aurelius-email

Draft Gmail messages with prepared-by and approved-by signatures.

1|Updated Apr 21, 2026
One-click install
npx skills add https://github.com/BenchAGI/bench-cowork --skill aurelius-email
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aurelius-email
Source: https://github.com/BenchAGI/bench-cowork/tree/main/skills/aurelius-email
Command: npx skills add https://github.com/BenchAGI/bench-cowork --skill aurelius-email

SYSTEM DOCUMENTATION & REQUIREMENTS

Drafts professional BenchAGI-branded outbound email as a Gmail draft, signed by Aurelius (or another named Bench agent) with a human-approver line and links to the public AI Transparency Audit Log. Use whenever the user asks to send, draft, compose, write, reply to, or follow up on any email on their behalf — especially to partners, customers, investors, cofounders (Jim, Jory), team members, or anyone outside the user. Also trigger on "as Aurelius", "on our behalf", "email them", "shoot a note", "write to", "ping <person>", or any variation implying outbound correspondence. Trigger even without the word "email" — "let them know", "follow up with X", "send a reminder" count when the medium is clearly written. Enforces our AI-transparency posture (every agent-drafted email gets a prepared-by/approved-by signature). Do NOT use for SMS, Slack DMs, in-app notifications, or internal system messages — those have their own channels.

Frequently Asked Questions about aurelius-email

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

FAQPage Schema
How do I draft Gmail emails with AI provenance and human approval signatures?

You can generate Gmail drafts with AI provenance by prompting the Skill to compose or reply to messages; it automatically embeds prepared-by and approved-by signatures, linking to a public AI Transparency Audit Log for human-approved outbound correspondence.

What is AI transparency in email drafting and why is an audit log needed?

AI transparency in email drafting means every AI-generated message includes a prepared-by signature for the AI agent and an approved-by line for the human reviewer, creating an auditable provenance trail to ensure accountability in outbound communications.

Can I use this to write follow-up emails to investors without saying the word email?

Yes, the Skill triggers on contextual phrases like "follow up with" or "let them know" when the medium is clearly written correspondence, automatically drafting the outbound message to investors, partners, or colleagues without requiring the explicit word email.

How do I add an AI-generated signature block with a named human approver to Gmail drafts?

The Skill enforces a consistent signature block by appending the AI agent name, such as Aurelius, alongside a named human approver and timestamp to every generated Gmail draft, fulfilling the AI-transparency posture required for outbound communication.

Does this email drafting approach work for Slack DMs or internal system messages?

No, this approach is explicitly restricted from SMS, Slack DMs, in-app notifications, and internal system messages; it is designed solely for drafting professional outbound Gmail correspondence to external parties or team members.

What is the best way to automate outbound email drafting while maintaining an auditable trail?

The best way to maintain an auditable trail when automating outbound email is to use a drafting process that enforces AI-transparency signatures, capturing both the AI preparer and human approver with timestamps in a public Audit Log for every generated message.