ID

ideogram-sdk-patterns

Provides standardized, type-safe wrappers and retry logic for interacting with the Ideogram API.

Install

mkdir -p .claude/skills/ideogram-sdk-patterns && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7953" && unzip -o skill.zip -d .claude/skills/ideogram-sdk-patterns && rm skill.zip

Installs to .claude/skills/ideogram-sdk-patterns

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Apply production-ready Ideogram API patterns for TypeScript and Python.
71 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Create type-safe client wrappers for REST API
  • Validate API responses using Zod schemas
  • Manage multi-tenant API key isolation
  • Automate image downloading to prevent data loss

How it works

It provides a singleton client wrapper that handles authentication, request retries for transient errors, and runtime response validation to ensure API consistency.

Inputs & outputs

You give it
Prompt string or image path
You get back
Validated JSON response or local file path

When to use ideogram-sdk-patterns

  • Implement Ideogram API integrations
  • Refactor existing SDK usage
  • Establish team coding standards for Ideogram

About this skill

Ideogram SDK Patterns

Overview

Production-ready patterns for Ideogram's REST API. Since Ideogram has no official SDK, these patterns provide type-safe wrappers, retry logic, response validation, and multi-tenant support for the api.ideogram.ai endpoints.

Prerequisites

  • Completed ideogram-install-auth setup
  • Familiarity with async/await and fetch API
  • Understanding of Ideogram response lifecycle (URLs expire)

Instructions

Step 1: Singleton Client with Auto-Download

// src/ideogram/client.ts
import { writeFileSync, mkdirSync } from "fs";
import { join } from "path";

const API_BASE = "https://api.ideogram.ai";

let instance: IdeogramClient | null = null;

export function getIdeogramClient(): IdeogramClient {
  if (!instance) {
    const key = process.env.IDEOGRAM_API_KEY;
    if (!key) throw new Error("IDEOGRAM_API_KEY not set");
    instance = new IdeogramClient(key);
  }
  return instance;
}

export class IdeogramClient {
  constructor(private apiKey: string) {}

  async generate(prompt: string, options: {
    model?: string;
    style_type?: string;
    aspect_ratio?: string;
    negative_prompt?: string;
    magic_prompt_option?: string;
    num_images?: number;
    seed?: number;
  } = {}) {
    const response = await fetch(`${API_BASE}/generate`, {
      method: "POST",
      headers: { "Api-Key": this.apiKey, "Content-Type": "application/json" },
      body: JSON.stringify({
        image_request: {
          prompt,
          model: options.model ?? "V_2",
          style_type: options.style_type ?? "AUTO",
          aspect_ratio: options.aspect_ratio ?? "ASPECT_1_1",
          magic_prompt_option: options.magic_prompt_option ?? "AUTO",
          negative_prompt: options.negative_prompt,
          num_images: options.num_images ?? 1,
          seed: options.seed,
        },
      }),
    });
    return this.handleResponse(response);
  }

  async describe(imagePath: string) {
    const form = new FormData();
    const file = new Blob([await import("fs").then(fs => fs.readFileSync(imagePath))]);
    form.append("image_file", file, "image.png");
    const response = await fetch(`${API_BASE}/describe`, {
      method: "POST",
      headers: { "Api-Key": this.apiKey },
      body: form,
    });
    return this.handleResponse(response);
  }

  async downloadImage(url: string, outputDir: string, filename?: string): Promise<string> {
    mkdirSync(outputDir, { recursive: true });
    const imgResponse = await fetch(url);
    if (!imgResponse.ok) throw new Error(`Download failed: ${imgResponse.status}`);
    const buffer = Buffer.from(await imgResponse.arrayBuffer());
    const outPath = join(outputDir, filename ?? `ideogram-${Date.now()}.png`);
    writeFileSync(outPath, buffer);
    return outPath;
  }

  private async handleResponse(response: Response) {
    if (!response.ok) {
      const body = await response.text();
      throw new IdeogramApiError(response.status, body);
    }
    return response.json();
  }
}

export class IdeogramApiError extends Error {
  constructor(public status: number, public body: string) {
    super(`Ideogram ${status}: ${body}`);
    this.name = "IdeogramApiError";
  }
  get isRateLimited() { return this.status === 429; }
  get isSafetyRejected() { return this.status === 422; }
  get isAuthError() { return this.status === 401; }
}

Step 2: Retry with Exponential Backoff

export async function withRetry<T>(
  operation: () => Promise<T>,
  config = { maxRetries: 3, baseDelayMs: 1000, maxDelayMs: 30000 }
): Promise<T> {
  for (let attempt = 0; attempt <= config.maxRetries; attempt++) {
    try {
      return await operation();
    } catch (err: any) {
      if (attempt === config.maxRetries) throw err;
      // Only retry on 429 (rate limit) or 5xx (server error)
      const status = err.status ?? err.response?.status;
      if (status && status !== 429 && status < 500) throw err;

      const delay = Math.min(
        config.baseDelayMs * Math.pow(2, attempt) + Math.random() * 500,
        config.maxDelayMs
      );
      console.warn(`Ideogram retry ${attempt + 1}/${config.maxRetries} in ${delay.toFixed(0)}ms`);
      await new Promise(r => setTimeout(r, delay));
    }
  }
  throw new Error("Unreachable");
}

// Usage: await withRetry(() => client.generate("a sunset"));

Step 3: Response Validation with Zod

import { z } from "zod";

const ImageResultSchema = z.object({
  url: z.string().url(),
  prompt: z.string(),
  resolution: z.string(),
  is_image_safe: z.boolean(),
  seed: z.number(),
  style_type: z.string().optional(),
});

const GenerateResponseSchema = z.object({
  created: z.string(),
  data: z.array(ImageResultSchema).min(1),
});

export function validateGenerateResponse(raw: unknown) {
  return GenerateResponseSchema.parse(raw);
}

Step 4: Python Client

# ideogram_client.py
import os, requests, hashlib, time
from pathlib import Path

class IdeogramClient:
    BASE_URL = "https://api.ideogram.ai"

    def __init__(self, api_key: str | None = None):
        self.api_key = api_key or os.environ.get("IDEOGRAM_API_KEY", "")
        if not self.api_key:
            raise ValueError("IDEOGRAM_API_KEY required")

    def generate(self, prompt: str, model="V_2", style_type="AUTO",
                 aspect_ratio="ASPECT_1_1", **kwargs) -> dict:
        resp = requests.post(f"{self.BASE_URL}/generate", headers=self._headers(),
            json={"image_request": {"prompt": prompt, "model": model,
                "style_type": style_type, "aspect_ratio": aspect_ratio,
                "magic_prompt_option": kwargs.get("magic_prompt", "AUTO"),
                **{k: v for k, v in kwargs.items() if k != "magic_prompt"}}})
        resp.raise_for_status()
        return resp.json()

    def download(self, url: str, output_dir: str = "./images") -> str:
        Path(output_dir).mkdir(parents=True, exist_ok=True)
        resp = requests.get(url)
        resp.raise_for_status()
        path = f"{output_dir}/ideogram-{int(time.time())}.png"
        Path(path).write_bytes(resp.content)
        return path

    def _headers(self):
        return {"Api-Key": self.api_key, "Content-Type": "application/json"}

Step 5: Multi-Tenant Factory

const tenantClients = new Map<string, IdeogramClient>();

export function getClientForTenant(tenantId: string): IdeogramClient {
  if (!tenantClients.has(tenantId)) {
    const apiKey = getTenantApiKey(tenantId); // from your secret store
    tenantClients.set(tenantId, new IdeogramClient(apiKey));
  }
  return tenantClients.get(tenantId)!;
}

Error Handling

PatternUse CaseBenefit
SingletonShared client across modulesSingle connection, consistent config
Retry wrapperRate limits and transient errorsAutomatic recovery from 429/5xx
Zod validationResponse validationCatches API changes at parse time
Auto-downloadImage persistencePrevents URL expiry data loss
Multi-tenantSaaS platformsPer-customer API key isolation

Output

  • Type-safe client singleton with generate and describe methods
  • Retry logic with exponential backoff and jitter
  • Runtime validation for API responses
  • Auto-download to prevent URL expiration issues

Resources

Next Steps

Apply patterns in ideogram-core-workflow-a for real-world usage.

When not to use it

  • When direct fetch calls are sufficient for simple scripts

Prerequisites

IDEOGRAM_API_KEYZod library for validationFamiliarity with async/await

Limitations

  • Requires manual implementation of retry logic for specific status codes
  • API keys must be managed per tenant

How it compares

Unlike raw fetch requests, this pattern provides built-in error handling for rate limits and type-safe response parsing.

Compared to similar skills

ideogram-sdk-patterns side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
ideogram-sdk-patterns (this skill)027dCautionIntermediate
copilot-sdk74moReviewIntermediate
llm-application-dev34moReviewIntermediate
mcp-builder1363moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

You might also like

copilot-sdk

github

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.

763

llm-application-dev

skillcreatorai

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

323

mcp-builder

anthropics

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

136215

langchain

zechenzhangAGI

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

26138

unit-testing-test-generate

sickn33

Generate comprehensive, maintainable unit tests across languages with strong coverage and edge case focus.

214

generate-subsystem-skills

llama-farm

Generate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation.

17

Search skills

Search the agent skills registry