maildb-operations

Query and analyze Mathematica mail databases with privacy-aware LLM routing.

3|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/transreal/claudecode --skill maildb-operations
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: maildb-operations
Source: https://github.com/transreal/claudecode/tree/main/Claude%20Directives/skills/maildb-operations
Command: npx skills add https://github.com/transreal/claudecode --skill maildb-operations

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you operate a Mathematica mail database by generating correct code for showing, searching, updating, and replying to mail while preventing privacy-unsafe model routing.

Core Features & Use Cases

  • Privacy-safe LLM routing: Uses $ClaudePrivateModel when mail privacy is high, and restricts $ClaudeModel use to public emails (privacy <= 0.5).
  • Correct MailDBObject workflow: Ensures you load mail once via mailEnsureLoaded and pass a MailDBObject into showMails/searchFromMails (never a raw mbox string).
  • Deadline and priority-aware filtering: Supports Period, HasDeadline, MinPriority/MaxPriority, MaxPrivacy, and dataset Select-based fallbacks for older versions.
  • LLM-assisted deadline summaries and analysis: Uses mailAskLLM with security-aware auto model assignment and options like IncludeBody and HasDeadline.
  • Ongoing maintenance tasks: Provides updateMonthlyMaildb, batchUpdateMaildb, and checkNewMail for keeping databases current, plus sendReply and translation-reply helpers.

Quick Start

Ask an AI to “Show my univ emails from the last week that have deadlines, and route any privacy-sensitive content correctly.”

Frequently Asked Questions about maildb-operations

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I securely query Mathematica mail databases to filter emails by deadline and priority?

To securely query a Mathematica mail database, use mailEnsureLoaded to load cached datasets, pass the resulting MailDBObject to searchFromMails, and apply filters like Period, HasDeadline, and MinPriority for targeted results.

How does privacy routing work when running LLM analysis on email datasets?

Privacy routing enforces secure LLM analysis by directing emails with a privacy threshold greater than 0.5 to $ClaudePrivateModel, restricting $ClaudeModel usage to public emails to prevent privacy-unsafe model routing.

Can I use IMAP mail datasets with this workflow or do I need a specific MailDBObject format?

You must use a MailDBObject rather than raw IMAP strings. The workflow requires loading your mail database once via mailEnsureLoaded to generate the correct MailDBObject before passing it to showMails or searchFromMails.

What is the best way to generate deadline-focused summaries from an inbox using LLMs?

The best way to generate deadline-focused summaries is using mailAskLLM with security-aware auto model assignment, applying the HasDeadline and IncludeBody options to extract and analyze relevant deadline information from your mail database.

How do I keep my Mathematica mail database current with ongoing maintenance tasks?

You can keep your Mathematica mail database current by utilizing updateMonthlyMaildb, batchUpdateMaildb, and checkNewMail maintenance tasks to regularly update datasets and ensure ongoing database accuracy.

Why does passing raw IMAP email strings directly to search functions fail?

Passing raw strings fails because the workflow requires a properly structured MailDBObject. Loading via mailEnsureLoaded first ensures the mail database is safely cached and formatted before querying with showMails or searchFromMails.