llm-output-schema-cons…
Zod schema constraints that Anthropic rejects or silently ignores when sent as structured-output tool definitions via aiSdk.Output.object(). Use when writing…
Create step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP requests, or LLM calls.
$ npx -y skills add growthxai/output --skill output-dev-step-function --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/output-dev-step-functionContext preview
The summary Claude sees to decide when to auto-load this skill.
Create step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP requests, or LLM calls.
name: output-dev-step-function description: Create step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP requests, or LLM calls. allowed-tools: [Read, Write, Edit]
This skill documents how to create step functions in `steps.ts` for Output SDK workflows. Steps are where all I/O operations happen - HTTP requests, LLM calls, database operations, file system access, etc.
For smaller workflows, use a single `steps.ts` file:
src/workflows/{workflow-name}/
├── workflow.ts
├── steps.ts # All steps in one file
├── types.ts
└── ...For larger workflows with many steps, use a `steps/` folder:
src/workflows/{workflow-name}/
├── workflow.ts
├── steps/ # Steps split into individual files
│ ├── fetch_data.ts
│ ├── process.ts
│ └── validate.ts
├── types.ts
└── ...**Important**: `step()` calls MUST be in files containing 'steps' in the path:
Steps are Temporal activities with strict import rules to ensure deterministic replay.
**Example of WRONG imports:**
// WRONG - steps cannot import other steps
import { otherStep } from '../../shared/steps/other.js'; // ✗
import { anotherStep } from './other_steps.js'; // ✗// CORRECT - Import from @outputai/core
import { step, z, FatalError, ValidationError } from '@outputai/core';
// WRONG - Never import z from zod
import { z } from 'zod';// CORRECT - Use @outputai/http wrapper
import { createKyClient } from '@outputai/http';
// WRONG - Never use axios directly
import axios from 'axios';**Related Skill**: `output-error-http-client`
// CORRECT - Use @outputai/llm wrapper
import { generateText, aiSdk } from '@outputai/llm';
// WRONG - Never call LLM providers directly
import OpenAI from 'openai';All imports MUST use `.js` extension:
// CORRECT
import { InputSchema, OutputSchema } from './types.js';
import { GeminiService } from '../../shared/clients/gemini_client.js';
// WRONG - Missing .js extension
import { InputSchema, OutputSchema } from './types';import { step, z, FatalError, ValidationError } from '@outputai/core';
import { createKyClient } from '@outputai/http';
import { generateText, aiSdk } from '@outputai/llm';
import { StepInputSchema, StepOutputSchema } from './types.js';
export const myStep = step( {
name: 'myStep',
description: 'Description of what this step does',
inputSchema: StepInputSchema,
outputSchema: StepOutputSchema,
fn: async input => {
// Implementation with I/O operations
return { /* output matching outputSchema */ };
}
} );Unique identifier for the step. Use camelCase.
name: 'generateImageIdeas'
Human-readable description of the step's purpose.
description: 'Generate creative infographic prompt ideas using Claude'
Schema for validating step input. Define in `types.ts` and import.
inputSchema: z.object( {
content: z.string(),
numberOfIdeas: z.number()
} )Schema for validating step output. Define in `types.ts` and import.
outputSchema: z.array( z.string() )
The step execution function. This is where I/O operations happen.
fn: async input => {
const result = await someExternalService( input );
return result;
}import { createKyClient } from '@outputai/http';
import { FatalError, ValidationError } from '@outputai/core';
const RETRY_STATUS_CODES = [ 408, 429, 500, 502, 503, 504 ];
const FATAL_STATUS_CODES = [ 401, 403, 404 ];
const client = createKyClient( {
timeout: 30000,
retry: {
limit: 3,
statusCodes: RETRY_STATUS_CODES
},
hooks: {
beforeError: [
( { error } ) => {
const status = error.response?.status;
const message = error.message;
if ( status && FATAL_STATUS_CODES.includes( status ) ) {
throw new FatalError(
`HTTP ${status} error: ${message}. This is a permanent error.`
);
}
throw new ValidationError(
`HTTP request failed: ${message}`
);
}
]
}
} );// GET request
const response = await client.get( 'https://api.example.com/data' );
const data = await response.json();
// POST request with JSON body
const response = await client.post( 'https://api.example.com/submit', {
json: { field: 'value' }
} );
// HEAD request (check URL accessibility)
const response = await client.head( url );
const contentType = respThe open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code — describe what you want, Claude builds it, with all the best practices already in place. One framework.
Repo: growthxai/output
Zod schema constraints that Anthropic rejects or silently ignores when sent as structured-output tool definitions via aiSdk.Output.object(). Use when writing…
Guide to the providerOptions structure in .prompt files — decision tree for where an option goes, common mistakes, per-provider quick reference, and Anthropic…
Implement an Output SDK workflow from a plan document. Use when the user asks to build, implement, or code a workflow from an existing plan, or after…
View and edit encrypted credentials in an Output.ai project. Use when adding secrets, updating API keys, verifying credential values, or retrieving a specific…
Wire encrypted credentials to environment variables using the credential: convention. Use when setting up LLM provider keys (ANTHROPIC_API_KEY, OPENAI_API_KEY)…