Skip to main content
skill CX Codex

create-structured-output — Claude Code skill for Vapi

create-structured-output is a Claude Code skill that defines a post-call extraction schema, attaches it to an assistant, and tests it on call recordings.

MIT 154 installs ★ 69 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add VapiAI/skills --skill create-structured-output -a claude-code
Open on GitHub

What create-structured-output does

The skill walks through building a Vapi Structured Output. You start from what should come out of a finished call, write a JSON Schema for it, save the definition, hook it to an assistant and test it on one real recording. It is a procedure, not a set of scripts.

Mode comes first. You can stop at a schema artifact and touch nothing in Vapi, save a reusable definition with POST /structured-output, or try a one-off run using previewEnabled: true. Extraction type is a separate choice: type: "ai" where meaning and categories matter, type: "regex" for literal RE2 matching. Saved names run from 1 to 40 characters.

Nothing gets saved, attached or executed without VAPI_API_KEY on a trusted server. Attachment patches only assistantIds, so unrelated IDs survive, and a backfill takes no more than 100 call IDs in a single request. The skill advises leaving compliancePlan.forceStoreOnHipaaEnabled alone unless the user asks for it.

What it helps with

  • define a post-call extraction schema for call data
  • attach a saved Structured Output to the right assistant
  • test extraction on one real call before a bulk run
  • backfill a new schema over calls that already finished
  • pull typed call results through the API

Example prompts for the agent

  • Draft a schema that pulls the order total and payment method out of a call. Artifact only, do not save anything.
  • Attach that definition to the assistant and leave the other assistantIds untouched.
  • Preview it on one real call with previewEnabled: true and show me the value that comes back.

How to install create-structured-output

1Skills CLI (Vercel)

npx skills add VapiAI/skills --skill create-structured-output -a claude-code

2Manually: put the files in place

~/.claude/skills/create-structured-output/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/create-structured-output/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about create-structured-output

How do I install create-structured-output in Claude Code?

Run npx skills add VapiAI/skills --skill create-structured-output -a claude-code; the skill lands at ~/.claude/skills/create-structured-output/SKILL.md.

What does create-structured-output do?

It guides the whole Vapi Structured Output flow: picking a mode, designing the extraction schema, saving the definition, attaching it to an assistant, previewing and running it over calls, then verifying the result.

What do I need before using it?

A VAPI_API_KEY on a trusted server, since saving definitions, attaching them and reading results all go through it. Internet access is recommended to recheck current Vapi schema fields.

Source text

SKILL.md · MIT
---
name: create-structured-output
description: Design, create, inspect, update, attach, detach, preview, execute, and verify reusable Vapi Structured Outputs through public API or Server SDK workflows. Use for post-call extraction, typed call artifacts, AI-versus-regex extraction, JSON Schema design, backfilling existing calls, or retrieving structured results programmatically.
license: MIT
compatibility: Internet access is recommended for current Vapi schema verification; VAPI_API_KEY is required for saved resources, assistant attachments, call execution, and result retrieval.
metadata:
  author: vapi
  version: "1.0"
---

# Vapi Structured Output Creation

Build the smallest reusable post-call extraction that represents the user's actual downstream contract. Keep definition creation, assistant attachment, execution, and result retrieval separate: success at one stage does not prove the next stage occurred.

## Source and Safety Rules

- Use the configured Vapi documentation MCP when available. Otherwise use current public Vapi API documentation and [API Examples](references/api-examples.md). Revalidate request fields and SDK methods before final implementation.
- Use a private Vapi API key only on a trusted server. Read it from `VAPI_API_KEY`; never print, request in chat, or embed it in source, client-side code, or examples.
- Never invent resource IDs, call IDs, extraction fields, enum values, data-retention requirements, or customer data.
- Do not enable `compliancePlan.forceStoreOnHipaaEnabled` unless the user explicitly requests it and confirms that the output cannot contain PHI or other sensitive data.
- Treat call transcripts, messages, tool results, and extracted values as sensitive customer data. Minimize what is logged or reproduced.

## Procedure

1. Choose the output mode.
   - For a schema, payload, review, or implementation example, return an artifact without calling Vapi. State that nothing was saved, attached, or executed.
   - For a reusable saved definition, use `POST /structured-output` only when the user asks to create or save it and credentials are available.
   - For a one-call experiment that does not need a saved definition, pass a transient `structuredOutput` to `POST /structured-output/run` with `previewEnabled: true`.
   - Treat attachment, detachment, and execution against existing calls as separate requested actions. Do not infer them from creation alone.

2. Define the extraction contract.
   - Identify the downstream consumer, required fields, optional fields, allowed categories, formats, and behavior when evidence is absent or ambiguous.
   - Ask only for missing facts that materially change the schema. State safe assumptions for the rest.
   - Split unrelated outputs when they have different consumers, retention policies, or iteration cycles. Keep one output when the fields form one stable business record.

3. Choose AI or regex.
   - Use `type: "ai"` for meaning, classification, summarization, sentiment, outcome detection, normalization, or facts expressed in varied language.
   - Use `type: "regex"` only for deterministic transcript matching with a stable pattern. Use RE2-compatible syntax and choose a top-level schema type that matches the documented regex result: boolean, string, number/integer, or array.
   - Do not use regex to infer meaning. Do not use AI when a literal, stable pattern is the entire requirement.

4. Design the smallest useful JSON Schema.
   - Include only fields the caller can provide or the call evidence can support.
   - Add concise descriptions that distinguish semantically similar fields.
   - Use `enum` for a closed category set, `format` or `pattern` for externally validated strings, and numeric bounds when the business contract defines them.
   - Mark a field required only when every valid call should produce it. Make conditionally available values optional instead of forcing guesses.
   - Prefer a primitive schema for a single value and an object only for a cohesive record. Avoid deep nesting unless the downstream contract needs it.
   - Validate the schema with a standard JSON Schema validator before sending it.

5. Create, inspect, or update the definition.
   - Keep saved names between 1 and 40 characters.
   - On create, send `name` and `schema`; add `type`, `description`, `regex`, `model`, or `compliancePlan` only when intentional.
   - On inspect, resolve the exact resource with list filters or a verified ID, then use `GET /structured-output/{id}`. Do not guess from a partial name.
   - On update, read the current definition first and send only fields that should change. Use `schemaOverride=true` only when intentionally changing the schema's top-level type; otherwise do not use it to bypass schema safety.
   - Re-fetch after mutation and compare the requested fields. A successful HTTP status without the expected returned state is not verified success.

6. Attach or detach safely.
   - Prefer the saved Structured Output's documented `assistantIds` relationship for attachment. Read its current `assistantIds`, add or remove exactly the resolved assistant ID, and preserve every unrelated ID.
   - Patch only `assistantIds` on the Structured Output for this operation. Re-fetch the Structured Output and assistant; verify the relationship and the assistant's `artifactPlan.structuredOutputIds` when returned.
   - If the implementation instead patches the assistant, first read the assistant and send the complete existing `artifactPlan` with only `structuredOutputIds` changed. Preserve recording, logging, transcript, scorecard, storage, and other artifact settings.
   - Do not claim that creating a definition attached it. Do not claim that detaching deleted it or removed results already stored on past calls.

7. Preview before broad execution.
   - Use `POST /structured-output/run` with one real call ID and `previewEnabled: true`. Supply either `structuredOutputId` or a transient `structuredOutput`, not both.
   - Confirm the selected call contains representative evidence and that the returned value satisfies the schema and business meaning.
   - State that preview does not update the call artifact.
   - If extraction is wrong, simplify the schema or improve descriptions before changing models or custom extraction prompts.

8. Execute or backfill only when requested.
   - Use `previewEnabled: false` or omit it to update call artifacts. Pass no more than the currently documented maximum of 100 call IDs per request.
   - Before a multi-call run, state the exact output, call count, and that existing values for this output may be replaced while other structured-output values remain.
   - Use only call IDs supplied by the user or returned by a verified public API query. Report partial failures by call ID; do not imply an all-or-nothing transaction.

9. Retrieve and verify results.
   - After a normal attached call finishes, allow for post-call processing before checking the call.
   - Retrieve each call with `GET /call/{id}` and read `call.artifact.structuredOutputs[structuredOutputId].result`.
   - Validate the result against the intended schema and inspect representative source evidence before calling it accurate. Schema validity proves shape, not factual correctness.
   - Report separately: definition saved, assistant linked, preview returned, call artifact updated, and result validated. Mention only stages actually verified.

## Error Handling

- On `400`, inspect the response for schema, regex, model, relationship, or run constraints. Correct one unambiguous documented issue and retry once; never repeat an unchanged request.
- On `401` or `403`, stop and report authentication or permission failure.
- On `404`, report the missing Structured Output, assistant, or call and identify the exact unresolved ID.
- On `409`, re-read current state before deciding whether the intended relationship or update already exists.
- On `429` or `5xx`, preserve the request context, report the service condition, and do not claim success.
- If a result is absent, distinguish processing delay, missing attachment, disabled artifact storage, insufficient call evidence, and extraction failure before recommending a change.

## API Implementation Examples

Read [API Examples](references/api-examples.md) when implementation code is needed. Use the official TypeScript or Python Server SDK only after confirming the generated method in its current official reference; use direct REST when SDK syntax is unavailable or unstable.

## Output Contract

Return only the sections relevant to the request:

- Mode: artifact-only, saved definition, relationship change, preview, or artifact-writing run
- Assumptions or blocking questions
- Final schema and Structured Output configuration
- Created or updated resource ID and verified fields, when mutated
- Attachment state and preserved relationships, when changed
- Preview or execution result, affected call IDs, and whether artifacts changed
- Retrieved result plus schema and evidence limitations
- Remaining configuration or validation work

## Public Sources

- [Structured Outputs quickstart](https://docs.vapi.ai/assistants/structured-outputs-quickstart/)
- [Create Structured Output API](https://docs.vapi.ai/api-reference/structured-outputs/structured-output-controller-create)
- [List Structured Outputs API](https://docs.vapi.ai/api-reference/structured-outputs/structured-output-controller-find-all)
- [Get Structured Output API](https://docs.vapi.ai/api-reference/structured-outputs/structured-output-controller-find-one)
- [Update Structured Output API](https://docs.vapi.ai/api-reference/structured-outputs/structured-output-controller-update)
- [Run Structured Output API](https://docs.vapi.ai/api-reference/structured-outputs/structured-output-controller-run)
- [Get Call API](https://docs.vapi.ai/api-reference/calls/get/)
- [Official TypeScript Server SDK reference](https://github.com/VapiAI/server-sdk-typescript/blob/main/reference.md)
- [Official Python Server SDK reference](https://github.com/VapiAI/server-sdk-python/blob/main/reference.md)

© vapi · MIT · VapiAI/skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set10

The whole set →
create-assistant create-assistant is a Claude Code skill for designing and validating Vapi voice assistants. It comes into play when building a phone or web agent and shaping its behavior. CX Codex +1 1,100installs create-phone-number create-phone-number — a skill for working with Vapi phone numbers through the public API: plan, provision, import, route, update and verify. Useful for connecting a voice assistant to calls. CX Codex +1 973installs setup-webhook setup-webhook — a skill for Claude Code that configures server URLs and webhooks to receive real-time events from Vapi. Use it when integrating Vapi into an application or building endpoints for call processing. CX Codex +1 968installs create-tool create-tool helps design, create, and attach tools to Vapi voice assistants through the public API. Supports native telephony controls, external integrations, declarative HTTP requests, and MCP servers. CX Codex +1 958installs create-squad create-squad decides whether a use case needs a multi-assistant Squad or a single assistant, then builds and verifies the Squad through the public Vapi API. CX Codex +1 910installs vapi-bootstrap-framework The vapi-bootstrap-framework skill scaffolds a Vapi voice-agent project from a ROUGH_DRAFT.md draft, generating a Bun + TypeScript structure, scenario registry, language stacks, and bootstrap script. CX Codex +1 314installs vapi-prompt-builder vapi-prompt-builder is a Claude Code skill that creates, refines, and audits Vapi system prompts for voice agents and Squads, including call flows, routing, and handoffs. CX Codex +1 297installs simulations Designs, builds, and executes conversation simulations for Vapi assistants and squads. It maps natural language requirements into realistic multi-turn voice or chat test suites. CX Codex +1 161installs

Project sponsors

Companies that keep this analytics open