Stable Diffusion with Diffusers
Orchestra-Research/AI-Research-SKILLs
Generates and edits images with Stable Diffusion through Hugging Face Diffusers, covering text-to-image, image-to-image, inpainting, SDXL and custom pipelines.
A skill your agent uses whenever the user asks for a graphical abstract, mechanism illustration, study design schematic, concept explainer, scientific cover art, or any non-data academic image that…
Install Scientific Image Prompting
$ npx skills add Citrus-bit/Anaxa --skill scientific-image-prompting -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Citrus-bit/Anaxa scientific-image-prompting --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/Citrus-bit/Anaxa.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public/scientific-image-prompting .claude/skills/scientific-image-prompting && 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 "scientific-image-prompting" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/scientific-image-prompting into .claude/skills/scientific-image-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-image-prompting", 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/Citrus-bit/Anaxa/tree/main/skills/public/scientific-image-promptingType 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 Citrus-bit/Anaxa --skill scientific-image-prompting -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Citrus-bit/Anaxa scientific-image-prompting --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/public/scientific-image-prompting .agents/skills/scientific-image-prompting && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scientific-image-prompting" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/scientific-image-prompting into .agents/skills/scientific-image-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-image-prompting", 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 Citrus-bit/Anaxa --skill scientific-image-prompting -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Citrus-bit/Anaxa scientific-image-prompting --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/public/scientific-image-prompting .cursor/skills/scientific-image-prompting && 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 "scientific-image-prompting" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/scientific-image-prompting into .cursor/skills/scientific-image-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-image-prompting", 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/Citrus-bit/Anaxa.git --path skills/public/scientific-image-prompting--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 Citrus-bit/Anaxa --skill scientific-image-prompting -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Citrus-bit/Anaxa scientific-image-prompting --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/public/scientific-image-prompting .gemini/skills/scientific-image-prompting && 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 "scientific-image-prompting" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/scientific-image-prompting into .gemini/skills/scientific-image-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-image-prompting", 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 Citrus-bit/Anaxa scientific-image-promptingInstalls 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 Citrus-bit/Anaxa --skill scientific-image-prompting -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/public/scientific-image-prompting .github/skills/scientific-image-prompting && 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 "scientific-image-prompting" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/scientific-image-prompting into .github/skills/scientific-image-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-image-prompting", 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 Citrus-bit/Anaxa --skill scientific-image-prompting -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Citrus-bit/Anaxa scientific-image-prompting --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/public/scientific-image-prompting .opencode/skills/scientific-image-prompting && 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 "scientific-image-prompting" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/scientific-image-prompting into .opencode/skills/scientific-image-prompting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-image-prompting", 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
scientific-image-prompting- GitHub stars
- 120
- Token cost
- ~1.4k tokens
- SKILL.md length
- 474 words
- Files
- 1
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses whenever the user asks for a graphical abstract, mechanism illustration, study design schematic, concept explainer, scientific cover art, or any non-data academic image that…
- The user asks for a graphical abstract
- SKILL.md covers Purpose, Hard Routing Rule, Allowed Figure Types and Prompt Contract, plus 6 more sections
- Calls python
- Mechanism illustration
What it does
Scientific Image Prompting is an agent skill from Citrus-bit/Anaxa. Use this skill whenever the user asks for a graphical abstract, mechanism illustration, study design schematic, concept explainer, scientific cover art, or any non-data academic image that may appear in a paper, report, poster, or slides. Always use this skill before image-generation for scientific illustrations. Do not use it for real data figures such as ROC curves, heatmaps, volcano plots, UMAPs, bar charts, or any plot that should come from validated data.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Image generation, Experimental design and Tutoring and explanations. It works with Python. The repository describes itself as: Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。 The licence is MIT.
When your agent uses it
- The user asks for a graphical abstract
- Mechanism illustration
- Study design schematic
- Concept explainer
Example prompts
- “/scientific-image-prompting”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit d57c708. 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
Shell commands in SKILL.md call:
python
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
Scientific Image Prompting loads about 1.4k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 474 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 Citrus-bit/Anaxa at commit d57c708, republished under its MIT licence (© Citrus-bit). 474 words, ~1,443 tokens.
Download SKILL.mdSave it as
.claude/skills/scientific-image-prompting/SKILL.md (or your agent's skills folder).- name
- scientific-image-prompting
- description
- Use this skill whenever the user asks for a graphical abstract, mechanism illustration, study design schematic, concept explainer, scientific cover art, or any non-data academic image that may appear in a paper, report, poster, or slides. Always use this skill before image-generation for scientific illustrations. Do not use it for real data figures such as ROC curves, heatmaps, volcano plots, UMAPs, bar charts, or any plot that should come from validated data.
Scientific Image Prompting
Purpose
This skill is for scientific illustrations, not data plots.
Use it to turn a research intent into a prompt package that is:
- publication-aware
- visually precise
- traceable
- explicit about what is conceptual vs. measured
Hard Routing Rule
Before writing any prompt, classify the request into exactly one route:
data_figure
- Real experiment or statistical figure
- Examples: ROC, PR, heatmap, volcano, PCA, UMAP, histogram, line chart, confusion matrix
- Action: stop using this skill and route to
experiment-lab,nature-figure, or validated Python/R plotting
deterministic_diagram
- Flowchart, architecture, workflow, study design, pipeline, mechanism path that should be clean and diagrammatic
- Action: prefer
fireworks-tech-graphor another deterministic diagram workflow
ai_scientific_illustration
- Graphical abstract, concept art, mechanism imagination, cover art, non-quantitative scientific explainer
- Action: continue with this skill, then hand off to
image-generation
If the request contains measured values, axes, significance claims, or looks like a result figure, it is not ai_scientific_illustration.
Allowed Figure Types
Use one of these figure_type values:
graphical_abstractmechanism_illustrationworkflow_schematicstudy_designcover_artconcept_explainer
Prompt Contract
Create prompt.json with this contract:
{
"prompt_contract_version": "scientific-image-prompting.v1",
"route": "ai_scientific_illustration",
"figure_type": "graphical_abstract",
"scientific_goal": "What the figure should explain",
"must_include": [
"Required scientific entities, stages, organs, cells, devices, molecules, or scene elements"
],
"must_not_invent": [
"Any measured result, axis, p-value, or unsupported biological / technical claim"
],
"label_strategy": "short labels only | no embedded labels | leave whitespace for post-edit annotation",
"composition": "panel structure, focal path, camera angle, negative space",
"style": "flat vector-like | polished 3D editorial | biomedical infographic | clean concept art",
"lighting": "if applicable",
"color_palette": "3-5 colors with scientific publishing intent",
"reference_requirements": [
"what reference images are needed and why"
],
"prompt": "Final English generation prompt",
"negative_prompt": "What must be excluded",
"technical": {
"aspect_ratio": "16:9",
"image_size": "4K",
"output_mime_type": "image/png",
"scientific_mode": true
}
}Writing Rules
- Always write the final generation prompt in English.
- Chinese may be used only for local explanation to the user.
- Keep the figure conceptual unless the user supplied real measured content to place into a non-plot illustration.
- Prefer white or very light backgrounds for paper-ready figures.
- Minimize embedded text inside the image. If labels are needed, keep them short and publication-like.
- If visual fidelity matters, gather reference images first.
Scientific Guardrails
- Do not fabricate data-like figures.
- Do not generate fake microscopy, fake western blots, fake sequencing plots, fake statistical charts, or fake benchmark panels as if they were results.
- Do not imply that an imagined mechanism has been experimentally validated unless the user explicitly provided that evidence.
- If the figure is conceptual, ensure the downstream deliverables say so.
Show full SKILL.md (173 more words)Show less
Required Deliverables
For scientific illustration requests, prepare these files in outputs:
scientific-illustration-4k.pngprompt.jsonprompt_audit.mdcaption.mdai_disclosure.md
Audit Notes
prompt_audit.md must briefly record:
- chosen route
- chosen
figure_type - why AIGC is appropriate here
- what was intentionally excluded to avoid fake data presentation
- provider/model choice, including whether it came from the active Settings configuration or an explicit override
- size/output target:
4K,PNG
ai_disclosure.md must explicitly state that the image is a conceptual or illustrative figure generated with AI assistance and should not be interpreted as raw experimental evidence.
Handoff to Image Generation
After prompt.json is ready, call image-generation in scientific mode with:
python /mnt/skills/public/image-generation/scripts/generate.py \
--prompt-file /mnt/user-data/outputs/prompt.json \
--output-file /mnt/user-data/outputs/scientific-illustration-4k.png \
--manifest-file /mnt/user-data/outputs/generation_manifest.json \
--aspect-ratio 16:9 \
--scientific-mode \
--image-size 4K \
--output-mime-type image/pngDefault to the active image provider/model configured in Settings. Only add --provider, --model, or --base-url when the user explicitly wants to override the configured provider.
If the user asked for a lower-cost draft, use:
--draft-mode- or explicitly
--model gemini-2.5-flash-image
Final Check
Before delivery, confirm:
- this is not a disguised data figure
- the image is conceptual and paper-appropriate
- prompt, manifest, caption, and disclosure files all exist
- the final output is
PNGand intended as4K
© Citrus-bit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/public/scientific-image-prompting of Citrus-bit/Anaxa.
Open the folder on GitHubat commit d57c708
Compare with similar skills
Scientific Image Prompting 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 |
|---|---|---|---|---|---|---|
| Scientific Image Prompting this skillCitrus-bit/Anaxa | 120 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Stable Diffusion with DiffusersOrchestra-Research/AI-Research-SKILLs | 13k | 5 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Structured Image Generationbytedance/deer-flow | 84k | 4 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Guizang Material Illustrationop7418/guizang-material-illustration | 1.2k | — | ~1.6k | Automated safety check: Pass | None | |
| Orange Line Illustrationorange2ai/orange-line-illustration | 441 | — | ~2.5k | Automated safety check: Pass | Proprietary | |
| Gemini Carouselcharlie947/social-media-skills | 3.8k | — | ~1.7k | Automated safety check: Pass | MIT |
Similar skills
Structured Image Generation
bytedance/deer-flow
Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.
Guizang Material Illustration
op7418/guizang-material-illustration
Generate Guizang-style material illustrations, labeled explanatory visuals, material-styled chart illustrations, and data-first editorial images from articles, notes, product concepts, workplace…
Orange Line Illustration
orange2ai/orange-line-illustration
Generate New Yorker-style minimalist editorial illustrations — thin black ink lines on white, vast negative space, a single orange accent (F97316) — for articles, principles, covers, concept…
Gemini Carousel
charlie947/social-media-skills
Generate a branded slide-by-slide LinkedIn carousel using Gemini.
Gemini Interactions API
Ayuilos/Miffan
A skill your agent uses when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses…
More from Citrus-bit/Anaxa
All 15 skills in this repoNature Figure
Citrus-bit/Anaxa
Submission-grade Nature/high-impact journal figure workflow for Python or R.
Chart Visualization
Citrus-bit/Anaxa
A skill your agent uses whenever the user wants a chart, graph, plot, dashboard visual, or asks to visualize structured numbers, trends, comparisons, proportions, distributions, correlations…
Claude To Medrixflow
Citrus-bit/Anaxa
Interact with MedrixFlow AI agent platform via its HTTP API.
Fireworks Tech Graph
Citrus-bit/Anaxa
A skill your agent uses when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG.
Bootstrap
Citrus-bit/Anaxa
Generate a personalized SOUL.md through a warm, adaptive onboarding conversation.
Deep Research
Citrus-bit/Anaxa
A skill your agent uses for general web research that needs current online information, multiple source angles, and synthesis, when no more specific research skill applies.
Related
Works with
Categories
Questions about Scientific Image Prompting
What does Scientific Image Prompting do?
A skill your agent uses whenever the user asks for a graphical abstract, mechanism illustration, study design schematic, concept explainer, scientific cover art, or any non-data academic image that…. Scientific Image Prompting is an agent skill from Citrus-bit/Anaxa. Use this skill whenever the user asks for a graphical abstract, mechanism illustration, study design schematic, concept explainer, scientific cover art, or any non-data academic image that may appear in a paper, report, poster, or slides.
When should I use Scientific Image Prompting?
Scientific Image Prompting fits situations like: the user asks for a graphical abstract; mechanism illustration; study design schematic; concept explainer.
How do I install Scientific Image Prompting in Claude Code?
Run `npx skills add Citrus-bit/Anaxa --skill scientific-image-prompting -a claude-code`. Or copy the skill folder (skills/public/scientific-image-prompting in Citrus-bit/Anaxa) into .claude/skills/scientific-image-prompting in your project. Claude Code loads it when a task matches its description.
How do I install Scientific Image Prompting in Codex?
Run `npx skills add Citrus-bit/Anaxa --skill scientific-image-prompting -a codex`. Or copy the skill folder (skills/public/scientific-image-prompting in Citrus-bit/Anaxa) into .agents/skills/scientific-image-prompting in your project. Codex loads it when a task matches its description.
Can I use Scientific Image Prompting 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 Citrus-bit/Anaxa --skill scientific-image-prompting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scientific-image-prompting, .gemini/skills/scientific-image-prompting, .github/skills/scientific-image-prompting and .opencode/skills/scientific-image-prompting in your project.
What does Scientific Image Prompting need to run?
Going by SKILL.md and its folder, Scientific Image Prompting needs the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Scientific Image Prompting 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 Scientific Image Prompting 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 Scientific Image Prompting use?
Scientific Image Prompting is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Scientific Image Prompting use?
About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Scientific Image Prompting?
Skills that share tags, products or a category with Scientific Image Prompting: Stable Diffusion with Diffusers (Orchestra-Research/AI-Research-SKILLs, 13k stars), Structured Image Generation (bytedance/deer-flow, 84k stars), Guizang Material Illustration (op7418/guizang-material-illustration, 1.2k stars) and Orange Line Illustration (orange2ai/orange-line-illustration, 441 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Scientific Image Prompting?
Citrus-bit (a GitHub user) maintains it in Citrus-bit/Anaxa, which has 120 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 7, 2026.
Source: Citrus-bit/Anaxa on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.