develop-ai-functions-example — Claude Code skill
The develop-ai-functions-example skill helps build and run AI SDK function examples for provider checks, feature demos, bug reproduction, and test fixtures.
Apache-2.0 21 installs ★ 28,120 updated 2026-11-11
npx skills add vercel/ai --skill develop-ai-functions-example -a claude-codeWhat develop-ai-functions-example does
The skill works in examples/ai-functions/src, where examples are grouped by AI SDK function and provider. It covers text and object generation, streaming, ToolLoopAgent, embeddings, images, speech, transcription, reranking, middleware, registries, telemetry, and multi-part examples. The primary entry file is basic.ts, with additional files using descriptive kebab-case names.
Examples use run() from lib/run.ts. The wrapper loads variables from .env and reports detailed API errors. Supporting helpers include print-full-stream.ts for streamed output and save-raw-chunks.ts for fixture data. Run files from examples/ai-functions with pnpm tsx.
Keep provider files inside the function directory. A flat path such as generate-text/openai.ts is explicitly disallowed, so that convention matters when adding providers or reproducing a bug.
What it helps with
- add a basic example for a new AI SDK provider
- demonstrate streaming text or structured output
- reproduce a provider bug in an isolated script
- show a tool call with a typed input schema
- capture streaming chunks for a test fixture
Example prompts for the agent
- Create a new provider example under
examples/ai-functions/src/generate-text/withbasic.tsas the entry file. - Add a streaming tool-call example and run
pnpm tsx src/stream-text/openai/tool-call.ts. - Prepare a response fixture by using the helpers in
examples/ai-functions/lib/.
How to install develop-ai-functions-example
1Skills CLI (Vercel)
npx skills add vercel/ai --skill develop-ai-functions-example -a claude-code2Manually: put the files in place
~/.claude/skills/develop-ai-functions-example/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/develop-ai-functions-example/
1Skills CLI (Vercel)
npx skills add vercel/ai --skill develop-ai-functions-example -a codex2Manually: put the files in place
.agents/skills/develop-ai-functions-example/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add vercel/ai --skill develop-ai-functions-example -a cursor2Manually: put the files in place
.cursor/skills/develop-ai-functions-example/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install vercel/ai skills/develop-ai-functions-example2Manually: put the files in place
.github/skills/develop-ai-functions-example/SKILL.md1Skills CLI (Vercel)
npx skills add vercel/ai --skill develop-ai-functions-example -a gemini-cli2Platform CLI
gemini skills install https://github.com/vercel/ai --path skills/develop-ai-functions-exampleManually: put the files in place
.devin/skills/develop-ai-functions-example/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add vercel/ai --skill develop-ai-functions-example -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about develop-ai-functions-example
How do I install develop-ai-functions-example in Claude Code?
Run npx skills add vercel/ai --skill develop-ai-functions-example -a claude-code. The skill file will be at ~/.claude/skills/develop-ai-functions-example/SKILL.md.
What does develop-ai-functions-example do?
It guides work on AI SDK examples under examples/ai-functions/src, including provider validation, feature demonstrations, bug reproduction, and test fixture creation.
Which AI SDK areas are covered?
The examples include text and object generation, agents, embeddings, image and speech generation, transcription, reranking, middleware, provider registries, telemetry, and complex multi-component cases.
Source text
SKILL.md · Apache-2.0
---
name: develop-ai-functions-example
description: Develop examples for AI SDK functions. Use when creating, running, or modifying examples under examples/ai-functions/src to validate provider support, demonstrate features, or create test fixtures.
metadata:
internal: true
---
## AI Functions Examples
The `examples/ai-functions/` directory contains reusable scripts for validating, testing, and iterating on AI SDK functions across providers. Place examples under `examples/ai-functions/src/<function>/<provider>/`. Reproduction-only scripts belong only in the PR description's **End-to-End Verification** section and must never be committed; see [Bug Reproductions](#bug-reproductions).
## Example Categories
Examples are organized by AI SDK function in `examples/ai-functions/src/`:
| Directory | Purpose |
| ------------------ | ---------------------------------------------------- |
| `generate-text/` | Non-streaming text generation with `generateText()` |
| `stream-text/` | Streaming text generation with `streamText()` |
| `generate-object/` | Structured output generation with `generateObject()` |
| `stream-object/` | Streaming structured output with `streamObject()` |
| `agent/` | `ToolLoopAgent` examples for agentic workflows |
| `embed/` | Single embedding generation with `embed()` |
| `embed-many/` | Batch embedding generation with `embedMany()` |
| `generate-image/` | Image generation with `generateImage()` |
| `generate-speech/` | Text-to-speech with `generateSpeech()` |
| `transcribe/` | Audio transcription with `transcribe()` |
| `rerank/` | Document reranking with `rerank()` |
| `middleware/` | Custom middleware implementations |
| `registry/` | Provider registry setup and usage |
| `telemetry/` | OpenTelemetry integration |
| `complex/` | Multi-component examples (agents, routers) |
| `lib/` | Shared utilities (not examples) |
| `tools/` | Reusable tool definitions |
## File Naming Convention
Group examples by function and provider. Name the entry example `basic.ts` and use descriptive `kebab-case.ts` names for additional examples:
| Pattern | Example | Description |
| --------------------------------------------------- | ------------------------------------------------------ | -------------------------- |
| `<function>/<provider>/basic.ts` | `generate-text/openai/basic.ts` | Basic provider usage |
| `<function>/<provider>/<feature>.ts` | `stream-text/openai/tool-call.ts` | Specific feature |
| `<function>/<provider>/<sub-provider>.ts` | `stream-text/amazon-bedrock/anthropic.ts` | Provider with sub-provider |
| `<function>/<provider>/<sub-provider>-<feature>.ts` | `stream-text/google/vertex-anthropic-cache-control.ts` | Sub-provider with feature |
Do not create flat provider files such as `generate-text/openai.ts`.
## Example Structure
All examples use the `run()` wrapper from `lib/run.ts` which:
- Loads environment variables from `.env`
- Provides error handling with detailed API error logging
### Basic Template
```typescript
import { providerName } from '@ai-sdk/provider-name';
import { generateText } from 'ai';
import { run } from '../../lib/run';
run(async () => {
const result = await generateText({
model: providerName('model-id'),
prompt: 'Your prompt here.',
});
console.log(result.text);
console.log('Token usage:', result.usage);
console.log('Finish reason:', result.finishReason);
});
```
### Streaming Template
```typescript
import { providerName } from '@ai-sdk/provider-name';
import { streamText } from 'ai';
import { printFullStream } from '../../lib/print-full-stream';
import { run } from '../../lib/run';
run(async () => {
const result = streamText({
model: providerName('model-id'),
prompt: 'Your prompt here.',
});
await printFullStream({ result });
});
```
### Tool Calling Template
```typescript
import { providerName } from '@ai-sdk/provider-name';
import { generateText, tool } from 'ai';
import { z } from 'zod';
import { run } from '../../lib/run';
run(async () => {
const result = await generateText({
model: providerName('model-id'),
tools: {
myTool: tool({
description: 'Tool description',
inputSchema: z.object({
param: z.string().describe('Parameter description'),
}),
execute: async ({ param }) => {
return { result: `Processed: ${param}` };
},
}),
},
prompt: 'Use the tool to...',
});
console.log(JSON.stringify(result, null, 2));
});
```
### Structured Output Template
```typescript
import { providerName } from '@ai-sdk/provider-name';
import { generateObject } from 'ai';
import { z } from 'zod';
import { run } from '../../lib/run';
run(async () => {
const result = await generateObject({
model: providerName('model-id'),
schema: z.object({
name: z.string(),
items: z.array(z.string()),
}),
prompt: 'Generate a...',
});
console.log(JSON.stringify(result.object, null, 2));
console.log('Token usage:', result.usage);
});
```
## Running Examples
From the `examples/ai-functions` directory:
```bash
pnpm tsx src/generate-text/openai/basic.ts
pnpm tsx src/stream-text/openai/tool-call.ts
pnpm tsx src/agent/openai/generate.ts
```
## When to Write Examples
Write examples when:
1. **Adding a new provider**: Create basic examples for each supported API (`generateText`, `streamText`, `generateObject`, etc.)
2. **Implementing a new feature**: Demonstrate the feature with at least one provider example
3. **Adding provider-specific options**: Show how to use `providerOptions` for provider-specific settings
4. **Creating test fixtures**: Use examples to generate API response fixtures (see `capture-api-response-test-fixture` skill)
## Bug Reproductions
Follow the [bug-fix workflow in AGENTS.md](../../AGENTS.md#bug-fixes). Use a temporary script outside the checkout to reproduce the failure end-to-end, then rerun it to verify the fix. Build and use the checkout's local packages for both runs. Publish reproduction-only code **only in the PR description's End-to-End Verification section**, in a collapsible `<details>` block with the complete runnable script, commands, and observed before/after results, following `.github/pull_request_template.md`. **Never commit reproduction-only files**, including under `examples/ai-functions` or elsewhere in the repository.
Regression tests remain alongside the affected source files. Reusable examples that demonstrate supported usage (including fixed behavior) belong under `examples/ai-functions/src/<function>/<provider>/`, using the naming conventions above.
## Utility Helpers
The `lib/` directory contains shared utilities:
| File | Purpose |
| ---------------------- | -------------------------------------------------------- |
| `run.ts` | Error-handling wrapper with `.env` loading |
| `print.ts` | Clean object printing (removes undefined values) |
| `print-full-stream.ts` | Colored streaming output for tool calls, reasoning, text |
| `save-raw-chunks.ts` | Save streaming chunks for test fixtures |
| `present-image.ts` | Display images in terminal |
| `save-audio.ts` | Save audio files to disk |
### Using print utilities
```typescript
import { print } from '../lib/print';
// Pretty print objects without undefined values
print('Result:', result);
print('Usage:', result.usage, { depth: 2 });
```
### Using printFullStream
```typescript
import { printFullStream } from '../lib/print-full-stream';
const result = streamText({ ... });
await printFullStream({ result }); // Colored output for text, tool calls, reasoning
```
## Reusable Tools
The `tools/` directory contains reusable tool definitions:
```typescript
import { weatherTool } from '../tools/weather-tool';
const result = await generateText({
model: openai('gpt-4o'),
tools: { weather: weatherTool },
prompt: 'What is the weather in San Francisco?',
});
```
## Best Practices
1. **Keep examples focused**: Each example should demonstrate one feature or use case
2. **Use descriptive prompts**: Make it clear what the example is testing
3. **Handle errors gracefully**: The `run()` wrapper handles this automatically
4. **Use realistic model IDs**: Use actual model IDs that work with the provider
5. **Add comments for complex logic**: Explain non-obvious code patterns
6. **Reuse tools when appropriate**: Use `weatherTool` or create new reusable tools in `tools/`
© vercel · Apache-2.0 · vercel/ai