Skills
Reusable code packages that give your assistant new capabilities — from API integration to file generation.
What it is
Skills are reusable code packages (.zip files) that give your assistant capabilities beyond pure prompting or knowledge binding. They run in a secure sandbox and can call external APIs, generate files, process data, or apply specialized logic.
Skills always run in the context of an assistant. The detailed documentation lives in Skills inside the Assistants guide — that section covers upload, in-chat creation, and package structure. This page gives you the overview and the rules of thumb.
When does a skill make sense?
Skills are the right tool when your assistant needs to:
- call an API for which meinGPT has no native connector (e.g. your internal contract management system)
- generate a file in your layout (Word template, Excel report in your format, PowerPoint deck with branding)
- process data in a format the LLM doesn't handle natively (e.g. parsing binary data, complex table transformations)
- apply deterministic logic (calculations, validation, business rules)
If your need is solved by a system prompt + RAG datapool + native tools (MCP Studio) — no skill needed. Skills are the next escalation step for your own executable logic.
Skill vs Tool vs Connector — quick distinction
| Tool | What it is | When |
|---|---|---|
| Native Tool / Connector (MCP Studio) | Pre-built integrations to standard services (Slack, Outlook, Salesforce, ...) | Standard integrations available in the marketplace |
Skill (.zip package) | Your own code (Python or JavaScript/TypeScript), running in a sandbox | Custom logic, proprietary APIs, file generation in your format |
| Knowledge / Datapools | RAG over static documents | When the assistant should know your knowledge, not execute it |
How to add a skill to your assistant
Two paths — both in the assistant editor:
-
Upload a finished package — if you or a colleague already has a
.zip: drag & drop it into the Skills section. Immediately available to the assistant. -
Create a skill via chat — if you don't have the skill yet: click Create Skill in the editor. A specialized chat walks you through creation — purpose, required APIs, credentials, logic. At the end, the package is built and automatically attached.
Detailed walkthrough with screenshots: Skills in the Assistants guide.
Security & sandbox
Skills run in an isolated sandbox environment:
- No direct host system access
- Dedicated runtime per skill (Python or JS — auto-detected)
- Credentials (API keys, tokens) stay inside the skill package and aren't exposed to the model
- Resource limits prevent infinite loops or excessive memory usage
The sandbox architecture is described in Code Sandbox.
Common uses in mid-sized companies
| Use case | Skill content |
|---|---|
| Generate quotes in company layout | Word template + Python script that fills data from the chat |
| DATEV export from invoice data | JS script that converts JSON data to CSV format |
| Integration with internal CRM (no standard connector) | Python API client that speaks to your CRM |
| Structured PDF extraction for your own layout | Python with pdfplumber for given contract structures |
| Custom validation (e.g. tax calculations) | JS with your calculation logic |
Management & versioning
- Click a skill in the list to open the file explorer (tree view on the left, editor on the right).
- You can view files, edit them, and save changes back to the package.
- Multiple versions of a skill can be attached to different assistants.
Where to go next
- Assistants + Skills full guide — the detailed walkthrough of upload, chat creation, and package structure
- Code Sandbox — how the execution environment looks in detail
- Assistants overview — the full assistant workflow that skills plug into