AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
为 Qwen-Image 编写和改写生图提示词，区分局部编辑与参考主体创作，处理同人物系列、画幅及原图验收；用户要求生成时连接其已有的 Qwen 图像工作流。不用于下载权重、通用模型运维或其他图像模型。
Install Qwen Image Gen
$ npx skills add ZSeven-W/craft-skills --skill qwen-image-gen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ZSeven-W/craft-skills qwen-image-gen --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/ZSeven-W/craft-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/qwen-image-gen .claude/skills/qwen-image-gen && 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 "qwen-image-gen" agent skill from https://github.com/ZSeven-W/craft-skills/tree/main/skills/qwen-image-gen into .claude/skills/qwen-image-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-image-gen", 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/ZSeven-W/craft-skills/tree/main/skills/qwen-image-genType 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 ZSeven-W/craft-skills --skill qwen-image-gen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ZSeven-W/craft-skills qwen-image-gen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZSeven-W/craft-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/qwen-image-gen .agents/skills/qwen-image-gen && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "qwen-image-gen" agent skill from https://github.com/ZSeven-W/craft-skills/tree/main/skills/qwen-image-gen into .agents/skills/qwen-image-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-image-gen", 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 ZSeven-W/craft-skills --skill qwen-image-gen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ZSeven-W/craft-skills qwen-image-gen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZSeven-W/craft-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/qwen-image-gen .cursor/skills/qwen-image-gen && 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 "qwen-image-gen" agent skill from https://github.com/ZSeven-W/craft-skills/tree/main/skills/qwen-image-gen into .cursor/skills/qwen-image-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-image-gen", 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/ZSeven-W/craft-skills.git --path skills/qwen-image-gen--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 ZSeven-W/craft-skills --skill qwen-image-gen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ZSeven-W/craft-skills qwen-image-gen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZSeven-W/craft-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/qwen-image-gen .gemini/skills/qwen-image-gen && 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 "qwen-image-gen" agent skill from https://github.com/ZSeven-W/craft-skills/tree/main/skills/qwen-image-gen into .gemini/skills/qwen-image-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-image-gen", 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 ZSeven-W/craft-skills qwen-image-genInstalls 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 ZSeven-W/craft-skills --skill qwen-image-gen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ZSeven-W/craft-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/qwen-image-gen .github/skills/qwen-image-gen && 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 "qwen-image-gen" agent skill from https://github.com/ZSeven-W/craft-skills/tree/main/skills/qwen-image-gen into .github/skills/qwen-image-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-image-gen", 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 ZSeven-W/craft-skills --skill qwen-image-gen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ZSeven-W/craft-skills qwen-image-gen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZSeven-W/craft-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/qwen-image-gen .opencode/skills/qwen-image-gen && 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 "qwen-image-gen" agent skill from https://github.com/ZSeven-W/craft-skills/tree/main/skills/qwen-image-gen into .opencode/skills/qwen-image-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-image-gen", 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
qwen-image-gen- GitHub stars
- 225
- Token cost
- ~478 tokens
- SKILL.md length
- 58 words
- Files
- 42 (incl. scripts, references, assets)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
为 Qwen-Image 编写和改写生图提示词，区分局部编辑与参考主体创作，处理同人物系列、画幅及原图验收；用户要求生成时连接其已有的 Qwen 图像工作流。不用于下载权重、通用模型运维或其他图像模型。
- Tasks that involve Image generation
- SKILL.md covers 先区分任务, 把单张、系列和画幅拆开, 已要求生成时 and 验收与修正
What it does
Qwen Image Gen is an agent skill from ZSeven-W/craft-skills. 为 Qwen-Image 编写和改写生图提示词，区分局部编辑与参考主体创作，处理同人物系列、画幅及原图验收；用户要求生成时连接其已有的 Qwen 图像工作流。不用于下载权重、通用模型运维或其他图像模型。
Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. The skill folder holds 45 other files, including scripts, reference files and assets (for example `ASSET-LICENSE.md`, `README.en.md` and `README.md`).
It sits in Media & Creative, covering Image generation. It works with Qwen. The repository describes itself as: Research-backed, eval-driven skills for AI agents. The licence is MIT.
When your agent uses it
- Tasks that involve Image generation
Example prompts
- “/qwen-image-gen”
Requirements
- Node.js
What it can do on your machine
Read from SKILL.md and the folder at commit 01c8ffe. 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.
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
Qwen Image Gen loads about 478 tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 29 tokens; SKILL.md has 58 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 ZSeven-W/craft-skills at commit 01c8ffe, republished under its MIT licence (© ZSeven-W). 58 words, ~478 tokens.
Download SKILL.mdSave it as
.claude/skills/qwen-image-gen/SKILL.md (or your agent's skills folder). This skill also uses 41 other files; get the full folder from GitHub.- name
- qwen-image-gen
- description
- 为 Qwen-Image 编写和改写生图提示词，区分局部编辑与参考主体创作，处理同人物系列、画幅及原图验收；用户要求生成时连接其已有的 Qwen 图像工作流。不用于下载权重、通用模型运维或其他图像模型。
Qwen Image Gen
将创作需求转成可执行的提示词、参考图关系和尺寸决策。默认由当前 Agent 改写，无需额外部署提示词增强模型。参考图任务需要视觉理解能力；纯文本执行者应先取得准确的图片描述。
先区分任务
- 提示词、改写、翻译：交付可复制文本与尺寸建议，不提交生图。
- 文生图：描述最终可见画面。身份、数量、文字、动作、颜色和位置是固定要求；只补全必要的构图与光照细节。
- 修改这张图：先说改哪里、改成什么，再简洁锁定未修改内容。改变姿势时不能同时要求姿势不变。
- 参考主体创作新图：先实际看图，明确哪张图提供身份、服装或背景，再描述新姿势与场景。不要只靠重复人物形容词维持同一张脸。
写提示词前读 rewriting.md。保留用户的创作意图，不用通用美化词覆盖具体要求。简单需求不必扩成长文。
把单张、系列和画幅拆开
单张只安排一个明确动作。系列总提示词包含多个动作时，拆为各自完整的单图提示词；同人物系列分别从一张通过验收的身份参考出发，避免逐张把上次生成的误差累积进去。只有用户要拼图时才描述多面板。
画幅是独立参数。明确像素或比例优先；没有指定时，根据构图建议比例并落实到下游接口。不要只在文字里说竖图，却提交方形画布。相同比例可以对应不同像素尺寸。
可供程序衔接的结构：
{"rewritten_prompt":"最终画面描述","wh_ratio":"9:16"}{"rewritten_prompt":"具体编辑要求及保留条款","wh_ratio":"","ratio_follow":"<image1>"}wh_ratio 与 ratio_follow 互斥。仅将 rewritten_prompt 送入模型的文字输入，不把 JSON 包装或解释一并送进去。用户只要提示词时，用普通文本交付即可。
已要求生成时
使用用户指定且已有的 Qwen 入口，沿用当前授权。先读 integration.md，核对实际接口：是否支持参考图、多图、显式宽高和原生 Alpha。模型有某能力，不代表当前封装已经接入。
本 Skill 不预置服务器地址或密钥，也不默认下载模型。没有生成连接时仍可交付提示词；不能把“已准备请求”说成“已生成”。
应用需要加载同一份版本化规则时，读 shared-runtime.md。可选 Node.js 模块只构造规划消息、校验结构和整理质量反馈，不联网、不执行生成；普通 Agent 无需运行它。
附带的 scripts/prepare_workbench_request.py 只是一个可选、离线、特定工作台协议的请求构建器。它不调用模型、不进行提示词改写、不联网。其 2048 像素和单参考图限制仅适用于该适配器，不是 Qwen 的模型上限。详见 workbench-adapter.md。
验收与修正
检查未经修饰的原图：目标文字、动作、肢体连接、身份、保留区域、实际像素尺寸；需要透明时检查 Alpha 和边缘，而非仅看文件扩展名。
为每个结果保留原提示词、实际提交文本、参考图、生成设置及结果位置。质量缺陷与审美不喜欢分开记录：多肢不代表不喜欢坐姿。修正时附上缺陷、目标状态和需要保留的内容；保留原图与新版本，让用户比较验收。没有更多生成授权时停止，不无限重抽。
当用户要 A/B 对照，固定图像模型、尺寸、步数、种子和参考图，只改变待测因素。把采用新画幅的实验单独比较。生成成功、图片更美观、严格完成要求是三个不同判断。
遇到文字泄漏、多宫格、姿势粘连、尺寸异常或透明边缘问题时读 tested-behavior.md。这些是具体条件下的观察，不能扩展为通用成功率。
© ZSeven-W, 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 41 other files (scripts, references, assets) in skills/qwen-image-gen of ZSeven-W/craft-skills.
- SKILL.md
- ASSET-LICENSE.md
- LICENSE
- README.en.md
- README.md
- agents/openai.yaml
- assets/examples/ab/README.md
- assets/examples/ab/baker-A.png
- assets/examples/ab/baker-B.png
- assets/examples/ab/baker-reference.png
- assets/examples/ab/cases.json
- assets/examples/ab/checksums.json
- assets/examples/ab/poster-A.png
- assets/examples/ab/poster-B.png
- assets/examples/ab/reach-A.png
- assets/examples/ab/reach-B.png
- assets/examples/ab/stool-A.png
- … and 25 more
Open the folder on GitHubat commit 01c8ffe
Compare with similar skills
Qwen Image Gen 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 |
|---|---|---|---|---|---|---|
| Qwen Image Gen this skillZSeven-W/craft-skills | 225 | — | ~478 | Automated safety check: Pass | MIT | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Qwen Image 2 1 Prompteriamyoki/qwen-image-2.1-skill | 157 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Qianwen Image GenerationQianWen-AI/qianwen-ai | 105 | — | ~5.2k | Automated safety check: Notes | Apache-2.0 | |
| Qwen Editdigitalsamba/claude-code-video-toolkit | 2.2k | — | ~711 | Automated safety check: Pass | MIT | |
| Qianwen Video GenerationQianWen-AI/qianwen-ai | 105 | — | ~5k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Qwen Image 2 1 Prompter
iamyoki/qwen-image-2.1-skill
Optimize, rewrite, and craft image generation and editing prompts tailored specifically for Alibaba's Qwen-Image-2.1 diffusion model.
Qianwen Image Generation
QianWen-AI/qianwen-ai
Generate and edit images using Wan and Qwen Image models. An agent skill from QianWen-AI/qianwen-ai.
Qwen Edit
digitalsamba/claude-code-video-toolkit
AI image editing prompting patterns for Qwen-Image-Edit. An agent skill from digitalsamba/claude-code-video-toolkit.
Qianwen Video Generation
QianWen-AI/qianwen-ai
Generate videos using Wan and HappyHorse models. An agent skill from QianWen-AI/qianwen-ai.
Qianwen Vision
QianWen-AI/qianwen-ai
Understand images and videos with Qwen vision models. An agent skill from QianWen-AI/qianwen-ai.
More from ZSeven-W/craft-skills
Native Transparent Imagegen
ZSeven-W/craft-skills
Generate new raster assets that must contain native pixel transparency, then verify the untouched PNG or WebP before delivery.
Recurring Character Diary Comic
ZSeven-W/craft-skills
Create, audit, and repair short page-native diary comics around an existing authorized recurring character, with story-directed page rhythm, exact dialogue, directional-surface proof, and…
Logo Semantic Fusion
ZSeven-W/craft-skills
Develop and evaluate logo concepts when the explicit design problem is semantic fusion: two or more brand meanings must share a contour, stroke, negative space, glyph skeleton, or shape system.
Single Path Process Diorama
ZSeven-W/craft-skills
将 3–5 步线性流程制作成单张完整、非宫格的微缩剧场成品。适用于流程故事封面、制作过程图、软件交付旅程与科普式微缩场景；以单一路径、可追踪载体、可辨识动作和题材匹配的材质表达顺序。不用于需要精确分支和数据尺度的流程图、实际操作规程或普通城市微缩景观。
Related
Works with
Categories
Questions about Qwen Image Gen
What does Qwen Image Gen do?
为 Qwen-Image 编写和改写生图提示词，区分局部编辑与参考主体创作，处理同人物系列、画幅及原图验收；用户要求生成时连接其已有的 Qwen 图像工作流。不用于下载权重、通用模型运维或其他图像模型。. Qwen Image Gen is an agent skill from ZSeven-W/craft-skills.
When should I use Qwen Image Gen?
Qwen Image Gen fits situations like: tasks that involve Image generation.
How do I install Qwen Image Gen in Claude Code?
Run `npx skills add ZSeven-W/craft-skills --skill qwen-image-gen -a claude-code`. Or copy the skill folder (skills/qwen-image-gen in ZSeven-W/craft-skills) into .claude/skills/qwen-image-gen in your project. Claude Code loads it when a task matches its description.
How do I install Qwen Image Gen in Codex?
Run `npx skills add ZSeven-W/craft-skills --skill qwen-image-gen -a codex`. Or copy the skill folder (skills/qwen-image-gen in ZSeven-W/craft-skills) into .agents/skills/qwen-image-gen in your project. Codex loads it when a task matches its description.
Can I use Qwen Image Gen 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 ZSeven-W/craft-skills --skill qwen-image-gen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qwen-image-gen, .gemini/skills/qwen-image-gen, .github/skills/qwen-image-gen and .opencode/skills/qwen-image-gen in your project.
What does Qwen Image Gen need to run?
SKILL.md names no scripts, command-line tools or credentials: Qwen Image Gen is instructions for the agent only. Our summary lists: Node.js.
Does Qwen Image Gen 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 Qwen Image Gen 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 Qwen Image Gen use?
Qwen Image Gen 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 Qwen Image Gen use?
About 478 tokens (SKILL.md is roughly 1.9k 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 4.9k tokens, read only when the agent opens those files.
What are the alternatives to Qwen Image Gen?
Skills that share tags, products or a category with Qwen Image Gen: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Qwen Image 2 1 Prompter (iamyoki/qwen-image-2.1-skill, 157 stars), Qianwen Image Generation (QianWen-AI/qianwen-ai, 105 stars) and Qwen Edit (digitalsamba/claude-code-video-toolkit, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Qwen Image Gen?
ZSeven-W (a GitHub organization) maintains it in ZSeven-W/craft-skills, which has 225 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 22, 2026.
Source: ZSeven-W/craft-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.