Skills Academy

Learn skills, connect them, then build your own.

Everything in one place, in five steps. Start at the top, or jump straight to the part you need.

01 · Understand

Prompts drift. Skills compound.

A prompt is a one-time instruction you retype every session. A skill is a living document that keeps your procedures, decision logic, and corrections in one place, so the work gets more accurate the more you use it. Here's what one actually is.

What a skill is made of
my-skill/ ├── SKILL.md ← instructions (required) ├── preferences.md ← what it learns from you ├── references/ ← supporting docs │ └── examples.md ├── scripts/ ← executable logic │ └── calculator.py └── assets/ ← templates, images └── template.docx

A skill is a folder of intelligence

At its core, a skill is a folder of files that teach AI how to do something specific. One file does most of the work, the SKILL.md:

· Metadata — the name, description, and when AI should use it
· Instructions — the actual procedures and decision logic
· References — links to the other files, including the preferences it learns into

Everything else is optional. You can build a powerful skill with just a well-written SKILL.md.

The three layers inside it

What a skill knows sorts into three layers. Separating them is what lets one skill keep paying off without constant rewrites:

Foundation — portable know-how
The transferable expertise you would bring to any job: triage heuristics, deal-analysis frameworks, coding standards.
rarely changes
Your context
Your VIP senders, brand voice, payer rules, investment thesis. This is the layer the feedback loop keeps refining.
changes periodically
Right now
Active deals, current projects, this week's priorities. Updated often.
changes frequently
How a skill learns

This is where "compound" comes from. You give the skill one standing instruction to capture your feedback. After that it runs the loop itself every session, with no re-prompting, asking what to change and saving the answer. It isn't the model rewriting itself unprompted; it's a loop you set up once:

1

Run the skill

It does the work using its current instructions.

2

You correct it

Flag what it got wrong, miscategorized, or should handle differently.

3

It saves the lesson

Your corrections are written to the preferences.md file inside the skill.

4

Next run is sharper

The skill reads those preferences first, so it starts where you left off.

Repeats every run. In the workshop, Prasad's preferences file reached 23 revisions over 7–8 weeks, and the assistant kept getting better.

That standing instruction is just one line: "After every run, ask me what to change, and update your preferences." No code, no retraining, and nothing changes unless you confirm it.

How skills stack

Skills aren't used one at a time. You can load several complementary skills into a single conversation so they work in concert — the AI applies all of them at once. Stack the right few and a workflow that used to mean switching between tools happens in one session.

Brand voice+Image prompt+Blog generator+Answer-engine optimization

One published blog post used all four together in a single Claude conversation — how the team writes, its visual style, the content structure, and the optimization that helps it rank in AI-powered search. The same approach works for presentations, sales outreach, or any workflow where consistency matters across a team.

02 · Connect

One connection. Every tool you already use.

Skills aren't locked to one app. Store them once in Agentman and reach them from any AI tool through a single MCP connection, the open standard for giving AI access to your tools and content.

{ }

Your skills

Stored once in Agentman

1 MCP connectionskills.agentman.ai/mcp
Claude
ChatGPT
Cursor
Your agents
Connect in under five minutes
1

Register free

Create your workspace at studio.agentman.ai/skills and add the skills you want.

2

Add a custom MCP server

In your AI's settings, add a connector and paste skills.agentman.ai/mcp.

3

Authorize & verify

Approve access, then ask "list my skills" to confirm they're live.

Operator or developer, the steps are identical. Connecting is no-code, paste one URL and you're done. There's nothing to install and no engineering required. The MCP standard is what lets the same skill work across Claude, ChatGPT, Cursor, and the agents you build.
03 · Your path

Go deeper on the path that fits your role.

Same foundation, different next steps. Each path is a short, ordered sequence that ends by handing you off to the right way to build.

For business operators

Put skills to work

Automate your own and your team's workflows. No code required.
Industry applications
Take action
For developers

Build skills into your products

Author robust skills and embed them in your own apps and agents, following the Agent Skills spec.
Browse all guides on the blog
04 · Watch

Watch a self-learning skill get built.

The fastest way to understand skills is to watch one come together. In 30 minutes, build a Gmail assistant that triages your inbox, then wire up the feedback loop from section 01 so it sharpens every time you correct it.

Workshop · 30 min

Build a Self-Learning Gmail Assistant

Sort important mail, summarize newsletters, flag spam, plus the feedback loop that writes your corrections back into the skill. No code required.

Hosted by Prasad Thammineni · Beginner-friendly
Open the full lesson
05 · Build

Create your own skill.

You've seen what a skill is, how it learns, and how to connect it. Now make one. Start the fast way, then refine in the visual editor. Your skill works in Claude, ChatGPT, and your agents.

Recommended · fastest

Quick Create

Describe what you need in plain English. The builder writes the SKILL.md, organizes your content, and formats it correctly, feedback loop included.

"Create an email-triage skill that sorts important mail, summarizes newsletters, flags spam, and after every run asks me what to fix and updates its preferences."
Try Quick Create
Best for: adapting existing expertise

Clone & Customize

Start from a system skill that's close, clone it to your workspace, then adjust the thresholds, templates, and decision logic for your team.

Browse skills to clone
Best for: unique organizational knowledge

Build from Scratch

Open the visual editor with a blank SKILL.md. Full control over structure, content, and organization.

Open the editor
Quick Create — from description to skill in about 2 minutes
1

Describe it

Say what the skill does, when AI should use it, and the key decision logic.

2

Review the structure

The builder generates a SKILL.md with frontmatter, instructions, and a decision tree.

3

Edit & refine

Adjust thresholds, add edge cases, and customize templates in the editor.

4

Publish & use

Save to your workspace, instantly available in Claude, ChatGPT, and your agents.

The visual skill editor

Metadata panel

Name, version, description, category, tags, all in form fields. No YAML required.

Content editor

Rich text for SKILL.md, with a markdown preview that shows exactly what the AI will see.

File manager

Drag and drop into references/, scripts/, and assets/ to organize supporting content.

Token counter

Real-time token count across GPT-4, Claude, and Gemini, so you know your context cost.

Version history

See every version, compare side by side, and restore any one with a click.

Preview mode

Test in a sandbox to see how AI applies your instructions before publishing.

Ready to build your first skill?

Describe what you need, clone a starting point, or open a blank canvas.