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 Orkas-AI/Orkas-Awesome-AgentSkills --skill image-designgit clone --depth 1 https://github.com/Orkas-AI/Orkas-Awesome-AgentSkillsWrote 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/orkas-ai/orkas-awesome-agentskills/image-design)<a href="https://agentmods.dev/skills/orkas-ai/orkas-awesome-agentskills/image-design"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/image-design/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/orkas-ai/orkas-awesome-agentskills/image-design"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/image-design.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 | $0.00000 | $0.01238 |
| Opus 5.5 | $0.00000 | $0.00495 |
| Sonnet 5.5 | $0.00000 | $0.00248 |
| Haiku 4.5 | $0.00000 | $0.00124 |
Grade A, and why
image-design 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 1mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Design
When to Use
Use this skill when the user wants to create or edit visual assets and needs a clear plan before execution:
- Posters, covers, banners, avatars, product images, social cards, icons, visual concepts, or image series.
- Prompt writing, style exploration, aspect-ratio selection, composition planning, and visual acceptance criteria.
- Model or tool selection across built-in image tools, Dreamina, Nano Banana / Gemini, ComfyUI, or other providers.
- Reference-image planning for style transfer, character consistency, product consistency, multi-image fusion, or series generation.
- Edit planning for inpainting, outpainting, background removal, restoration, relighting, upscaling, style transfer, or local post-processing.
Do not use this skill to claim that an image was actually generated or edited. If no executable image tool/provider is available, return only the brief, prompt, workflow, and acceptance checklist.
Workflow
- Clarify the visual job:
- final use case, audience, platform, required format, aspect ratio, brand constraints, text needs, source/reference images, and deadline.
- whether the user expects execution now or only a prompt/design plan.
- Convert the request into a creative brief:
- purpose, target viewer, subject, visual hierarchy, mood, style, composition, color, lighting, materials, and constraints.
- Choose the path:
- generate from text when the desired image does not exist yet.
- edit from an existing image when preserving identity, product, layout, or reference detail matters.
- use local deterministic processing for resize, crop, format conversion, compression, EXIF stripping, DPI, or watermarking.
- use review-only when the user asks whether an existing result is good enough.
- Route to an executable provider only when available:
- built-in image generation/editing tool when available in the current session.
dreaminafor Jimeng/Dreamina image or video generation through an already logged-in CLI.nano-bananafor Gemini / Imagen-style generation or editing when credentials and upload consent are available.comfyuionly after its local install/model/workflow safety has been reviewed.
- Write structured prompts:
- SUBJECT, CONTEXT, COMPOSITION, STYLE, LIGHTING, TEXT, TECHNICAL, CONSTRAINTS.
- Keep text inside generated images short. For long text, recommend post-production layout.
- For reference images:
- confirm usage rights and privacy.
- state what each reference should preserve and what may change.
- warn when provider reference-image count, upload policy, or consistency limits are unknown.
- For editing:
- choose the edit type, identify the protected area and edit area, define mask/selection needs, and preserve the original file.
- use non-destructive output paths and stepwise intermediate outputs for multi-step edits.
- End with a review plan:
- prompt adherence, technical quality, composition, target-platform fit, text correctness, safety/copyright/privacy risks, and next iteration.
What ships with it
3 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.
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.
- 1mo ago First seen · 115 lines · 0 tokens per session scan A 4bca1e45313e
image-design is a skill published in the GitHub repository Orkas-AI/Orkas-Awesome-AgentSkills (13 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,238 tokens. 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 2026-08-30.
Other skills, from other repositories
DesignSystemArchitect
Complete design system intelligence — component library design, design tokens, documentation, adoption strategy, governance, versioning, and building a design system that scales with your product.
UserResearchOS
Complete user research intelligence — research planning, interview mastery, usability testing, survey design, Jobs-to-be-Done framework, synthesis, and turning user insights into product decisions.
onboarding-designer
Activates OnboardingDesigner for user and customer onboarding experience design. Use when you need to design a product onboarding flow that minimizes time-to-value, create an in-app onboarding checklist or tour, design a customer onboarding sequence for B2B SaaS, build an email onboarding drip campaign, or analyze…
multi-modal-analyst
Activates MultiModalAnalyst for analyzing images, charts, diagrams, screenshots, and visual documents alongside text. Use when you need to extract data from chart images, analyze UI screenshots for UX issues, interpret architectural diagrams, read scanned documents, analyze product mockups, or process any visual input…
ui-ux-designer
Activates UI-UX-Designer for user experience design, interface critique, and accessibility review. Use when you need user flow mapping and friction identification, wireframe critique and design improvement recommendations, accessibility audit against WCAG 2.1 AA standards, design system component specification, or…
frontend-ui-engineering
Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.