Model guidesOfficial documentation7 min readModel guides

Set Up FastGPT Plugin Project Skeletons

The FastGPT official @fastgpt-plugin/cli tool automates creation of standardized project skeletons for custom system tools, ensuring compliance with FastG…

Plugin CLI Basics

The FastGPT official @fastgpt-plugin/cli tool automates creation of standardized project skeletons for custom system tools, ensuring compliance with FastGPT plugin development conventions. Two core plugin types are supported: single-tool plugins for individual custom tools, and toolkit plugins for grouped collections of multiple related tools.

Direct Command Project Creation

You can generate a plugin skeleton with a single terminal command, using explicit flags to define project details. For a single-tool plugin, run:

pnpx @fastgpt-plugin/cli create my-tool --type tool --cwd packages/tools

Replace my-tool with your desired plugin directory name. For a toolkit plugin bundling multiple tools, use:

pnpx @fastgpt-plugin/cli create my-tool-suite --type tool-suite --cwd packages/tools

The --type flag specifies the plugin category, accepting either tool for single-tool projects or tool-suite for grouped collections. The --cwd flag sets the working directory for the plugin, commonly packages/tools for standard FastGPT plugin repositories.

Interactive Project Setup

For ad-hoc plugin creation without manual flag entry, run the CLI in interactive mode:

pnpx @fastgpt-plugin/cli create

This prompt will collect required project information step-by-step, eliminating the need to memorize command-line parameters.

Standard Generated File Structure

The CLI creates a complete plugin directory with the following standardized files:

FilePurpose
index.tsPlugin entry, default-exporting defineTool() or defineToolSet().
package.jsonPlugin dependencies and build, build:dev, pack, and test scripts.
tsconfig.jsonTypeScript config.
vitest.config.tsTest config.
README.mdPlugin description.
logo.svgMain plugin icon.

All generated files align with FastGPT’s official development standards, ensuring compatibility and ease of maintenance.

Source: FastGPT official source

Applicability and version scope

Use this page for the documented Model guides scenario. Confirm the FastGPT, dependency, API, and deployment versions in the official source before applying a change.

Safety guardrails

Use [REDACTED_CREDENTIAL] for credentials and private data. Confirm the documented environment and version before review.

Rollback guidance

Restore the prior technical-content authority snapshot. Restore saved configuration and data snapshots, then repeat the smallest verification scenario.