Space Image Studio
SpaceZephyr/design-buddy
Generates PNG images for four common needs: Xiaohongshu covers, slide illustrations, charts and article logic diagrams, with twelve visual styles and automatic style suggestions.
Directly generate design-oriented AI images with strong creative direction and prompt engineering.
Install Design Image Studio
$ npx skills add kangarooking/design-image-studio --skill design-image-studio -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kangarooking/design-image-studio design-image-studio --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "design-image-studio" agent skill from https://github.com/kangarooking/design-image-studio/tree/main into .claude/skills/design-image-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-image-studio", 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.
$ npx skills add kangarooking/design-image-studio --skill design-image-studio -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kangarooking/design-image-studio design-image-studio --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "design-image-studio" agent skill from https://github.com/kangarooking/design-image-studio/tree/main into .agents/skills/design-image-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-image-studio", 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 kangarooking/design-image-studio --skill design-image-studio -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kangarooking/design-image-studio design-image-studio --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "design-image-studio" agent skill from https://github.com/kangarooking/design-image-studio/tree/main into .cursor/skills/design-image-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-image-studio", 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.
$ npx skills add kangarooking/design-image-studio --skill design-image-studio -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kangarooking/design-image-studio design-image-studio --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "design-image-studio" agent skill from https://github.com/kangarooking/design-image-studio/tree/main into .gemini/skills/design-image-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-image-studio", 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 kangarooking/design-image-studio design-image-studioInstalls 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 kangarooking/design-image-studio --skill design-image-studio -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "design-image-studio" agent skill from https://github.com/kangarooking/design-image-studio/tree/main into .github/skills/design-image-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-image-studio", 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 kangarooking/design-image-studio --skill design-image-studio -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kangarooking/design-image-studio design-image-studio --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "design-image-studio" agent skill from https://github.com/kangarooking/design-image-studio/tree/main into .opencode/skills/design-image-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "design-image-studio", 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
design-image-studio- GitHub stars
- 102
- Token cost
- ~1.5k tokens
- SKILL.md length
- 630 words
- Files
- 28 (incl. scripts, references, assets)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Directly generate design-oriented AI images with strong creative direction and prompt engineering.
- Works in 10 steps: Classify the request into one of:… → Read the full design system prompt → Read the compiler references → …
- Product visuals
- SKILL.md covers Primary Source of Truth, When to Use, Default Workflow and What Must Be Preserved From…, plus 5 more sections
- Calls python3
What it does
Design Image Studio is an agent skill from kangarooking/design-image-studio. Directly generate design-oriented AI images with strong creative direction and prompt engineering. Use this skill for posters, product visuals, PPT illustrations, infographics, teaching/demo diagrams, campaign key visuals, cover art, or when the user wants design-quality image generation rather than generic AI art. This skill turns a loose brief into a design brief, assembles a structured prompt, routes to the right Volcengine Seedream settings, and can generate the image immediately.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files, including scripts, reference files and assets (for example `README.md`, `references/anti-slop-and-failure-patterns.md` and `references/claude-design-map.md`).
It sits in Media & Creative, covering Image generation, Infographics and Design review and critique. The repository describes itself as: 把模糊视觉需求直接变成可落地生成的高质量设计图. The licence is MIT.
When your agent uses it
- Product visuals
- PPT illustrations
- Teaching/demo diagrams
- Campaign key visuals
Example prompts
- “/design-image-studio”
Requirements
- Python 3
Workflow steps
10 steps, taken from the first numbered list in SKILL.md.
- Classify the request into one of: poster, product, ppt, infographic, teaching, or auto
- Read the full design system prompt
- Read the compiler references
- Read the matching task file, such as references/poster.md
- If the user wants refinement or the first result is weak, also read
- Compile the full design system into a design_reasoning layer
- Condense the reasoning into a compiled_brief
- Translate the compiled brief into the shortest useful image prompt
- Run scripts/design_image.py to generate directly, unless the user explicitly asks for prompt-only output
- Iterate by changing one major variable at a time: direction, hierarchy, palette, lighting, realism, or density
What it can do on your machine
Read from SKILL.md and the folder at commit dc43ec4. 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
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Design Image Studio loads about 1.5k tokens when it runs, and up to ~25k if it reads all its reference files. Until then it costs about 127 tokens; SKILL.md has 630 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); the scripts in this folder are not scanned.
SKILL.md
The full file from kangarooking/design-image-studio at commit dc43ec4, republished under its MIT licence (© kangarooking). 630 words, ~1,506 tokens.
Download SKILL.mdSave it as
.claude/skills/design-image-studio/SKILL.md (or your agent's skills folder). This skill also uses 27 other files; get the full folder from GitHub.- name
- design-image-studio
- description
- Directly generate design-oriented AI images with strong creative direction and prompt engineering. Use this skill for posters, product visuals, PPT illustrations, infographics, teaching/demo diagrams, campaign key visuals, cover art, or when the user wants design-quality image generation rather than generic AI art. This skill turns a loose brief into a design brief, assembles a structured prompt, routes to the right Volcengine Seedream settings, and can generate the image immediately.
Design Image Studio
Generate design-quality images directly. This skill preserves the full Claude design-system prompt as the upstream design brain, then compiles that design logic into a shorter image-model prompt.
Primary Source of Truth
Do not treat references/design-principles.md as the whole design system. It is only an index.
The primary design source is:
references/claude-design-sys-prompt-full.txt
Always read that file first for substantive design work. Then use:
references/claude-design-map.mdreferences/design-compiler.md- the task-specific reference file for the current request
This skill should preserve as much of the original design-system prompt as possible at the reasoning layer, while stripping away HTML/tool-specific noise before handing a prompt to the image model.
When to Use
Use this skill when the user wants any of the following:
- Poster generation
- Product hero images, ad visuals, or e-commerce scenes
- PPT cover art, chapter art, or slide illustrations
- Infographic-style visuals
- Teaching/demo diagrams or explanatory scenes
- Visual concept exploration with stronger art direction than a generic image prompt
Do not use this skill for pixel-accurate UI recreation, editable charts, or layouts that require precise text rendering. For those, generate HTML/SVG/PPT assets instead.
Default Workflow
- Classify the request into one of:
poster,product,ppt,infographic,teaching, orauto - Read the full design system prompt:
references/claude-design-sys-prompt-full.txt
- Read the compiler references:
references/claude-design-map.mdreferences/design-compiler.mdreferences/model-routing.md
- Read the matching task file, such as
references/poster.md - If the user wants refinement or the first result is weak, also read:
references/anti-slop-and-failure-patterns.md
- Compile the full design system into a
design_reasoninglayer:- purpose
- audience
- channel
- context/brand strategy
- visual system
- hierarchy strategy
- safe-zone or text-zone logic
- anti-filler rules
- anti-slop rules
- task-specific design constraints
- Condense the reasoning into a
compiled_brief - Translate the compiled brief into the shortest useful image prompt
- Run
scripts/design_image.pyto generate directly, unless the user explicitly asks for prompt-only output - Iterate by changing one major variable at a time: direction, hierarchy, palette, lighting, realism, or density
What Must Be Preserved From the Full Prompt
These must survive the compilation process:
- Start from purpose, audience, and channel
- Create a coherent visual system up front
- Treat hierarchy and whitespace as design decisions
- Avoid filler content and decorative noise
- Avoid AI-slop tropes
- Respect brand/context when available
- If no context exists, still commit to a strong direction instead of averaging styles
- Prefer multiple directions for ambiguous work, usually
conservative,balanced, andbold
Show full SKILL.md (243 more words)Show less
Primary Command
Use the wrapper script first. It is the opinionated entry point for this skill.
python3 scripts/design_image.py \
--task poster \
--brief "为 AI 训练营生成一张高冲击力招生海报，强调增长、实战和速度" \
--direction balanced \
--aspect 3:4 \
--quality final \
--output training-poster.pngPrompt-Only Mode
If the user only wants prompts, do:
python3 scripts/design_image.py \
--task product \
--brief "高端陶瓷咖啡杯广告图，适合电商首图" \
--prompt-onlyThe wrapper prints:
design_reasoningcompiled_brief- final
prompt
Use those intermediate layers to judge whether the full design-system prompt has actually been preserved.
Task References
references/poster.md— posters, key visuals, coversreferences/product-image.md— product ads, hero shots, e-commerce visualsreferences/ppt-visual.md— slide cover art, chapter visuals, concept illustrationsreferences/infographic.md— infographic-like visuals and structured information compositionsreferences/teaching-demo.md— educational and explanatory diagrams/scenesreferences/claude-design-map.md— which sections of the full design prompt matter for image generationreferences/design-compiler.md— how to compile the full prompt into design reasoning, a compiled brief, and a final image prompt
Execution Notes
- Prefer
Seedream 5.0 liteas the default final model - Use lower-cost draft settings before premium reruns when the direction is still unclear
- Use image-to-image or multi-image fusion when the user provides source materials
- For infographic or teaching visuals, avoid asking the model to render dense, tiny text accurately; prefer text placeholders or low-text compositions
- The wrapper script is not the design brain; it is the compiler between the full design system and the image model
- Do not collapse the full design prompt into a few style adjectives unless the user explicitly wants a minimal prompt
Files
scripts/design_image.py— design compiler and prompt builderscripts/generate.py— bundled Volcengine generation enginereferences/claude-design-sys-prompt-full.txt— full upstream design-system promptreferences/claude-design-map.md— section map for image usereferences/design-compiler.md— compilation workflowreferences/models.md— model and resolution referencereferences/troubleshooting.md— common error handling
© kangarooking, MIT. 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 27 other files (scripts, references, assets) in the repository root of kangarooking/design-image-studio.
- SKILL.md
- .gitignore
- LICENSE
- README.md
- assets/demo-poster.png
- assets/examples/infographic-structure.png
- assets/examples/poster-directions.png
- assets/examples/ppt-visual-directions.png
- assets/examples/product-multi-scene.png
- assets/examples/teaching-rag-flow.png
- references/anti-slop-and-failure-patterns.md
- references/claude-design-map.md
- references/claude-design-sys-prompt-full.txt
- references/design-compiler.md
- references/design-principles.md
- references/infographic.md
- references/model-routing.md
- references/models.md
- … and 10 more
Open the folder on GitHubat commit dc43ec4
Compare with similar skills
Design Image Studio 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 |
|---|---|---|---|---|---|---|
| Design Image Studio this skillkangarooking/design-image-studio | 102 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Space Image StudioSpaceZephyr/design-buddy | 174 | — | ~2k | Automated safety check: Pass | None | |
| Sketch Image Promptokooo5km/Skills4U | 183 | — | ~1.8k | Automated safety check: Pass | MIT | |
| ContentclawLeoYeAI/openclaw-master-skills | 2.2k | — | ~6.8k | Automated safety check: Notes | MIT | |
| Create Explanatory ImageAbilityai/cornelius | 109 | — | ~2.8k | Automated safety check: Notes | MIT | |
| Chart Image Generator for WeChat ArticlesSpaceZephyr/creator-buddy | 1.6k | — | ~1.7k | Automated safety check: Pass | None |
Similar skills
Sketch Image Prompt
okooo5km/Skills4U
Transforms article content or summaries into minimalist hand-drawn style JSON prompts for AI image generation tools.
Contentclaw
LeoYeAI/openclaw-master-skills
Automated content generation engine. An agent skill from LeoYeAI/openclaw-master-skills.
Create Explanatory Image
Abilityai/cornelius
Generate explanatory diagrams and infographics that visually communicate concepts.
Chart Image Generator for WeChat Articles
SpaceZephyr/creator-buddy
Draws chart images such as flowcharts, architecture diagrams, ER diagrams and SWOT boards for WeChat official account articles, in one of six visual styles.
Generate Image
Microck/ordinary-claude-skills
Generate or edit images using AI models (FLUX, Gemini). An agent skill from Microck/ordinary-claude-skills.
Related
Categories
Questions about Design Image Studio
What does Design Image Studio do?
Directly generate design-oriented AI images with strong creative direction and prompt engineering. Design Image Studio is an agent skill from kangarooking/design-image-studio. Directly generate design-oriented AI images with strong creative direction and prompt engineering.
When should I use Design Image Studio?
Design Image Studio fits situations like: product visuals; PPT illustrations; teaching/demo diagrams; campaign key visuals.
How do I install Design Image Studio in Claude Code?
Run `npx skills add kangarooking/design-image-studio --skill design-image-studio -a claude-code`. Or copy the skill folder (the kangarooking/design-image-studio repository) into .claude/skills/design-image-studio in your project. Claude Code loads it when a task matches its description.
How do I install Design Image Studio in Codex?
Run `npx skills add kangarooking/design-image-studio --skill design-image-studio -a codex`. Or copy the skill folder (the kangarooking/design-image-studio repository) into .agents/skills/design-image-studio in your project. Codex loads it when a task matches its description.
Can I use Design Image Studio 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 kangarooking/design-image-studio --skill design-image-studio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-image-studio, .gemini/skills/design-image-studio, .github/skills/design-image-studio and .opencode/skills/design-image-studio in your project.
What does Design Image Studio need to run?
Going by SKILL.md and its folder, Design Image Studio needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Design Image Studio access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Design Image Studio 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Design Image Studio use?
Design Image Studio is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Design Image Studio use?
About 1.5k tokens (SKILL.md is roughly 6k 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 23k tokens, read only when the agent opens those files.
What are the alternatives to Design Image Studio?
Skills that share tags, products or a category with Design Image Studio: Space Image Studio (SpaceZephyr/design-buddy, 174 stars), Sketch Image Prompt (okooo5km/Skills4U, 183 stars), Contentclaw (LeoYeAI/openclaw-master-skills, 2.2k stars) and Create Explanatory Image (Abilityai/cornelius, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Design Image Studio?
kangarooking (a GitHub user) maintains it in kangarooking/design-image-studio, which has 102 GitHub stars. The repository was last updated on April 20, 2026.
Source: kangarooking/design-image-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.