Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Horizons

ASecurity

Hostinger Horizons API for the AI website builder. Use when creating a website, landing page, blog, or web app from a natural-language prompt, or when getting an editor link to modify an existing Horizons website.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentstypescriptpythonphpbashgitapidocumentation

Works with

cliapi

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill horizons --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Horizons?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Horizons
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-horizons/badge)](https://www.skillsdirectory.com/skills/aicodedecode-horizons)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: horizons
description: Hostinger Horizons API for the AI website builder. Use when creating a website, landing page, blog, or web app from a natural-language prompt, or when getting an editor link to modify an existing Horizons website.
last_updated: "2026-06-12"
doc_source: https://developers.hostinger.com
---

# Hostinger Horizons

Horizons is Hostinger's AI website builder. The API creates a website from a natural-language description and returns a link where the user can preview and edit it. Use it when a user asks to build a website, landing page, blog, or other web application, or to fetch an edit link for an existing Horizons site.

## Table of Contents

- [Core Concepts](#core-concepts)
- [Common Patterns](#common-patterns)
- [API Reference](#api-reference)
- [Best Practices](#best-practices)
- [Troubleshooting](#troubleshooting)
- [References](#references)

## Core Concepts

### Prompt-Driven Creation

You describe the desired site in natural language (the `message`), and Horizons generates it. The create call returns a **website URL and ID immediately**, but generation happens **asynchronously** — the site is built in the background after the call returns.

### Messages

The create request takes a `message` array of message objects. Each has a `type` (currently `text`) and the `text` describing what to build, e.g. *"Create a landing page for a coffee shop with a hero section, menu, and contact form."*

### Editing in the Horizons Interface

Horizons websites can only be modified inside the Horizons web interface. To change an existing site, fetch its edit link with `GET /websites/{websiteId}` and open the returned URL — there is no direct content-editing API.

## Common Patterns

### Create a Website from a Prompt

```bash
curl -X POST "https://developers.hostinger.com/api/horizons/v1/websites" \
  -H "Authorization: Bearer $HOSTINGER_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "message": [
      {
        "type": "text",
        "text": "Create a landing page for a coffee shop with a hero section, menu, and contact form"
      }
    ]
  }'
```

> Returns a website URL and ID right away; the site continues generating asynchronously. Share the URL with the user to watch progress and preview the result.

**Python SDK:**

```python
from hostinger_api import Hostinger

client = Hostinger(api_token="YOUR_API_TOKEN")

site = client.horizons.websites.create(
    message=[{"type": "text", "text": "Create a portfolio site for a photographer"}]
)
print(site.id, site.url)
```

**TypeScript SDK:**

```typescript
import { Hostinger } from "hostinger-api-sdk";

const client = new Hostinger({ apiToken: "YOUR_API_TOKEN" });

const site = await client.horizons.websites.create({
  message: [{ type: "text", text: "Create a portfolio site for a photographer" }],
});
console.log(site.id, site.url);
```

**PHP SDK:**

```php
use Hostinger\Api\HostingerApi;

$client = new HostingerApi('YOUR_API_TOKEN');

$site = $client->horizons->websites->create([
    'message' => [
        ['type' => 'text', 'text' => 'Create a portfolio site for a photographer'],
    ],
]);
echo $site->id . ' ' . $site->url . "\n";
```

### Get an Edit Link for an Existing Website

```bash
curl -X GET "https://developers.hostinger.com/api/horizons/v1/websites/12345" \
  -H "Authorization: Bearer $HOSTINGER_API_TOKEN"
```

> Returns a link to edit the website in the Horizons interface. Use this whenever the user wants to modify, edit, or add features to an existing Horizons site.

## API Reference

### Websites

| Method | Endpoint | Description |
|--------|----------|-------------|
| `POST` | `/api/horizons/v1/websites` | Create a website from a prompt (async generation) |
| `GET` | `/api/horizons/v1/websites/{websiteId}` | Get a Horizons editor link for the website |

### Create Website Body

| Field | Type | Description |
|-------|------|-------------|
| `message` | array | Required. Array of message objects describing the site |
| `message[].type` | string | Message type (currently `text`) |
| `message[].text` | string | The natural-language description of what to build |

## Best Practices

### Prompts
- Be specific about sections, purpose, and tone in the `message` text — more detail yields a closer first result
- One clear description per create call; refine afterwards in the Horizons interface rather than re-creating

### Async Handling
- Treat create as fire-and-forget: surface the returned URL to the user so they can watch generation finish
- Don't expect a fully built site in the create response — only the URL and ID are immediate

### Editing
- Always fetch a fresh edit link via `GET /websites/{websiteId}` rather than caching old URLs

## Troubleshooting

### 401 Unauthorized
- Verify your API token is valid and not expired
- Check the `Authorization: Bearer <token>` header format

### 422 Unprocessable Content
- The `message` array is missing or empty
- A message object is missing `type` or `text`

### Website Not Ready
- Generation is asynchronous — give it time and revisit the returned URL
- The edit link from `GET /websites/{websiteId}` opens the site in the Horizons interface even while it finishes building

## References

- [Hostinger API Documentation](https://developers.hostinger.com)
- [Hostinger API Changelog](https://github.com/hostinger/api/blob/main/CHANGELOG.md)
- [Python SDK](https://github.com/hostinger/api-python-sdk)
- [TypeScript SDK](https://github.com/hostinger/api-typescript-sdk)
- [PHP SDK](https://github.com/hostinger/api-php-sdk)
- [CLI Tool](https://github.com/hostinger/api-cli)

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →