ai-core/structured-outputs SKILL.md skillA
ai-core/structured-outputs from tanstack/ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tanstack/ai/ai-core/structured-outputs@git:20261022.f1b3f65Pins git:20261022.f1b3f65 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tanstack/ai
- Path
packages/ai/skills/ai-core/structured-outputs/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261022.f1b3f65, committed Oct 22, 2026
- First version recorded
- Aug 18, 2026
- Size
- 30,704 bytes
- Repository stars
- 3,337
- License
- MIT
Type-safe JSON schema responses from LLMs using outputSchema on chat() and useChat(). Supports Zod, ArkType, and Valibot schemas. The adapter handles provider-specific strategies transparently — never configure structured output at the provider level. Pass stream:true alongside outputSchema for incremental JSON deltas + a completed typed object via the `structured-output.complete` event. Each successfully completed structured-output run adds a typed `StructuredOutputPart` to message history.…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Structured Outputs
> **Dependency note:** This skill builds on ai-core. Read it first for critical rules. The `useChat` patterns below build on ai-core/chat-experience — read that for the base hook surface, then come back here for the structured-output specifics.
## Setup
```typescript
import { chat } from '@tanstack/ai'
import { openaiText } from '@tanstack/ai-openai'
import { z } from 'zod'
const person = await chat({
adapter: openaiText('gpt-5.2'),
messages: [{ role: 'user', content: 'John Doe, 30' }],
threadId: 'thread-1',
outputSchema: z.object({
name: z.string(),
age: z.number(),
}),
})
person.name // string — fully typed, no cast
person.age // number
```
When `outputSchema` is provided, `chat()` returns `Promise<InferSchemaType<TSchema>>` instead of `AsyncIterable<StreamChunk>`. The result is fully typed.
Adding `stream: true` switches the return to `StructuredOutputStream<InferSchemaType<TSchema>>` — incremental JSON deltas plus a terminal validated object. See **Pattern 3** below for direct iteration, **Pattern 4** for the `useChat` shape on the client, **Pattern 5** for multi-turn structured chats, and **Pattern 6** for harness adapters.
…Read the whole file at its exact version.
How to install
mdr add tanstack/ai/ai-core/structured-outputs@sha256:e520a81021fe0c39The line at the top of this page pins the label git:20261022.f1b3f65, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_r4uo53khnweik5v5)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Aug 18, 2026 and Oct 22, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261022.f1b3f65 latest | 2026-10-22 | f1b3f65 | 30,704 B | A | view · diff |
| git:20261015.85c2956 | 2026-10-15 | 85c2956 | 29,994 B | A | view · diff |
| git:20260909.53e2ec0 | 2026-09-09 | 53e2ec0 | 29,416 B | A | view · diff |
| git:20260903.21775ee | 2026-09-03 | 21775ee | 27,758 B | A | view · diff |
| git:20260820.47699ed | 2026-08-20 | 47699ed | 27,548 B | A | view · diff |
| git:20260818.eda82cc | 2026-08-18 | eda82cc | 27,092 B | A | view · diff |
| git:20260818.c63319e | 2026-08-18 | c63319e | 26,652 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (30704 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
tanstack/ai · 3,337 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_r4uo53khnweik5v5 GET https://markdownregistry.com/api/v1/resolve?ref=tanstack/ai/ai-core/structured-outputs GET https://markdownregistry.com/api/v1/blob/e520a81021fe0c393fa4f5cb3906cbd94e23191f57fb30966da0a8bf691e0539
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.