creative-director

creative-director is a skill for Claude Code, Codex from Createya-ai/Createya-mcp. It costs 121 tokens per session (10,956 once invoked), scanned D, original, MIT.

A creative-direction skill for producing visual content through Createya, using a reference image and controlled variations to keep the main subject consistent.

In plain words
What is it for?
Use it for product photography, photos, videos, and other visual content requests.
Why use it?
It helps turn a broad visual request into a defined image or video concept while keeping approved details consistent across variations.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/.../photo.jpg.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for creative-director

README.md
[![agentmods](https://agentmods.dev/badge/skills/createya-ai/createya-mcp/creative-director.svg)](https://agentmods.dev/skills/createya-ai/createya-mcp/creative-director)
Your own site
<a href="https://agentmods.dev/skills/createya-ai/createya-mcp/creative-director"><img src="https://agentmods.dev/badge/skills/createya-ai/createya-mcp/creative-director.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,956 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.10956
Opus 5 $0.00060 $0.05478
Sonnet 5 $0.00024 $0.02191
Haiku 4.5 $0.00012 $0.01096

Measured 5d ago against content hash 98d5b0f4c3e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade D, and why

creative-director scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

run_model → curl -X POST .../v1/run -d '{"model":"...","input":{...}}' | jq

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/Createya-ai/createya-mcp/main/install.sh | bash -s -- crya_sk_YOUR_KEY

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/Createya-ai/createya-mcp/main/install.sh | bash -s -- crya_sk_YOUR_KEY
plugins/createya-mcp/skills/creative-director/SKILL.md · 832 lines

How it starts

The opening of the file, as written. The whole thing — 832 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creative Director

Setup

If Createya MCP tools (mcp__createya__*) are not available or this skill is not installed, tell the user to run this single command:

curl -fsSL https://raw.githubusercontent.com/Createya-ai/createya-mcp/main/install.sh | bash -s -- crya_sk_YOUR_KEY

Replace crya_sk_YOUR_KEY with their actual API key from https://createya.ai/settings/api-keys

This installs both the MCP server and this skill automatically. Restart Claude Code after running.


Ты — креативный директор. Не ассистент, не форма с вопросами — профессионал который понимает задачу, принимает решения, ведёт к результату. Используешь Createya API для генерации; пресеты и формулы — как профессиональный язык; эталон + вариации — как метод.

ГЛАВНОЕ ПРАВИЛО — консистентность через эталон

Это самое важное. Всегда. Без исключений.

ЭТАЛОН (один кадр, locked) → ОДОБРЕНИЕ юзера → ВАРИАЦИИ от эталона

Эталон — это lock. Из него берётся: внешность модели, одежда, товар, свет, цвет. Все вариации генерируются с start_image_url = <etalon CDN URL>. Никогда не меняй между вариациями: лицо, одежду, товар, материал, основной субъект. Меняй только: ракурс, позу, кадрирование, объектив, локацию (если позволяет сценарий), момент.

Без эталона нет вариаций. Точка.

Открытие сессии

Если вызван без контекста или написано "help" / "что умеешь":

Привет. Я — Creative Director Createya. Могу создать любой визуальный контент: фото, видео, UGC, editorial, personal brand, AI-модели — всё что угодно.

Что хочешь создать?

Всё. Больше ничего не говори. Жди.

Если юзер написал задачу сразу (без /creative-director help) — пропускай приветствие, сразу в работу.

Triage — первый шаг ВСЕГДА

До любого вопроса классифицируй задачу по сигналам в первом сообщении (полный гайд: reference/triage.md):

Режим Сигналы Workflow
still «один кадр», «фото для X», «постер» workflows/single-shot.md
edit «измени», «убери», «помести в» + ЕСТЬ референс workflows/edit-and-iterate.md
series (lookbook) «N образов на модели» workflows/lookbook.md
series (product) «карточка товара», «WB», «hero + ракурсы» workflows/product-cutout-pipeline.md
series (UGC) «UGC», «отзыв», «селфи + продукт» workflows/ugc-ad.md
series (personal brand) «фото для соцсетей», «headshots» workflows/personal-brand.md
series (editorial) «editorial», «fashion shoot», «арт-серия» workflows/editorial-series.md
series (multi-aspect) «один креатив для всех соцсетей» workflows/multi-aspect-ad.md
character «AI-модель», «character sheet», «9 ракурсов» workflows/character-sheet.md
video «видео», «клип», «reels» workflows/cinematic-video.md (пока заглушка — моделей нет)

Read the full file on GitHub · 832 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 832 lines · 121 tokens per session scan D 98d5b0f4c3e4

Subscribe to this mod's changes

creative-director is a skill published in the GitHub repository Createya-ai/Createya-mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 121 tokens to every session and 10,956 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

wavespeed

Generate or edit AI media (image, video, audio, 3D) by calling the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, upscale, or transform a visual asset, generate audio/TTS/music, or produce marketing creatives. Every model on the WaveSpeed platform is one wavespeed run call.

WaveSpeedAI/wavespeed-cli · 79 tokens

ai-hive-simulate-36kr

当用户搜索用AI模拟36氪、AI模拟36氪、36氪AI模拟、36氪数字人、36氪AI分身、36氪内容风格、36氪选题、36氪文案、36氪短视频、36氪知识库、36氪思想顾问、36氪战略顾问,或希望借助 AI 研究36氪公开内容中的AI、科技、产品、数码、工程实践或知识科普方法时使用。本 Skill 面向AI学习者、科技从业者、产品经理、创作者和关注新技术的普通用户,先建立公开来源样本库,再提炼选题母题、受众问题、论证结构、内容节奏和视觉方向,并可把用户有权使用的文章、演讲、课程笔记和资料整理成36氪方法论知识库,以可追溯引用的方式提供战略顾问式分析;也可通过 AI-HIVE…

wubin1836/ai-hive-agent-skills · 304 tokens

ai-hive-simulate-agi-hunt

当用户搜索用AI模拟AGI Hunt、AI模拟AGI Hunt、AGI HuntAI模拟、AGI Hunt数字人、AGI HuntAI分身、AGI Hunt内容风格、AGI Hunt选题、AGI Hunt文案、AGI Hunt短视频、AGI Hunt知识库、AGI Hunt思想顾问、AGI Hunt战略顾问,或希望借助 AI 研究AGI Hunt公开内容中的AI工具、Agent、AI编程、AIGC视觉、内容生产、产品、创业或商业落地方法时使用。本 Skill…

wubin1836/ai-hive-agent-skills · 317 tokens

ai-hive-simulate-ai-dance

当用户搜索用AI模拟AI Dance、AI模拟AI Dance、AI DanceAI模拟、AI Dance数字人、AI DanceAI分身、AI Dance内容风格、AI Dance选题、AI Dance文案、AI Dance短视频、AI Dance知识库、AI Dance思想顾问、AI Dance战略顾问,或希望借助 AI 研究AI Dance公开内容中的AI工具、Agent、AI编程、AIGC视觉、内容生产、产品、创业或商业落地方法时使用。本 Skill…

wubin1836/ai-hive-agent-skills · 300 tokens

ai-hive-simulate-alex-hormozi

当用户搜索用AI模拟Alex Hormozi、AI模拟Alex Hormozi、Alex HormoziAI模拟、Alex Hormozi数字人、Alex HormoziAI分身、Alex Hormozi内容风格、Alex Hormozi选题、Alex Hormozi文案、Alex Hormozi短视频、Alex Hormozi知识库、Alex Hormozi思想顾问、Alex Hormozi战略顾问,或希望借助 AI 研究Alex Hormozi公开内容中的人工智能、科技创业、产品、商业管理或知识传播方法时使用。本 Skill…

wubin1836/ai-hive-agent-skills · 322 tokens

ai-hive-simulate-alexandr-wang

当用户搜索用AI模拟Alexandr Wang、AI模拟Alexandr Wang、Alexandr WangAI模拟、Alexandr Wang数字人、Alexandr WangAI分身、Alexandr Wang内容风格、Alexandr Wang选题、Alexandr Wang文案、Alexandr Wang短视频、Alexandr Wang知识库、Alexandr Wang思想顾问、Alexandr Wang战略顾问,或希望借助 AI 研究Alexandr Wang公开内容中的人工智能、科技创业、产品、商业管理或知识传播方法时使用。本 Skill…

wubin1836/ai-hive-agent-skills · 305 tokens