What you'll learn in this lesson
Why email is the ideal first AI skill to build, how to design a self-learning feedback loop that improves with every correction, and how to walk away with a working email triage skill you can use immediately.
- 1
Why Gmail triage is the perfect first skill
High-volume, pattern-rich, and it improves with feedback: the ideal skill to build and learn from.
- 2
How to design a self-learning loop
Build a skill that captures your corrections and gets smarter over time, stored in a preferences file that evolves with you.
- 3
Walk away with a working skill
Leave with a ready-to-use Claude skill that sorts, prioritizes, summarizes newsletters, and drafts replies.
Lesson chapters
- 0:00The email overload problem & virtual assistant analogy
- 2:45Who is Prasad & what is Agentman
- 5:26What a skill looks like — anatomy of a SKILL.md
- 7:56Hands-on: Creating the email triage skill
- 13:00Other ways to create skills (past work, cloning)
- 16:00Running the skill: Live email triage demo
- 20:00The three-layer skill architecture
- 22:15Multi-skill stacking in marketing & beyond
- 24:18The future: Skills marketplace & selling expertise
- 26:05Q&A: Evaluator skills, pricing, versioning
Why email is the best first AI skill to build
Email combines three things: high volume, strong pattern-recognition potential, and natural feedback loops that improve accuracy over time. You've built mental patterns over years (what to answer first, what to skim, what to archive), but they live in your head and cost you time every day.
The virtual assistant analogy
Think of hiring a human assistant for the first time. They already know what an important email generally looks like: addressed to you, from a known contact. What they don't know are your preferences: which clients matter most, which newsletters you actually read, how your priorities shift. You teach them through feedback. Early on you correct them daily; after a few weeks they've got it. That's exactly how this skill works.
New to skills and the feedback loop? Start with the Skills Academy. It covers what a skill is, how it learns, and why prompts drift while skills compound.
Two steps before you start (~5 minutes)
- 1
Connect Claude to Agentman Skills
Store your skills centrally and use them across Claude, ChatGPT, and more.
- Register for a free account at studio.agentman.ai/register
- In Claude → Settings → Connectors, find Agentman Skills in the Connectors Directory
- Click Connect, log in, pick your workspace, and authorize access to your Agentman account
- Verify: type list my skills in Claude. If it responds with your account, you're connected
- 2
Connect Claude to your Gmail
The Agentman Gmail MCP is feature-rich: unsubscribe, labels, tasks, and more.
- In Claude → Settings → Connectors → Custom MCP Connector, add server URL https://mcp.agentman.ai/gmail/mcp
- Click Connect to log in
Google verification in progress. When connecting, Google may show a security warning. Click Advanced → "Go to Agentman (unsafe)" → Grant permissions. We're completing Google's verification, and it's safe. The walkthrough below shows you how.
Setup walkthrough video
How to build the self-learning email triage skill
It takes about 10 minutes and no code. You describe what you want in plain English, Claude generates and publishes the skill through the Agentman MCP server, and the feedback loop starts with your first triage session.
- 1
Set up prerequisites
Create an Agentman account, connect the Skills MCP server, and connect Gmail. Takes about 5 minutes (see Before you start, above).
- 2
Prompt Claude to create the skill
Tell it what you want: identify important emails, summarize newsletters, spot spam, and after every run, ask you for detailed feedback.
- 3
Claude builds and publishes it
It downloads the skill creation guide, validates the structure, creates the skill, and publishes it, all through the MCP server.
- 4
Run the skill on your inbox
Say "Triage my work email" and watch it load your skill, read your preferences, fetch your inbox, and classify every message.
- 5
Give feedback to improve it
After each run, tell it what it got wrong: miscategorized emails, new VIP senders, changed priorities. The skill stores your corrections and improves.
Try this prompt in Claude
Using the Agentman Skills MCP server skills creator,
create me an email triage skill that will:
1. Identify important emails
2. Find newsletters, summarize key insights, and archive them
3. Identify spam and unsubscribe
4. After every run, ask me for detailed feedback — which
drafts needed changes, which emails were miscategorized,
and any preferences I want updated
Name it: my-email-triageWhat a run looks like
The skill reads your preferences, sorts the inbox, acts on what you allowed it to, and ends by asking what it got wrong.
- Dana Whitfield, Northgate SupplyRenewal terms need your sign-off by Friday. Draft reply ready.
- Marcus Oyelaran, FinanceAsks for the Q3 forecast file. Task created.
- Priya Raman, Halden LabsMoves Thursday's call to 2 pm. Draft reply ready.
- SummaryThe Ops Weekly: three notes on vendor onboarding.
- Before I finishWhich of these did I get wrong, and is anyone here a VIP I should remember?
How the three layers show up in email
The lesson uses the three-layer model from the Skills Academy. Here's how it maps onto an inbox. For the full breakdown, see the Academy.
Email intelligence layer
Spam detection, newsletter patterns, triage heuristics, response etiquette. Portable knowledge that rarely changes.
Personal preferences
Your VIP senders, response style, archive rules, and priorities, layered on top and refined by the feedback loop.
Situational context
Active deals, current projects, this week’s priorities: the things you update often.
Why use Agentman's Gmail connector
Claude's native Gmail integration is read-only. Agentman's Gmail MCP server adds the write capabilities a real triage workflow needs: archiving, unsubscribing, creating Google Tasks, and managing multiple accounts.
Compared when this lesson was last updated, March 2026.
Key takeaways
Five principles from this lesson apply to every AI skill you build, not just email triage.
- 1
Skills encode judgment, not just knowledge
The rules, exceptions, and preferences that make your work yours. That’s what separates a skill from a generic prompt.
- 2
The feedback loop is the superpower
A preferences.md file that accumulates your corrections turns a generic classifier into a personal assistant that improves with every session.
- 3
Think in three layers
A portable intelligence layer, your personal preferences on top, and the situational context that changes week to week.
- 4
Skills are portable across AI platforms
What you build works in Claude, ChatGPT, Cursor, and any MCP-compatible tool. Your intelligence layer isn’t locked to one vendor.
- 5
Everything here applies beyond email
The creation process, the feedback loop, the layered architecture: if you can build an email triage skill, you can build one for any part of your knowledge work.