Agent skill

AI Image Creator

by evolution-foundation in evolution-foundation/evo-nexus

Generates PNG images through OpenRouter models, with transparent backgrounds and reference-image edits, and describes existing images with multimodal vision.

Custom licenceAuto-check: notesMedia & Creative

Install AI Image Creator

skills CLI
$ npx skills add evolution-foundation/evo-nexus --skill ai-image-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install evolution-foundation/evo-nexus ai-image-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/evolution-foundation/evo-nexus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ai-image-creator .claude/skills/ai-image-creator && rm -rf skills-src

Use ~/.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/

Facts

Skill name
ai-image-creator
GitHub stars
545
Token cost
~5.1k tokens
SKILL.md length
1,824 words
Files
10 (incl. scripts, references)
Skills in repo
117
Repo updated
First seen
Licence
Custom licence

At a glance

Generates PNG images through OpenRouter models, with transparent backgrounds and reference-image edits, and describes existing images with multimodal vision.

  • Works in 8 steps: Write Prompt → 5: Prompt Enhancement (Optional —… → 5b: Output Path Convention → …
  • Generating a PNG icon or illustration for a project
  • SKILL.md covers Model Selection, Instructions, Parameters and Environment Variables, plus 7 more sections
  • Runs Python scripts from its folder; calls uv, magick and brew; needs AI_IMG_CREATOR_CF_TOKEN and AI_IMG_CREATOR_OPENROUTER_KEY

What it does

Images are generated through several models routed via Cloudflare AI Gateway with your own keys, or directly through OpenRouter or Google AI Studio. Saying gemini, riverflow, flux2, seedream or gpt5 selects the matching --model value, with gemini as the default. Long prompts go into workspace/assets/prompts/prompt.txt and short ones inline. The agent is told to write detailed prompts with style, composition, an explicit background and a target size, and optional prompt-pattern reference files load only when a request fits their category.

Flags include -t for a transparent background, -r to edit from a reference image, --analyze to describe or explain an existing image, and --costs for per-project cost tracking, along with aspect ratio and resolution settings. The folder holds generate-image.py and composite-banners.py plus references for the API, setup, platforms and analysis. It needs uv and network access, with keys set in your shell profile.

When your agent uses it

  • Generating a PNG icon or illustration for a project
  • Making an asset with a transparent background
  • Editing an image from a reference picture
  • Describing or analyzing an existing image

Example prompts

  • “Generate a flat-design globe icon with a transparent background for the web app.”
  • “Use flux2 to make a hero image with a warm sunset palette.”
  • “Describe what is in screenshot.png and list any visible text.”
  • “Show the image generation costs for this project.”

Requirements

  • uv, the Python runner
  • Network access
  • Cloudflare AI Gateway variables or direct API keys set in your shell profile
  • Compatibility (from SKILL.md): Requires uv (Python runner) and network access. Environment variables for CF AI Gateway or direct API keys must be configured in shell profile (~/.zshrc on macOS, ~/.bashrc on Linux, or System Environment Variables on Windows).
  • Pre-approved tools (allowed-tools): Bash, Read, Write

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Write Prompt
  2. 5: Prompt Enhancement (Optional — Progressive Disclosure)
  3. 5b: Output Path Convention
  4. 5c: Provider Selection
  5. Run Generation Script
  6. Save Prompt (rename to match image)
  7. Verify Output
  8. Post-Processing (optional)

What it can do on your machine

Read from SKILL.md and the folder at commit 7f5dd76. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • magick
    • brew
    • apt
    • ffmpeg

    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):

    • openrouter.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • AI_IMG_CREATOR_CF_TOKEN
    • AI_IMG_CREATOR_OPENROUTER_KEY
    • AI_IMG_CREATOR_GEMINI_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires uv (Python runner) and network access. Environment variables for CF AI Gateway or direct API keys must be configured in shell profile (~/.zshrc on macOS, ~/.bashrc on Linux, or System Environment Variables on Windows).

    From compatibility in the SKILL.md frontmatter.

Context cost

AI Image Creator loads about 5.1k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 186 tokens; SKILL.md has 1,824 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~186
When it runs · the whole SKILL.md, loaded when a task matches
~5.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~18k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:98
    auto-loads env vars from the workspace `.env`. Choose provider based on available keys:
  • NoteMentions a .env fileSKILL.md:102
    - **Do NOT use `source .env`** — the Python script loads it internally. Just run the command directly.
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,824 words (~5,092 tokens).

“Generate PNG images via multiple AI models, routed through Cloudflare AI Gateway BYOK or directly via OpenRouter/Google AI Studio.”

— opening of SKILL.md by evolution-foundation, Custom licence
name
ai-image-creator
allowed-tools
Bash, Read, Write
compatibility
Requires uv (Python runner) and network access. Environment variables for CF AI Gateway or direct API keys must be configured in shell profile (~/.zshrc on macOS, ~/.bashrc on Linux, or System Environment Variables on Windows).
metadata.tags
image-generation, ai, openrouter, cloudflare, gemini, flux2, riverflow, seedream, gpt5

Read the full SKILL.md on GitHub

Files

SKILL.md and 9 other files (scripts, references) in .claude/skills/ai-image-creator of evolution-foundation/evo-nexus.

  • SKILL.md
  • references/analyze-reference.md
  • references/api-reference.md
  • references/composite-reference.md
  • references/prompt-categories.md
  • references/prompt-core.md
  • references/prompt-platforms.md
  • references/setup-guide.md
  • scripts/composite-banners.py
  • scripts/generate-image.py

Open the folder on GitHubat commit 7f5dd76

Compare with similar skills

AI Image Creator 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.

AI Image Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Image Creator this skillevolution-foundation/evo-nexus545—~5.1kAutomated safety check: NotesCustom licence
Generate ImageK-Dense-AI/claude-scientific-writer2.4k1 repos~3.8kAutomated safety check: NotesMIT
Nano Banana Pro Openroutergithub/awesome-copilot40k1 repos~664Automated safety check: PassMIT
AI Image Creatorcentminmod/my-claude-code-setup2.7k—~8.1kAutomated safety check: NotesMIT
Openrouter Imgrtadewald/skills180—~800Automated safety check: NotesNone
Image Genwpsnote/wpsnote-skills179—~1.3kAutomated safety check: PassNone

Similar skills

  • Generate Image

    K-Dense-AI/claude-scientific-writer

    Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow).

    2.4k GitHub starsUsed in 1 repo~3.8k tokens
    Media & CreativeAuto-check: notes
  • Nano Banana Pro Openrouter

    github/awesome-copilot

    Official

    Generate or edit images via OpenRouter with the Gemini 3 Pro Image model.

    40k GitHub starsUsed in 1 repo~664 tokens
    Media & CreativeAuto-check passed
  • AI Image Creator

    centminmod/my-claude-code-setup

    Generate, edit-from-reference, or analyze images with AI via OpenRouter (Gemini, GPT Image, Seedream, Qwen, MAI, Grok, FLUX.2, Recraft, Muse, Riverflow; Cloudflare AI Gateway BYOK).

    2.7k GitHub stars~8.1k tokensUpdated today
    Media & CreativeAuto-check: notes
  • Openrouter Img

    rtadewald/skills

    Generate or edit images via OpenRouter Image API across top models (Nano Banana, GPT Image, FLUX.2, Seedream, Qwen, Grok).

    180 GitHub stars~800 tokensUpdated 9 days ago
    Media & CreativeAuto-check: notes
  • Image Gen

    wpsnote/wpsnote-skills

    AI 图像生成助手,支持文生图和图生图,对接 OpenRouter / 阿里云百炼 / 火山方舟 / Google Gemini。

    179 GitHub stars~1.3k tokensUpdated 4 mo ago
    Media & CreativeAuto-check passed
  • Model Routing

    fal-ai-community/skills

    Choose default fal.ai endpoint IDs for genmedia production skills.

    249 GitHub stars~1.5k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed

More from evolution-foundation/evo-nexus

All 117 skills in this repo
  • MongoDB Query Client

    evolution-foundation/evo-nexus

    Runs read-only MongoDB finds, aggregations and collection listings against databases named in your .env, choosing the connection by label or index.

    545 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check: notes
  • MySQL and MariaDB Query Tool

    evolution-foundation/evo-nexus

    Queries MySQL or MariaDB databases declared in .env by label, read-only by default unless a connection explicitly allows writes.

    545 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check: notes
  • Postgres Query Client

    evolution-foundation/evo-nexus

    Runs read-only SQL queries and schema exploration against PostgreSQL databases declared in .env, chosen by label or index, with writes blocked unless a connection allows them.

    545 GitHub stars~1.8k tokensUpdated 4 mo ago
    Auto-check: notes
  • Redis Inspector

    evolution-foundation/evo-nexus

    Reads keys and server state from Redis instances configured in .env through a read-only Python client, choosing connections by label or index.

    545 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check: notes
  • Int Bling

    evolution-foundation/evo-nexus

    Bling ERP integration via API v3. An agent skill from evolution-foundation/evo-nexus.

    545 GitHub stars~2.5k tokensUpdated 4 mo ago
    Auto-check: notes
  • Int Evo CRM

    evolution-foundation/evo-nexus

    Query and manage Evo AI CRM data via REST API. An agent skill from evolution-foundation/evo-nexus.

    545 GitHub stars~2k tokensUpdated 4 mo ago
    Auto-check passed

Questions about AI Image Creator

What does AI Image Creator do?

Generates PNG images through OpenRouter models, with transparent backgrounds and reference-image edits, and describes existing images with multimodal vision. Images are generated through several models routed via Cloudflare AI Gateway with your own keys, or directly through OpenRouter or Google AI Studio. Saying gemini, riverflow, flux2, seedream or gpt5 selects the matching --model value, with gemini as the default.

When should I use AI Image Creator?

AI Image Creator fits situations like: generating a PNG icon or illustration for a project; making an asset with a transparent background; editing an image from a reference picture; describing or analyzing an existing image.

How do I install AI Image Creator in Claude Code?

Run `npx skills add evolution-foundation/evo-nexus --skill ai-image-creator -a claude-code`. Or copy the skill folder (.claude/skills/ai-image-creator in evolution-foundation/evo-nexus) into .claude/skills/ai-image-creator in your project. Claude Code loads it when a task matches its description.

How do I install AI Image Creator in Codex?

Run `npx skills add evolution-foundation/evo-nexus --skill ai-image-creator -a codex`. Or copy the skill folder (.claude/skills/ai-image-creator in evolution-foundation/evo-nexus) into .agents/skills/ai-image-creator in your project. Codex loads it when a task matches its description.

Can I use AI Image Creator 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 evolution-foundation/evo-nexus --skill ai-image-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-image-creator, .gemini/skills/ai-image-creator, .github/skills/ai-image-creator and .opencode/skills/ai-image-creator in your project.

What does AI Image Creator need to run?

Going by SKILL.md and its folder, AI Image Creator needs Python for the scripts in its folder, the command-line tools its instructions call (uv, magick, brew, apt and ffmpeg) and credentials named AI_IMG_CREATOR_CF_TOKEN, AI_IMG_CREATOR_OPENROUTER_KEY and AI_IMG_CREATOR_GEMINI_KEY. Our summary lists: uv, the Python runner; Network access; Cloudflare AI Gateway variables or direct API keys set in your shell profile. Its frontmatter pre-approves these tools: Bash, Read, Write. Compatibility (from SKILL.md): Requires uv (Python runner) and network access. Environment variables for CF AI Gateway or direct API keys must be configured in shell profile (~/.zshrc on macOS, ~/.bashrc on Linux, or System Environment Variables on Windows)..

Does AI Image Creator access the network?

SKILL.md names 1 domain. As links in the text: openrouter.ai. This is read from the text; nothing was executed.

Is AI Image Creator safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. 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 AI Image Creator use?

AI Image Creator has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does AI Image Creator use?

About 5.1k tokens (SKILL.md is roughly 20k 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 13k tokens, read only when the agent opens those files.

What are the alternatives to AI Image Creator?

Skills that share tags, products or a category with AI Image Creator: Generate Image (K-Dense-AI/claude-scientific-writer, 2.4k stars), Nano Banana Pro Openrouter (github/awesome-copilot, 40k stars), AI Image Creator (centminmod/my-claude-code-setup, 2.7k stars) and Openrouter Img (rtadewald/skills, 180 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Image Creator?

evolution-foundation (a GitHub organization) maintains it in evolution-foundation/evo-nexus, which has 545 GitHub stars. The repository holds 117 skills in this directory. The repository was last updated on May 13, 2026.

Source: evolution-foundation/evo-nexus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.