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).
独立的 Nano Banana 2 / Gemini 3.1 Flash Image 图片生成 skill。支持单图、批量、workflow、JSON Prompt Mode、飞书上传；不依赖文章封面生成流程。
Install Nano Banana Image
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection nano-banana-image --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/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .claude/skills && cp -r skills-src/nano-banana-image .claude/skills/nano-banana-image && 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 "nano-banana-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/nano-banana-image into .claude/skills/nano-banana-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana-image", 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/dracohu2025-cloud/draco-skills-collection/tree/main/nano-banana-imageType 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 dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection nano-banana-image --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .agents/skills && cp -r skills-src/nano-banana-image .agents/skills/nano-banana-image && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nano-banana-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/nano-banana-image into .agents/skills/nano-banana-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana-image", 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 dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection nano-banana-image --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/nano-banana-image .cursor/skills/nano-banana-image && 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 "nano-banana-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/nano-banana-image into .cursor/skills/nano-banana-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana-image", 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/dracohu2025-cloud/draco-skills-collection.git --path nano-banana-image--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 dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection nano-banana-image --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/nano-banana-image .gemini/skills/nano-banana-image && 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 "nano-banana-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/nano-banana-image into .gemini/skills/nano-banana-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana-image", 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 dracohu2025-cloud/draco-skills-collection nano-banana-imageInstalls 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 dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .github/skills && cp -r skills-src/nano-banana-image .github/skills/nano-banana-image && 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 "nano-banana-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/nano-banana-image into .github/skills/nano-banana-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana-image", 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 dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection nano-banana-image --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/nano-banana-image .opencode/skills/nano-banana-image && 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 "nano-banana-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/nano-banana-image into .opencode/skills/nano-banana-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nano-banana-image", 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
nano-banana-image- GitHub stars
- 227
- Token cost
- ~635 tokens
- SKILL.md length
- 131 words
- Files
- 12 (incl. scripts, assets)
- Skills in repo
- 27
- Repo updated
- First seen
- Licence
- MIT
At a glance
独立的 Nano Banana 2 / Gemini 3.1 Flash Image 图片生成 skill。支持单图、批量、workflow、JSON Prompt Mode、飞书上传；不依赖文章封面生成流程。
- Works in 5 steps: 读入自然语言 prompt → 做轻量解析 → 合并模板默认值 → …
- Tasks that involve Image generation
- SKILL.md covers 这是什么, 默认能力, 依赖环境变量 and 统一入口, plus 4 more sections
- Runs Python and Shell scripts from its folder; calls python3 and bash; needs OPENROUTER_API_KEY and GEMINI_API_KEY
What it does
Nano Banana Image is an agent skill from dracohu2025-cloud/draco-skills-collection. 独立的 Nano Banana 2 / Gemini 3.1 Flash Image 图片生成 skill。支持单图、批量、workflow、JSON Prompt Mode、飞书上传；不依赖文章封面生成流程。
Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts and assets (for example `README.md`, `scripts/nano_banana_batch.py` and `scripts/nano_banana_image.py`).
It sits in Media & Creative, covering Image generation. It works with Google Gemini, OpenRouter and WeChat. The licence is MIT.
When your agent uses it
- Tasks that involve Image generation
Example prompts
- “/nano-banana-image”
Requirements
- Python 3
- A Bash shell
- A credential in OPENROUTER_API_KEY
- A credential in GEMINI_API_KEY
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 读入自然语言 prompt
- 做轻量解析
- 合并模板默认值
- 生成结构化 JSON spec
- 把 JSON 作为 authoritative image spec 发给模型
What it can do on your machine
Read from SKILL.md and the folder at commit 26e8975. 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 6 files in scripts/ (Python and Shell), which the agent can run.
Shell commands in SKILL.md call:
python3bash
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 these keys or tokens, usually read from environment variables:
OPENROUTER_API_KEYGEMINI_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Nano Banana Image loads about 635 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 131 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 dracohu2025-cloud/draco-skills-collection at commit 26e8975, republished under its MIT licence (© dracohu2025-cloud). 131 words, ~635 tokens.
Download SKILL.mdSave it as
.claude/skills/nano-banana-image/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- nano-banana-image
- description
- 独立的 Nano Banana 2 / Gemini 3.1 Flash Image 图片生成 skill。支持单图、批量、workflow、JSON Prompt Mode、飞书上传；不依赖文章封面生成流程。
- version
- 1.0.0
- author
- Hermes Agent
- license
- MIT
- platforms
- linux, macos
Nano Banana 2 Image
当用户想要：
- 单独用 Nano Banana 2 / Gemini 3.1 Flash Image 生成图片
- 不经过“文章理解 → 封面图”的那套流程
- 做通用插图、海报、产品头图、banner、公众号头图
- 批量跑多个 prompt
- 生成后上传飞书
就用这个 skill。
这是什么
这是一个独立图片生成 skill，核心职责只有一件事：
给 prompt，调用 OpenRouter 上的 google/gemini-3.1-flash-image-preview 出图。
它和 article-to-wechat-cover 的边界很明确：
article-to-wechat-cover偏工作流，先读文章，再提炼主题，再出图nano-banana-image偏底层出图器，直接把 prompt 变成图
默认能力
- 单图生成
- 批量生成
- workflow 目录化生成
- JSON Prompt Mode
- 模板化 prompt（wechat-cover / product-hero / poster / landing-hero）
- 飞书上传
- 自定义 aspect ratio
依赖环境变量
至少需要：
OPENROUTER_API_KEY
推荐：
OPENROUTER_IMAGE=google/gemini-3.1-flash-image-preview
可选：
GEMINI_API_KEY
统一入口
公开仓库里优先用：
python3 scripts/run.py --mode single --prompt '一只香蕉机器人坐在图书馆里读书'本地 Hermes skill 脚本路径：
scripts/nano_banana_image.pyscripts/nano_banana_batch.pyscripts/nano_banana_workflow.pyscripts/nano_banana_run.py
推荐命令
单图
python3 scripts/run.py \
--mode single \
--prompt '一个现代 AI 工作台界面，深色背景，蓝绿色科技风，适合 SaaS 头图' \
--template landing-hero \
--aspect-ratio 16:9 \
--output ./outputs/hero.png批量
python3 scripts/run.py \
--mode batch \
--input ./examples/prompts.txt \
--outdir ./outputs/batch \
--zipworkflow
python3 scripts/run.py \
--mode workflow \
--title '产品头图实验' \
--input ./examples/prompts.txt \
--output-dir ./outputs/jobs \
--aspect-ratio 16:9上传飞书
python3 scripts/run.py \
--mode single \
--prompt '一个未来感 AI 控制中枢，适合横幅头图' \
--upload-feishuJSON Prompt Mode
默认开启。
逻辑是：
- 读入自然语言 prompt
- 做轻量解析
- 合并模板默认值
- 生成结构化 JSON spec
- 把 JSON 作为 authoritative image spec 发给模型
这样做比纯 prompt 更稳，尤其在：
- 批量任务
- 多次复现
- 同一视觉体系延展
如果用户明确要原始 prompt，才加：
--raw-prompt验证建议
先跑：
bash scripts/smoke-test.sh再跑最小真实生成：
python3 scripts/run.py \
--mode single \
--prompt '一只未来香蕉机器人在图书馆里读书，温暖光线，插画风格' \
--output /tmp/nano-banana-demo.png完成标准
满足下面几点，才算这条链路真的可用：
scripts/run.py --help正常scripts/nano_banana_image.py --help正常- 能成功调用 OpenRouter 返回图片
- 输出文件 MIME type 与文件内容一致
- 若启用飞书上传，能返回有效
feishu_url
© dracohu2025-cloud, 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 11 other files (scripts, assets) in nano-banana-image of dracohu2025-cloud/draco-skills-collection.
- SKILL.md
- .env.example
- .gitignore
- README.md
- assets/example-generated-banner.jpg
- examples/prompts.txt
- scripts/nano_banana_batch.py
- scripts/nano_banana_image.py
- scripts/nano_banana_run.py
- scripts/nano_banana_workflow.py
- scripts/run.py
- scripts/smoke-test.sh
Open the folder on GitHubat commit 26e8975
Compare with similar skills
Nano Banana Image 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 |
|---|---|---|---|---|---|---|
| Nano Banana Image this skilldracohu2025-cloud/draco-skills-collection | 227 | — | ~635 | Automated safety check: Pass | MIT | |
| AI Image Creatorcentminmod/my-claude-code-setup | 2.7k | — | ~8.1k | Automated safety check: Notes | MIT | |
| Nano Banananexu-io/nexu | 3.3k | — | ~757 | Automated safety check: Pass | MIT | |
| Nano Banana One Shopnexu-io/nexu | 3.3k | — | ~870 | Automated safety check: Pass | MIT | |
| AI Image Creatorevolution-foundation/evo-nexus | 545 | — | ~5.1k | Automated safety check: Notes | Custom licence | |
| Openrouter Imgrtadewald/skills | 185 | — | ~800 | Automated safety check: Notes | None |
Similar skills
Nano Banana
nexu-io/nexu
Generate or edit images via Nano Banana image models. An agent skill from nexu-io/nexu.
Nano Banana One Shop
nexu-io/nexu
All-in-one image generation with Gemini models. An agent skill from nexu-io/nexu.
AI Image Creator
evolution-foundation/evo-nexus
Generates PNG images through OpenRouter models, with transparent backgrounds and reference-image edits, and describes existing images with multimodal vision.
Openrouter Img
rtadewald/skills
Generate or edit images via OpenRouter Image API across top models (Nano Banana, GPT Image, FLUX.2, Seedream, Qwen, Grok).
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).
More from dracohu2025-cloud/draco-skills-collection
All 27 skills in this repoAI News Bitable Archive Dingtalk
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when parsing a DingTalk daily news document and syncing title, date, Top 3, summary, conclusion, document link, and status into a DingTalk multidimensional table.
Feishu Seedance Video Pipeline
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when running a Feishu/Lark Base-centered Seedance video production pipeline: inspect/backfill the Base row, create/reference assets, build Row-24-style Chinese Seedance…
Motion Canvas
dracohu2025-cloud/draco-skills-collection
Production pipeline for Motion Canvas — TypeScript-based programmatic vector animation with real-time preview.
News Aggregator Skill
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when collecting public news candidates from Hacker News, GitHub Trending, Hugging Face papers, and other web sources for briefings and daily reports.
Open Design To Open Slide
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when mining Open Design visual systems and converting them into Open Slide React template kits or standalone 20-page template albums, with build, deployment, screenshot QA…
Daily AI Agent Aigc Top News Dingtalk
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when generating a daily 24h AI / Agent / AIGC top-news briefing, publishing it as a DingTalk document, validating it, and optionally archiving it to a DingTalk…
Related
Works with
Categories
Questions about Nano Banana Image
What does Nano Banana Image do?
独立的 Nano Banana 2 / Gemini 3.1 Flash Image 图片生成 skill。支持单图、批量、workflow、JSON Prompt Mode、飞书上传；不依赖文章封面生成流程。. Nano Banana Image is an agent skill from dracohu2025-cloud/draco-skills-collection.
When should I use Nano Banana Image?
Nano Banana Image fits situations like: tasks that involve Image generation.
How do I install Nano Banana Image in Claude Code?
Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a claude-code`. Or copy the skill folder (nano-banana-image in dracohu2025-cloud/draco-skills-collection) into .claude/skills/nano-banana-image in your project. Claude Code loads it when a task matches its description.
How do I install Nano Banana Image in Codex?
Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a codex`. Or copy the skill folder (nano-banana-image in dracohu2025-cloud/draco-skills-collection) into .agents/skills/nano-banana-image in your project. Codex loads it when a task matches its description.
Can I use Nano Banana Image 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 dracohu2025-cloud/draco-skills-collection --skill nano-banana-image -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nano-banana-image, .gemini/skills/nano-banana-image, .github/skills/nano-banana-image and .opencode/skills/nano-banana-image in your project.
What does Nano Banana Image need to run?
Going by SKILL.md and its folder, Nano Banana Image needs Python and a shell for the scripts in its folder, the command-line tools its instructions call (python3 and bash) and credentials named OPENROUTER_API_KEY and GEMINI_API_KEY. Our summary lists: Python 3; A Bash shell; A credential in OPENROUTER_API_KEY; A credential in GEMINI_API_KEY.
Does Nano Banana Image 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 Nano Banana Image 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 Nano Banana Image use?
Nano Banana Image is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Nano Banana Image use?
About 635 tokens (SKILL.md is roughly 2.5k 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 Nano Banana Image?
Skills that share tags, products or a category with Nano Banana Image: AI Image Creator (centminmod/my-claude-code-setup, 2.7k stars), Nano Banana (nexu-io/nexu, 3.3k stars), Nano Banana One Shop (nexu-io/nexu, 3.3k stars) and AI Image Creator (evolution-foundation/evo-nexus, 545 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Nano Banana Image?
dracohu2025-cloud (a GitHub user) maintains it in dracohu2025-cloud/draco-skills-collection, which has 227 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on September 17, 2026.
Source: dracohu2025-cloud/draco-skills-collection on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.