Design Master
minhnv0807/ai-business-skills
Handles eight kinds of marketing visual requests, from logos and campaign key visuals to infographics and quote graphics, by generating images or writing paste-ready prompts.
Turn a creative request into a production-ready AI image brief, reference plan, node workflow, and model-profile prompt.
Install Direct Image Creation
$ npx skills add openvetta/open-vetta --skill direct-image-creation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openvetta/open-vetta direct-image-creation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/openvetta/open-vetta.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/plugins/presets/content-creation/agent/skills/direct-image-creation .claude/skills/direct-image-creation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "direct-image-creation" agent skill from https://github.com/openvetta/open-vetta/tree/main/packages/plugins/presets/content-creation/agent/skills/direct-image-creation into .claude/skills/direct-image-creation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "direct-image-creation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/openvetta/open-vetta/tree/main/packages/plugins/presets/content-creation/agent/skills/direct-image-creationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add openvetta/open-vetta --skill direct-image-creation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openvetta/open-vetta direct-image-creation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openvetta/open-vetta.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/plugins/presets/content-creation/agent/skills/direct-image-creation .agents/skills/direct-image-creation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "direct-image-creation" agent skill from https://github.com/openvetta/open-vetta/tree/main/packages/plugins/presets/content-creation/agent/skills/direct-image-creation into .agents/skills/direct-image-creation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "direct-image-creation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openvetta/open-vetta --skill direct-image-creation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openvetta/open-vetta direct-image-creation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openvetta/open-vetta.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/plugins/presets/content-creation/agent/skills/direct-image-creation .cursor/skills/direct-image-creation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "direct-image-creation" agent skill from https://github.com/openvetta/open-vetta/tree/main/packages/plugins/presets/content-creation/agent/skills/direct-image-creation into .cursor/skills/direct-image-creation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "direct-image-creation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/openvetta/open-vetta.git --path packages/plugins/presets/content-creation/agent/skills/direct-image-creation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add openvetta/open-vetta --skill direct-image-creation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openvetta/open-vetta direct-image-creation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openvetta/open-vetta.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/plugins/presets/content-creation/agent/skills/direct-image-creation .gemini/skills/direct-image-creation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "direct-image-creation" agent skill from https://github.com/openvetta/open-vetta/tree/main/packages/plugins/presets/content-creation/agent/skills/direct-image-creation into .gemini/skills/direct-image-creation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "direct-image-creation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install openvetta/open-vetta direct-image-creationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add openvetta/open-vetta --skill direct-image-creation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openvetta/open-vetta.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/plugins/presets/content-creation/agent/skills/direct-image-creation .github/skills/direct-image-creation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "direct-image-creation" agent skill from https://github.com/openvetta/open-vetta/tree/main/packages/plugins/presets/content-creation/agent/skills/direct-image-creation into .github/skills/direct-image-creation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "direct-image-creation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openvetta/open-vetta --skill direct-image-creation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openvetta/open-vetta direct-image-creation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openvetta/open-vetta.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/plugins/presets/content-creation/agent/skills/direct-image-creation .opencode/skills/direct-image-creation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "direct-image-creation" agent skill from https://github.com/openvetta/open-vetta/tree/main/packages/plugins/presets/content-creation/agent/skills/direct-image-creation into .opencode/skills/direct-image-creation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "direct-image-creation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
direct-image-creation- GitHub stars
- 291
- Token cost
- ~1.2k tokens
- SKILL.md length
- 323 words
- Files
- 22 (incl. references)
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Turn a creative request into a production-ready AI image brief, reference plan, node workflow, and model-profile prompt.
- Works in 6 steps: Inspect project state, references, and… → If no concrete visual concept exists,… → Classify the request as new generation,… → …
- Surgical editing
- SKILL.md covers Route the task and Brief requirements
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Direct Image Creation is an agent skill from openvetta/open-vetta. Turn a creative request into a production-ready AI image brief, reference plan, node workflow, and model-profile prompt. Use for text-to-image, surgical editing, exact text or infographics, image analysis and style transfer, logos and brand kits, ads and publishing assets, ecommerce listing sets, product/food/fashion/portrait imagery, virtual try-on and identity-preserving effects, interiors and floor plans, UI mockups, character sheets, presentation visuals, social covers and thumbnails, multi-panel grids…
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 23 other files, including reference files (for example `agents/openai.yaml`, `references/brand-and-publishing-recipes.md` and `references/commerce-and-food-patterns.md`).
It sits in Media & Creative, covering Image generation, Comics and storyboards and UI design. The repository describes itself as: Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases. The licence is Apache-2.0.
When your agent uses it
- Surgical editing
- Image analysis and style transfer
- Logos and brand kits
- Ads and publishing assets
Example prompts
- “/direct-image-creation”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Inspect project state, references, and image capabilities.
- If no concrete visual concept exists, invoke $develop-creative-concept before authoring prompts.
- Classify the request as new generation, edit, variation, composition transfer, character/product continuity, or multi-asset set.
- Define the brief and acceptance criteria before creating nodes.
- Generate a small candidate set when direction is uncertain; select before producing expensive derivatives.
- Review the actual output with $review-content-quality and repair the smallest failing dimension.
What it can do on your machine
Read from SKILL.md and the folder at commit b983179. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Direct Image Creation loads about 1.2k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 156 tokens; SKILL.md has 323 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from openvetta/open-vetta at commit b983179, republished under its Apache-2.0 licence (© openvetta). 323 words, ~1,191 tokens.
Download SKILL.mdSave it as
.claude/skills/direct-image-creation/SKILL.md (or your agent's skills folder). This skill also uses 21 other files; get the full folder from GitHub.- name
- direct-image-creation
- description
- Turn a creative request into a production-ready AI image brief, reference plan, node workflow, and model-profile prompt. Use for text-to-image, surgical editing, exact text or infographics, image analysis and style transfer, logos and brand kits, ads and publishing assets, ecommerce listing sets, product/food/fashion/portrait imagery, virtual try-on and identity-preserving effects, interiors and floor plans, UI mockups, character sheets, presentation visuals, social covers and thumbnails, multi-panel grids, storyboards, visual variants, composition changes, or improving an image-generation node.
Direct AI image creation
Use $operate-content-workflow for inspection and mutations. Capabilities are the source of truth for executable models and modes.
Route the task
- Inspect project state, references, and image capabilities.
- If no concrete visual concept exists, invoke
$develop-creative-conceptbefore authoring prompts. - Classify the request as new generation, edit, variation, composition transfer, character/product continuity, or multi-asset set.
- Define the brief and acceptance criteria before creating nodes.
- Generate a small candidate set when direction is uncertain; select before producing expensive derivatives.
- Review the actual output with
$review-content-qualityand repair the smallest failing dimension.
Read only the references needed:
- Any prompt: read references/model-prompt-profiles.md, then references/prompt-framework.md
- Ready-to-fill prompt structures: references/production-prompt-skeletons.md
- Editing or reference continuity: references/editing-and-continuity.md
- Model/mode choice: references/model-routing.md
- Exact text, infographic, diagram, or localization: references/text-and-information-design.md
- Recreate, analyze, or transfer an attached visual: references/visual-decomposition.md
- Sketch, wireframe, floor plan, or 2D/3D translation: references/structural-and-dimensional-control.md
- Grid, collage, contact sheet, comic, or storyboard sheet: references/multi-panel-and-sequential.md
- Slide visual: references/presentation-visuals.md
- Product, character, storyboard, or social patterns: references/task-patterns.md
- Commerce, product, food, or beverage: references/commerce-and-food-patterns.md
- Fashion, portrait, or character design: references/fashion-portrait-and-character-patterns.md
- Poster, illustration, UI mockup, or social asset: references/poster-ui-and-social-patterns.md
- Need to choose a specialized production recipe: references/scenario-routing.md
- Logo, brand system, advertising, brochure, blog, social cover, or thumbnail: references/brand-and-publishing-recipes.md
- Ecommerce listing, product angle set, spatial design, floor plan, or interior visualization: references/commerce-product-and-spatial-recipes.md
- Identity-preserving portrait pack, virtual try-on, color board, collectible, collage, or selfie effect: references/identity-fashion-and-social-effect-recipes.md
- UI redesign, URL-to-design, dense information board, text object, or storyboard layout: references/interface-storyboard-and-layout-recipes.md
- Output review: references/quality-checklist.md
Brief requirements
Record purpose, audience, publishing surface, aspect ratio, subject, action/pose, environment, composition, lighting, palette, medium, references and their roles, immutable details, exclusions, deliverables, and acceptance criteria. Distinguish hard constraints from preferences.
Prefer an explicit visual decision over a pile of adjectives. Make each variation change one named axis such as composition, palette, lens, pose, or rendering medium.
This method is an original Vetta adaptation informed by Generative-Media-Skills (MIT), visual-skills by Serge Shima (CC BY 4.0, https://github.com/smixs/visual-skills), and ViMax (MIT).
© openvetta, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 21 other files (references) in packages/plugins/presets/content-creation/agent/skills/direct-image-creation of openvetta/open-vetta.
- SKILL.md
- agents/openai.yaml
- references/brand-and-publishing-recipes.md
- references/commerce-and-food-patterns.md
- references/commerce-product-and-spatial-recipes.md
- references/editing-and-continuity.md
- references/fashion-portrait-and-character-patterns.md
- references/identity-fashion-and-social-effect-recipes.md
- references/interface-storyboard-and-layout-recipes.md
- references/model-prompt-profiles.md
- references/model-routing.md
- references/multi-panel-and-sequential.md
- references/poster-ui-and-social-patterns.md
- references/presentation-visuals.md
- references/production-prompt-skeletons.md
- references/prompt-framework.md
- references/quality-checklist.md
- references/scenario-routing.md
- references/structural-and-dimensional-control.md
- … and 3 more
Open the folder on GitHubat commit b983179
Compare with similar skills
Direct Image Creation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Direct Image Creation this skillopenvetta/open-vetta | 291 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Design Masterminhnv0807/ai-business-skills | 610 | — | ~4.6k | Automated safety check: Pass | MIT | |
| Image Generationonyx-dot-app/onyx | 32k | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| Ecom Image2buluslan/gpt-image2-ecommerce | 409 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Scroll Promo Site Builderkangarooking/kangarooking-skills | 661 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Brand Design Skillziguishian/brand-design-skill | 152 | — | ~4.4k | Automated safety check: Pass | None |
Similar skills
Image Generation
onyx-dot-app/onyx
Generate or edit raster images (photos, illustrations, textures, sprites, mockups, logos, infographics) using the workspace's configured image-generation provider via onyx-cli image.
Ecom Image2
buluslan/gpt-image2-ecommerce
由 buluslan（公众号：新西楼.AI）研发的开源电商做图 Skill：39 个电商场景模板、Campaign 套图一致性、GPT-Image-2.5 官方双模型路由（Flare/Sunburst）与平台技术预检。通过用户配置的 OpenAI 兼容端点生成图片，或导出 prompt 包手动使用。Trigger whenever the user wants product main…
Scroll Promo Site Builder
kangarooking/kangarooking-skills
Create a scroll-controlled cinematic product website with rich motion (动效网站) from product materials, reference pages or videos, and brand assets.
Brand Design Skill
ziguishian/brand-design-skill
Drive a strict conversational, image-first and image-final brand identity design process.
Carousels
TheCraigHewitt/skills
Turns a piece of Craig's content (an email, a YouTube script, an essay, or pasted text) into a polished image carousel publishable to both LinkedIn and Instagram from one set of 1080x1350 slides.
More from openvetta/open-vetta
All 21 skills in this repoMobile Android Design
openvetta/open-vetta
Master Material Design 3 and Jetpack Compose patterns for building native Android apps.
Publish Ability
openvetta/open-vetta
Publish a skill, scene, MCP server, plugin, or bundle to the Vetta ability marketplace.
Plugin Workbench
openvetta/open-vetta
Create, implement, build, pack, install, reload, and manage Vetta desktop plugins for non-developers.
Create Skill
openvetta/open-vetta
Create or update Vetta-compatible Agent Skills. An agent skill from openvetta/open-vetta.
Mobile UI Design
openvetta/open-vetta
Design mobile-style HTML pages (iOS / Android) for preview in the Mobile UI Preview panel.
Remotion Video
openvetta/open-vetta
Create, modify, and render Remotion React video projects in the current Vetta conversation workspace.
Related
Categories
Questions about Direct Image Creation
What does Direct Image Creation do?
Turn a creative request into a production-ready AI image brief, reference plan, node workflow, and model-profile prompt. Direct Image Creation is an agent skill from openvetta/open-vetta. Turn a creative request into a production-ready AI image brief, reference plan, node workflow, and model-profile prompt.
When should I use Direct Image Creation?
Direct Image Creation fits situations like: surgical editing; image analysis and style transfer; logos and brand kits; ads and publishing assets.
How do I install Direct Image Creation in Claude Code?
Run `npx skills add openvetta/open-vetta --skill direct-image-creation -a claude-code`. Or copy the skill folder (packages/plugins/presets/content-creation/agent/skills/direct-image-creation in openvetta/open-vetta) into .claude/skills/direct-image-creation in your project. Claude Code loads it when a task matches its description.
How do I install Direct Image Creation in Codex?
Run `npx skills add openvetta/open-vetta --skill direct-image-creation -a codex`. Or copy the skill folder (packages/plugins/presets/content-creation/agent/skills/direct-image-creation in openvetta/open-vetta) into .agents/skills/direct-image-creation in your project. Codex loads it when a task matches its description.
Can I use Direct Image Creation in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openvetta/open-vetta --skill direct-image-creation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/direct-image-creation, .gemini/skills/direct-image-creation, .github/skills/direct-image-creation and .opencode/skills/direct-image-creation in your project.
What does Direct Image Creation need to run?
SKILL.md names no scripts, command-line tools or credentials: Direct Image Creation is instructions for the agent only.
Does Direct Image Creation access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Direct Image Creation safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Direct Image Creation use?
Direct Image Creation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Direct Image Creation use?
About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.
What are the alternatives to Direct Image Creation?
Skills that share tags, products or a category with Direct Image Creation: Design Master (minhnv0807/ai-business-skills, 610 stars), Image Generation (onyx-dot-app/onyx, 32k stars), Ecom Image2 (buluslan/gpt-image2-ecommerce, 409 stars) and Scroll Promo Site Builder (kangarooking/kangarooking-skills, 661 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Direct Image Creation?
openvetta (a GitHub organization) maintains it in openvetta/open-vetta, which has 291 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 9, 2026.
Source: openvetta/open-vetta on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.