Platform adaptation guide
Every platform wraps the same skill differently. This guide maps each .aiskill section to the native concept on all five supported platforms — so a skill you download here behaves consistently everywhere.
ChatGPT GPTs
by OpenAI
| .aiskill section | ChatGPT GPTs equivalent |
|---|
Paste the system prompt into the GPT "Instructions" field and keep the user template as your starter message.
Official ChatGPT GPTs documentation →Claude Code
by Anthropic
| .aiskill section | Claude Code equivalent |
|---|
Save the exported .aiskill JSON as a skill file in your project or paste the system prompt into CLAUDE.md / a slash-command markdown file.
Official Claude Code documentation →Cursor
by Anysphere
| .aiskill section | Cursor equivalent |
|---|
Copy the system prompt into .cursor/rules/*.mdc (or Project Rules in Settings) and reference the user template in your agent prompts.
Official Cursor documentation →Dify
by LangGenius
| .aiskill section | Dify equivalent |
|---|
Create a new Agent/App, paste the system prompt as the system prompt, and register template variables as input fields.
Official Dify documentation →LangGraph
by LangChain
| .aiskill section | LangGraph equivalent |
|---|
Load the JSON config into your graph state: use prompts.system for the system message and prompts.user_template as a runnable template.
Official LangGraph documentation →Choosing a primary platform
- ChatGPT GPTs — best for non-technical teammates; everything lives in the OpenAI UI.
- Claude Code — best for agentic coding tasks that read/write files and run commands.
- Cursor — best for in-editor coding assistance with project-scoped rules.
- Dify — best for product teams assembling chatbots/workflows without code.
- LangGraph — best for engineers building stateful, multi-step agent graphs.