Step 1
Keep it in sqemes
Write skills, prompts and personas once. Every saved change keeps a version, and you decide who may see and who may edit each one.
Many teams already work in ChatGPT. sqemes does not replace it. It keeps your team's skills, prompts and personas once and brings them into ChatGPT and every other AI tool you use.
sqemes reaches ChatGPT in two ways: the browser extension next to the input box, and the MCP server on ChatGPT Business and Enterprise.
Three steps, whichever ChatGPT plan you use.
Step 1
Write skills, prompts and personas once. Every saved change keeps a version, and you decide who may see and who may edit each one.
Step 2
Install the browser extension for every plan. On Business and Enterprise, an admin can also add sqemes as a custom MCP server on ChatGPT web.
Step 3
In ChatGPT and in every other tool connected to sqemes, your team works from the same playbooks. A change in sqemes reaches all of them.
| Feature | sqemes | ChatGPT |
|---|---|---|
| What it is | A library for AI know-how: skills, prompts and personas, used in other AI tools and in sqemes Chat | An AI assistant with chat, projects, skills, plugins and Codex |
| Where the know-how is used | In ChatGPT, Claude and Gemini through the browser extension, any MCP client, sqemes Chat | In ChatGPT and Codex |
| Reusable knowledge | Skills with files, loaded when a task needs them | Skills and projects; plugins bundle skills and apps |
| Sharing | Per playbook: everyone, named people and groups, or only me; who may edit is set separately | Skills and plugins can be shared with people, groups or the workspace; editing by the creator or permitted admins |
| MCP | An MCP server for your playbooks and personas; sqemes Chat also connects other MCP servers | Connects custom MCP servers on Business and Enterprise (web), set up by admins |
| Models | Any provider with your own key, or the plan's AI credits | OpenAI models |
| Training | Your content is never used to train a model | Business and Enterprise data is not used for training by default |
| Hosting | Hosted in the EU; self-host on your own servers under a fair-code license | Data residency in Europe for Enterprise and Edu; for Business it is rolling out |
As of: 14 November 2026, from OpenAI's own pages. Sources: ChatGPT plans, OpenAI: skills, OpenAI: plugins, OpenAI: custom MCP servers, OpenAI: data residency.
Most teams use both. This helps if you wonder whether ChatGPT alone is enough.
your whole team works in ChatGPT and nowhere else.
your know-how should work in ChatGPT and beyond.
What teams ask about sqemes and ChatGPT.