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 skills add DeepKolor/deepkolor-agent-skills --skill ad-creative-agentgit clone --depth 1 https://github.com/DeepKolor/deepkolor-agent-skillsWrote 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/deepkolor/deepkolor-agent-skills/ad-creative-agent)<a href="https://agentmods.dev/skills/deepkolor/deepkolor-agent-skills/ad-creative-agent"><img src="https://agentmods.dev/badge/skills/deepkolor/deepkolor-agent-skills/ad-creative-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/deepkolor/deepkolor-agent-skills/ad-creative-agent"><img src="https://agentmods.dev/badge/skills/deepkolor/deepkolor-agent-skills/ad-creative-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00202 | $0.00605 |
| Opus 5 | $0.00101 | $0.00302 |
| Sonnet 5 | $0.00040 | $0.00121 |
| Haiku 4.5 | $0.00020 | $0.00060 |
Grade A, and why
ad-creative-agent 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 9d 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.
What it actually says
Ad Creative Agent
Lite edition — routing and core rules for agent discovery. Full prompt templates, platform playbooks, and production workflows run on DeepKolor.
Paid-placement ad visuals — social feed/story, display banners, web banners — with on-image headline and CTA.
When to use
See description in frontmatter — the agent loads it at startup for routing.
Workflow
- Draft headline/CTA when the user omits copy; render copy directly in the image.
- Match format to placement (9:16 story, 1:1 feed, 16:9 banner).
- Use image-to-image when a product photo or brand asset must be preserved.
- High contrast and mobile-readable typography.
Defaults
resolution=1K
Tool: create_image_task
{
prompt: string,
scene: "text-to-image" | "image-to-image",
aspectRatio?: string,
imageUrls?: string[],
resolution?: "1K"
}
Available when your agent runtime exposes DeepKolor generation tools. Otherwise use this skill as a prompt-engineering guide and adapt tool names to your stack.
Boundaries
- Paid/off-store acquisition assets only — not marketplace listing or PDP galleries.
- Not for YouTube thumbnails or artistic posters/covers.
- No invented claims, pricing, or certifications.
Output
After generation, reply briefly: what was created, key parameters, and one useful next step. Return a full prompt only when the user explicitly asks.
Full version
Production-grade references (SOPs, templates, platform rules) ship inside DeepKolor — not in this public lite package.
What ships with it
1 file 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.
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.
- 9d ago First seen · 59 lines · 202 tokens per session scan A be4a19e1dad6
ad-creative-agent is a skill published in the GitHub repository DeepKolor/deepkolor-agent-skills (2 stars, last pushed 20d ago), licensed MIT. It adds 202 tokens to every session and 605 once invoked, about $0.0010 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
gpt-image-2-prompt-engine
A structured prompt-writing tool for GPT-Image-2, using reusable JSON templates and a four-step workflow. It is designed for controlled commercial images such as product photos, posters, infographics, brand visuals, UI screenshots, and character designs.
photo-revival
Turn ordinary photos or everyday snapshots into poetic hand-drawn illustrations with large white-paper negative space, vivid localized color, subtle collage accents, and tiny handwritten captions. Use when a user wants a real photo reimagined as an illustration rather than filtered, beautified, or photorealistically…
creative-brief
Use when planning ad creative, social posts, launch videos, product demos, thumbnails, images, carousels, UGC concepts, creator briefs, or campaign assets.
gc-muted-zine-poster-v0-1
Generate Muted Zine Poster v0.1 poetic paper-poster prompts and the matching generated image. Use when the user gives a theme, sentence, object, mood, article idea, photo, or content brief and wants a quiet Japanese/Korean zine-like editorial poster with large negative space, aged paper texture, experimental…
image-to-prompt
Analyze one or more reference images and reconstruct faithful, reusable image-generation prompts in Chinese and English. Use when users want to reverse-engineer, infer, restore, imitate, or write prompts from visual references.
model-aware-image-prompt-engineer
Model-aware image prompt engineering for any agent or image generation workflow. Use when writing, improving, translating, debugging, or evaluating prompts for OpenAI image models, Gemini Nano Banana, Midjourney, FLUX, Qwen-Image, Z-Image, Stable Diffusion, SDXL, Pony, Illustrious, NoobAI, Animagine, HunyuanImage…