Imagen
sanjay3290/ai-skills
Generate images using Google Gemini's image generation capabilities.
Generate and iterate images in Cursor using the built-in image model and strong prompts.
Install Cursor Image Generation
$ npx skills add tmcfarlane/oh-my-cursor --skill cursor-image-generation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tmcfarlane/oh-my-cursor cursor-image-generation --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/tmcfarlane/oh-my-cursor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cursor-image-generation .claude/skills/cursor-image-generation && 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 "cursor-image-generation" agent skill from https://github.com/tmcfarlane/oh-my-cursor/tree/main/skills/cursor-image-generation into .claude/skills/cursor-image-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cursor-image-generation", 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/tmcfarlane/oh-my-cursor/tree/main/skills/cursor-image-generationType 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 tmcfarlane/oh-my-cursor --skill cursor-image-generation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tmcfarlane/oh-my-cursor cursor-image-generation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursor.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cursor-image-generation .agents/skills/cursor-image-generation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cursor-image-generation" agent skill from https://github.com/tmcfarlane/oh-my-cursor/tree/main/skills/cursor-image-generation into .agents/skills/cursor-image-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cursor-image-generation", 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 tmcfarlane/oh-my-cursor --skill cursor-image-generation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tmcfarlane/oh-my-cursor cursor-image-generation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursor.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cursor-image-generation .cursor/skills/cursor-image-generation && 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 "cursor-image-generation" agent skill from https://github.com/tmcfarlane/oh-my-cursor/tree/main/skills/cursor-image-generation into .cursor/skills/cursor-image-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cursor-image-generation", 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/tmcfarlane/oh-my-cursor.git --path skills/cursor-image-generation--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 tmcfarlane/oh-my-cursor --skill cursor-image-generation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tmcfarlane/oh-my-cursor cursor-image-generation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursor.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cursor-image-generation .gemini/skills/cursor-image-generation && 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 "cursor-image-generation" agent skill from https://github.com/tmcfarlane/oh-my-cursor/tree/main/skills/cursor-image-generation into .gemini/skills/cursor-image-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cursor-image-generation", 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 tmcfarlane/oh-my-cursor cursor-image-generationInstalls 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 tmcfarlane/oh-my-cursor --skill cursor-image-generation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursor.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cursor-image-generation .github/skills/cursor-image-generation && 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 "cursor-image-generation" agent skill from https://github.com/tmcfarlane/oh-my-cursor/tree/main/skills/cursor-image-generation into .github/skills/cursor-image-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cursor-image-generation", 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 tmcfarlane/oh-my-cursor --skill cursor-image-generation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tmcfarlane/oh-my-cursor cursor-image-generation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursor.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cursor-image-generation .opencode/skills/cursor-image-generation && 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 "cursor-image-generation" agent skill from https://github.com/tmcfarlane/oh-my-cursor/tree/main/skills/cursor-image-generation into .opencode/skills/cursor-image-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cursor-image-generation", 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
cursor-image-generation- GitHub stars
- 110
- Token cost
- ~1.8k tokens
- SKILL.md length
- 758 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate and iterate images in Cursor using the built-in image model and strong prompts.
- Works in 3 steps: Infer or ask for missing constraints… → Rewrite the ask into one structured… → Call GenerateImage with the rewritten…
- Marketing visuals
- SKILL.md covers Rough prompt in, strong prompt…, When to use this skill, Core principles (Nano Banana /… and Anti-patterns, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Cursor Image Generation is an agent skill from tmcfarlane/oh-my-cursor. Generate and iterate images in Cursor using the built-in image model and strong prompts. Use when creating icons, illustrations, UI mockups, diagrams, marketing visuals, or any raster asset from a text description or reference image.
Its SKILL.md is about 1.8k 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, Icons and illustration and UI design. It works with Google Gemini. The repository describes itself as: Like “oh-my-opencode”, but for Cursor IDE. Multi-agent orchestration, natively, using nothing but a few config files. The licence is MIT.
When your agent uses it
- Marketing visuals
- Any raster asset from a text description
- Reference image
Example prompts
- “/cursor-image-generation”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Infer or ask for missing constraints (medium, aspect ratio, style, brand colors, text to render).
- Rewrite the ask into one structured prompt (or a tight second pass) using the principles below.
- Call GenerateImage with the rewritten prompt only.
What it can do on your machine
Read from SKILL.md and the folder at commit 5bad458. 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):
blog.googlecloud.google.comdeepmind.google
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
Cursor Image Generation loads about 1.8k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 758 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 tmcfarlane/oh-my-cursor at commit 5bad458, republished under its MIT licence (© tmcfarlane). 758 words, ~1,762 tokens.
Download SKILL.mdSave it as
.claude/skills/cursor-image-generation/SKILL.md (or your agent's skills folder).- name
- cursor-image-generation
- description
- Generate and iterate images in Cursor using the built-in image model and strong prompts. Use when creating icons, illustrations, UI mockups, diagrams, marketing visuals, or any raster asset from a text description or reference image.
- metadata.author
- oh-my-cursor
- metadata.version
- 1.0.0
Cursor image generation (Nano Banana Pro)
Generate images in the Cursor agent using the GenerateImage tool. Image generation is backed by Google Nano Banana Pro. Previews are saved under assets/ by default unless you specify otherwise.
This skill is about prompting and workflow, not about replacing Figma or vector code (use other skills for those).
Rough prompt in, strong prompt out
The user may give a short or vague request (“a hero for the login page”, “cyberpunk icon”). Do not pass that string raw to GenerateImage when it lacks the layers this skill describes. Instead:
- Infer or ask for missing constraints (medium, aspect ratio, style, brand colors, text to render).
- Rewrite the ask into one structured prompt (or a tight second pass) using the principles below.
- Call GenerateImage with the rewritten prompt only.
The skill is the contract: the agent’s job is to expand and sharpen the user’s intent before generation, then iterate with deltas.
When to use this skill
- User asks for an image, icon, hero visual, diagram look, mockup still, or iteration on an existing generated image.
- You need text in the image (titles, labels, buttons in a mockup).
- User uploads a reference image and wants a variation or edit-style direction.
Core principles (Nano Banana / Gemini image family)
The bullets below are a condensed synthesis of common guidance for Nano Banana Pro / Gemini image models — not verbatim quotes. For authoritative wording and edge cases, use the References below.
They align with the spirit of Google’s public guides (prompt tips, Google Cloud guide, DeepMind prompt guide):
- Brief a human artist — Use clear, grammatical sentences. Avoid keyword soup (
"cyber, 4k, hdr, epic") unless you deliberately want a tag-like aesthetic. - Layer the description — Subject → action/pose → environment → camera (wide shot, isometric, macro) → lighting (soft window light, neon rim, overcast) → materials (brushed aluminum, matte paper, glass) → style (editorial photo, flat illustration, low-poly 3D render).
- Text in images — Put exact wording in double quotes and specify typography feel (e.g.
"bold geometric sans","narrow serif for headlines"). Ask for legibility and high contrast if the text is important. - Aspect ratio and framing — State orientation (square, 16:9 landscape, 9:16 story) and safe margins if the asset will be cropped (e.g. app icon: centered subject, padding).
- Edit, don't always re-roll — If the image is roughly right, ask for specific changes (
"change the background to warm beige","make the logo 20% larger","remove the extra person on the left") instead of a full new prompt. - Reference images — When the user supplies a reference, describe what to keep (palette, mood, composition) and what to change so the model does not drift.
Show full SKILL.md (317 more words)Show less
Anti-patterns
- Vague superlatives with no visual anchor: “make it more beautiful / premium / modern” — always attach concrete cues (materials, palette, era, reference).
- Contradictory constraints in one shot: “minimalist” + “dense infographic” + “single hero object” — split into steps or iterations.
- Ignoring the use case: icon vs hero vs print — state target size or viewing distance when it matters.
Workflow
- Capture — Accept the user’s brief even if it is one line; note gaps.
- Clarify — Output medium (icon, social, slide, mockup), rough dimensions or aspect ratio, brand colors if any, and must-have vs nice-to-have (ask only when blocking).
- Rewrite — Produce the full prompt using the layering order above (this is the “good practices” step).
- Generate — Call GenerateImage with the rewritten description. Prefer saving to
assets/with a descriptive filename (e.g.assets/hero-spring-campaign.png). - Iterate — If close: issue a delta prompt; if wrong: adjust the layer that failed (camera, lighting, style) before scrapping everything.
- Report — Return file path(s), the final prompt (or summary), and optional next iterations.
Prompting patterns (copy and adapt)
Square brackets [like-this] mark placeholders to fill in. Double quotes "..." mark exact text the model should render in the image.
App icon (square, legible at small size)
Square app icon, centered symbol of [subject], flat vector style with subtle depth, limited palette [colors], 10% safe margin from edges, no tiny text, crisp edges, high contrast on [background tone].UI mockup still (marketing)
Photorealistic product screenshot of a [mobile/web] app, [screen name] view, centered device, soft studio lighting, neutral background, clean sans UI. Render the following text exactly: headline "[headline text]", button label "[CTA text]". Modern SaaS aesthetic.Illustration (not photo)
Editorial illustration of [subject], [mood], limited palette [colors], visible brush texture or clean vector shapes (pick one), generous whitespace, no photorealistic faces unless requested.Diagram / concept
Isometric diagram of [system], simple shapes, light grid, high contrast lines, no clutter, presentation slide style. Label the zones exactly: "[zone A label]", "[zone B label]".Examples: weak vs stronger
| Weak | Stronger |
|---|---|
"A nice logo for my app" | Minimal wordmark for a productivity app, lowercase sans-serif feel, single accent color #2563EB on white, generous letter-spacing, no icon, horizontal logo lockup. |
"Cyberpunk city" | Wide 16:9 cinematic shot of a rainy cyberpunk street at night, neon reflections on wet asphalt, single vanishing point, shallow depth of field, no readable text, teal and magenta accents. |
"Fix the image" | Keep the same subject and composition; change only the background to soft gradient from #0f172a to #1e293b; leave lighting on the subject unchanged. |
References
© tmcfarlane, 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/cursor-image-generation of tmcfarlane/oh-my-cursor.
Open the folder on GitHubat commit 5bad458
Compare with similar skills
Cursor Image Generation 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 |
|---|---|---|---|---|---|---|
| Cursor Image Generation this skilltmcfarlane/oh-my-cursor | 110 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Imagensanjay3290/ai-skills | 431 | 7 repos | ~657 | Automated safety check: Pass | Apache-2.0 | |
| Sf Diagram NanobananaproJaganpro/sf-skills | 424 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Imagennexu-io/open-design | 100k | — | ~279 | Automated safety check: Pass | Apache-2.0 | |
| Nano Bananakkoppenhaver/cc-nano-banana | 378 | 1 repos | ~1.4k | Automated safety check: Pass | MIT | |
| FigureMuuuun/luxas | 1.2k | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Sf Diagram Nanobananapro
Jaganpro/sf-skills
AI-powered image generation for Salesforce visuals via Nano Banana Pro.
Imagen
nexu-io/open-design
Generate images using Google Gemini's image generation API for UI mockups, icons, illustrations, and visual assets.
Nano Banana
kkoppenhaver/cc-nano-banana
REQUIRED for all image generation requests. An agent skill from kkoppenhaver/cc-nano-banana.
Figure
Muuuun/luxas
Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly).
AI Multimodal
Microck/ordinary-claude-skills
Process and generate multimedia content using Google Gemini API.
More from tmcfarlane/oh-my-cursor
All 14 skills in this repoDocs Write
tmcfarlane/oh-my-cursor
Write documentation following Metabase's conversational, clear, and user-focused style.
Debugging
tmcfarlane/oh-my-cursor
Systematic 4-phase debugging with root cause investigation. An agent skill from tmcfarlane/oh-my-cursor.
Documentation Engineer
tmcfarlane/oh-my-cursor
Technical documentation expert for creating clear, comprehensive documentation.
Planning
tmcfarlane/oh-my-cursor
Technical implementation planning and architecture design. An agent skill from tmcfarlane/oh-my-cursor.
Codebase Search
tmcfarlane/oh-my-cursor
Search and navigate large codebases efficiently. An agent skill from tmcfarlane/oh-my-cursor.
Design Patterns Implementation
tmcfarlane/oh-my-cursor
Apply appropriate design patterns (Singleton, Factory, Observer, Strategy, etc.) to solve architectural problems.
Related
Works with
Categories
Questions about Cursor Image Generation
What does Cursor Image Generation do?
Generate and iterate images in Cursor using the built-in image model and strong prompts. Cursor Image Generation is an agent skill from tmcfarlane/oh-my-cursor. Generate and iterate images in Cursor using the built-in image model and strong prompts.
When should I use Cursor Image Generation?
Cursor Image Generation fits situations like: marketing visuals; any raster asset from a text description; reference image.
How do I install Cursor Image Generation in Claude Code?
Run `npx skills add tmcfarlane/oh-my-cursor --skill cursor-image-generation -a claude-code`. Or copy the skill folder (skills/cursor-image-generation in tmcfarlane/oh-my-cursor) into .claude/skills/cursor-image-generation in your project. Claude Code loads it when a task matches its description.
How do I install Cursor Image Generation in Codex?
Run `npx skills add tmcfarlane/oh-my-cursor --skill cursor-image-generation -a codex`. Or copy the skill folder (skills/cursor-image-generation in tmcfarlane/oh-my-cursor) into .agents/skills/cursor-image-generation in your project. Codex loads it when a task matches its description.
Can I use Cursor Image Generation 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 tmcfarlane/oh-my-cursor --skill cursor-image-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cursor-image-generation, .gemini/skills/cursor-image-generation, .github/skills/cursor-image-generation and .opencode/skills/cursor-image-generation in your project.
What does Cursor Image Generation need to run?
SKILL.md names no scripts, command-line tools or credentials: Cursor Image Generation is instructions for the agent only.
Does Cursor Image Generation access the network?
SKILL.md names 3 domains. As links in the text: blog.google, cloud.google.com and deepmind.google. This is read from the text; nothing was executed.
Is Cursor Image Generation 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 Cursor Image Generation use?
Cursor Image Generation 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 Cursor Image Generation use?
About 1.8k tokens (SKILL.md is roughly 7k 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 Cursor Image Generation?
Skills that share tags, products or a category with Cursor Image Generation: Imagen (sanjay3290/ai-skills, 431 stars), Sf Diagram Nanobananapro (Jaganpro/sf-skills, 424 stars), Imagen (nexu-io/open-design, 100k stars) and Nano Banana (kkoppenhaver/cc-nano-banana, 378 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cursor Image Generation?
tmcfarlane (a GitHub user) maintains it in tmcfarlane/oh-my-cursor, which has 110 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on July 2, 2026.
Source: tmcfarlane/oh-my-cursor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.