Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/juliandickie/creators-studio/create-imagenpx skills add juliandickie/creators-studio --skill create-imagegit clone --depth 1 https://github.com/juliandickie/creators-studioWrote 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.
[](https://agentmods.dev/skills/juliandickie/creators-studio/create-image)<a href="https://agentmods.dev/skills/juliandickie/creators-studio/create-image"><img src="https://agentmods.dev/badge/skills/juliandickie/creators-studio/create-image.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00062 | $0.04762 |
| Opus 5 | $0.00031 | $0.02381 |
| Sonnet 5 | $0.00012 | $0.00952 |
| Haiku 4.5 | $0.00006 | $0.00476 |
Grade A, and why
create-image scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creators Studio -- Creative Director for AI Image Generation
Core Principles
- Creative Director -- NEVER pass raw user text to the API. Always interpret, enhance, and construct an optimized prompt.
- Edit First -- 90% of refinements should use
gemini_edit_imageorgemini_chat, not regeneration. Only regenerate when composition or concept is fundamentally wrong. - Start with Intent, Refine with Specs -- Initial generation uses conceptual prompts. Follow-ups add technical specs via the PEEL strategy (Position, Expression, Environment, Lens). See
references/prompt-engineering.md→ Start with Intent.
Quick Reference
| Command | What it does |
|---|---|
/create-image |
Interactive -- detect intent, craft prompt, generate |
/create-image generate <idea> |
Full Creative Director pipeline |
/create-image edit <path> <instructions> |
Intelligent image editing |
/create-image chat |
Multi-turn visual session (character/style consistent) |
/create-image slides [plan|prompts|generate] |
Slide deck pipeline |
/create-image inspire [category] |
Browse prompt database for ideas |
/create-image batch <idea> [N] |
Generate N variations (default: 3) |
/create-image social <idea> --platforms <list> |
Platform-native image generation (87 sizes × 16 platforms, max-quality upload specs, 4K generation + exact-dim crop, text-rendering by default in v4.1.2+) |
/create-image brand |
Conversational brand guide builder (learn → refine → preview → save) |
/create-image asset [list|show|create|delete] |
Manage persistent character/product/object references |
/create-image reverse <image-path> |
Analyze image → extract 5-Component Formula prompt to recreate it |
/create-image book --preset <name> [--tier quick|standard|comprehensive] |
Generate visual brand book (markdown + pptx + html) |
/create-image setup |
Guided Google AI API key setup |
/create-image setup replicate |
Guided Replicate token setup (optional fallback) |
/create-image status |
Check version, installation, and API key status |
/create-image update |
Pull latest version from GitHub |
/create-image preset [list|create|show|delete] |
Manage brand/style presets |
/create-image cost [summary|today|estimate] |
View cost tracking and estimates |
/create-image formats <path> [--formats] [--sizes] |
Convert image to multiple formats/sizes |
/create-image history [list|show|export|sessions] |
View session generation history and export gallery |
/create-image ab-test <idea> [--count N] |
Generate Literal/Creative/Premium variations and track preferences |
/create-image deck --images DIR --output PATH |
Assemble slide images into editable .pptx with brand styling |
/create-image analytics [--format html|json] [--days 30] |
Usage analytics dashboard (cost trends, domain usage, quota) |
/create-image content <idea> --outputs hero,social,email |
Multi-modal content pipeline from a single idea |
/create-image vectorize <image> |
v4.1.0 Convert raster image (PNG/JPG/WEBP) to scalable SVG via Recraft Vectorize ($0.01/call) |
What ships with it
53 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.
- presets/corporate-professional.json 1.7 KB
- presets/creative-agency.json 1.7 KB
- presets/education-friendly.json 1.7 KB
- presets/fashion-editorial.json 1.8 KB
- presets/fitness-energy.json 1.7 KB
- presets/food-lifestyle.json 1.7 KB
- presets/healthcare-clinical.json 1.6 KB
- presets/luxury-dark.json 1.7 KB
- presets/organic-natural.json 1.7 KB
- presets/real-estate-luxury.json 1.8 KB
- presets/startup-bold.json 1.7 KB
- presets/tech-saas.json 1.6 KB
- references/ab-testing.md 2.2 KB
- references/analytics.md 1.7 KB
- references/asset-registry.md 3.7 KB
- references/brand-book.md 3.3 KB
- references/brand-builder.md 6.1 KB
- references/content-pipeline.md 2.7 KB
- references/cost-tracking.md 1.5 KB
- references/deck-builder.md 2.7 KB
- references/gemini-models.md 13 KB
- references/mcp-tools.md 5.6 KB
- references/multi-format.md 2.1 KB
- references/post-processing.md 5.1 KB
- references/presets.md 6.3 KB
- references/prompt-engineering.md 48 KB
- references/replicate.md 4.1 KB
- references/reverse-prompt.md 5.7 KB
- references/session-history.md 2.1 KB
- references/setup.md 6.1 KB
- references/social-platforms.md 15 KB
- references/vectorize.md 7.4 KB
- scripts/abtester.py 13 KB runs code
- scripts/analytics.py 19 KB runs code
- scripts/assets.py 8.0 KB runs code
- scripts/batch.py 3.1 KB runs code
- scripts/brandbook.py 41 KB runs code
- scripts/content_pipeline.py 15 KB runs code
- scripts/cost_tracker.py 22 KB runs code
- scripts/deckbuilder.py 20 KB runs code
- scripts/edit.py 6.1 KB runs code
- scripts/generate.py 12 KB runs code
- scripts/history.py 9.0 KB runs code
- scripts/multiformat.py 11 KB runs code
- scripts/pantone_lookup.py 11 KB runs code
- scripts/presets.py 7.3 KB runs code
- scripts/replicate_edit.py 9.2 KB runs code
- scripts/replicate_generate.py 11 KB runs code
- scripts/setup_mcp.py 11 KB runs code
- scripts/slides.py 13 KB runs code
- scripts/social.py 47 KB runs code
- scripts/validate_setup.py 8.5 KB runs code
- scripts/vectorize.py 9.6 KB runs code
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.
- 5d ago First seen · 318 lines · 62 tokens per session scan A 94fd94ae98eb
create-image is a skill published in the GitHub repository juliandickie/creators-studio (2 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 4,762 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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…
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…
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…
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…
ai-hive-simulate-ali-abdaal
当用户搜索用AI模拟Ali Abdaal、AI模拟Ali Abdaal、Ali AbdaalAI模拟、Ali Abdaal数字人、Ali AbdaalAI分身、Ali Abdaal内容风格、Ali Abdaal选题、Ali Abdaal文案、Ali Abdaal短视频、Ali Abdaal知识库、Ali Abdaal思想顾问、Ali Abdaal战略顾问，或希望借助 AI 研究Ali Abdaal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…
ai-hive-simulate-aravind-srinivas
当用户搜索用AI模拟Aravind Srinivas、AI模拟Aravind Srinivas、Aravind SrinivasAI模拟、Aravind Srinivas数字人、Aravind SrinivasAI分身、Aravind Srinivas内容风格、Aravind Srinivas选题、Aravind Srinivas文案、Aravind Srinivas短视频、Aravind Srinivas知识库、Aravind Srinivas思想顾问、Aravind Srinivas战略顾问，或希望借助 AI 研究Aravind Srinivas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…