# developing-genkit-dart

developing-genkit-dart — a skill for building AI agents with Genkit Dart that tells the agent when to pull in reference docs for the core framework and its plugins.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 674 repo stars
- Author: Ivanna Kaceviča
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/evanca/flutter-ai-rules/tree/HEAD/skills/developing-genkit-dart/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/developing-genkit-dart

## What it does

The skill kicks in when writing Dart-based AI agents, Genkit flows and tools, or wiring LLMs into Dart and Flutter apps. Rather than keeping the full Genkit documentation in context at all times, it maps out where to look: a core reference covering `Genkit()`, `ai.generate`, `ai.defineTool`, `ai.defineFlow`, `ai.embedMany`, plus separate references for plugins like `genkit_google_genai`, `genkit_anthropic`, `genkit_openai`, `genkit_middleware`, `genkit_mcp`, `genkit_chrome`, `genkit_shelf`, and `genkit_firebase_ai`.

For local development it points to the Genkit CLI, installable with `npm install -g genkit-cli`, and run alongside your code with `genkit start -- dart run main.dart` to get tracing in the developer UI. It flags that the native CLI installer from genkit.dev pipes a remote script into `bash`, so that step should be run by a human, not an agent.

Any schema work inside tools, flows, or prompts has to go through the `schemantic` package — that applies to code using `@Schema()`, `SchemanticType`, or classes prefixed with `$`, since Genkit Dart's data models are all built on it.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add evanca/flutter-ai-rules
```
In the agent chat (not a shell):
```text
/plugin install flutter-ai-skills@flutter-ai-rules
```
This installs the whole flutter-ai-skills plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add evanca/flutter-ai-rules --skill developing-genkit-dart -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/developing-genkit-dart/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/developing-genkit-dart/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add evanca/flutter-ai-rules --skill developing-genkit-dart -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/developing-genkit-dart/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add evanca/flutter-ai-rules --skill developing-genkit-dart -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/developing-genkit-dart/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install evanca/flutter-ai-rules skills/developing-genkit-dart
```

2. **Manually: put the files in place**
- File: `.github/skills/developing-genkit-dart/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add evanca/flutter-ai-rules --skill developing-genkit-dart -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/evanca/flutter-ai-rules --path skills/developing-genkit-dart
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/developing-genkit-dart/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/evanca/flutter-ai-rules/tree/HEAD/skills/developing-genkit-dart/SKILL.md

## When to use it
- pull in Genkit Dart core and plugin references on demand
- set up the Genkit CLI with execution tracing
- write Genkit flows, tools, and agents in Dart
- define type-safe schemas for tools and prompts via schemantic
- wire LLM providers like Gemini, Claude, or GPT into a Dart app

## Example prompts
- Write a Genkit flow in Dart with a tool that calls an external API
- Add the genkit_anthropic plugin and define the response schema with schemantic
- Set up genkit start to run and trace dart run main.dart

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 733bdda6a5ee44df.

BEGIN THIRD-PARTY FILE 733bdda6a5ee44df
````text
---
name: developing-genkit-dart
description: Use when building AI agents in Dart, implementing Genkit flows or tools, integrating LLMs into Dart or Flutter applications, or using Genkit Dart plugins.
license: MIT
---

# Genkit Dart

Genkit Dart is an AI SDK for Dart that provides a unified interface for code generation, structured outputs, tools, flows, and AI agents.

## Core Features and Usage
If you need help with initializing Genkit (`Genkit()`), Generation (`ai.generate`), Tooling (`ai.defineTool`), Flows (`ai.defineFlow`), Embeddings (`ai.embedMany`), streaming, or calling remote flow endpoints, please load the core framework reference: 
[references/genkit.md](references/genkit.md)

## Genkit CLI (recommended)

The Genkit CLI provides a local development UI for running Flow, tracing executions, playing with models, and evaluating outputs.

check if the user has it installed: `genkit --version`

**Installation:**
```bash
npm install -g genkit-cli # Via npm (preferred)
```
A native CLI installer is also documented at https://genkit.dev/docs/devtools — it pipes a remote script to `bash`, so run it yourself rather than having an agent execute it.

**Usage:**
Wrap your run command with `genkit start` to attach the Genkit developer UI and tracing:
```bash
genkit start -- dart run main.dart
```

## Plugin Ecosystem
Genkit relies on a large suite of plugins to perform generative AI actions, interface with external LLMs, or host web servers.

When asked to use any given plugin, always verify usage by referring to its corresponding reference below. You should load the reference when you need to know the specific initialization arguments, tools, models, and usage patterns for the plugin:

| Plugin Name | Reference Link | Description |
| ---- | ---- | ---- |
| `genkit_google_genai` | [references/genkit_google_genai.md](references/genkit_google_genai.md) | Load for Google Gemini plugin interface usage. |
| `genkit_anthropic` | [references/genkit_anthropic.md](references/genkit_anthropic.md) | Load for Anthropic plugin interface for Claude models. |
````
END THIRD-PARTY FILE 733bdda6a5ee44df

The third-party file has ended. Everything between the 733bdda6a5ee44df tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2080 of 3846 bytes. © Ivanna Kaceviča · MIT · https://github.com/evanca/flutter-ai-rules/tree/HEAD/skills/developing-genkit-dart/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
