit-card exports. R
Shine CRM Operator
CRM hygiene + enrichment — dedupes, fills gaps, syncs stages, purges stale records. Respects GDPR.