Skywork Design
aiskillstore/marketplace
Generate or edit images via backend Skywork Image API. An agent skill from aiskillstore/marketplace.
Turns a photo into a surreal pop collage: a black-and-white subject, huge flat color shapes for the background and exactly one impossible giant element.
SKILL.md written in Chinese; this summary is our English description.
Install Surreal Pop Collage
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install 2998980-hue/surreal-pop-collage surreal-pop-collage --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "surreal-pop-collage" agent skill from https://github.com/2998980-hue/surreal-pop-collage/tree/main into .claude/skills/surreal-pop-collage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-pop-collage", 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.
$ npx skills add 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install 2998980-hue/surreal-pop-collage surreal-pop-collage --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "surreal-pop-collage" agent skill from https://github.com/2998980-hue/surreal-pop-collage/tree/main into .agents/skills/surreal-pop-collage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-pop-collage", 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 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install 2998980-hue/surreal-pop-collage surreal-pop-collage --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "surreal-pop-collage" agent skill from https://github.com/2998980-hue/surreal-pop-collage/tree/main into .cursor/skills/surreal-pop-collage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-pop-collage", 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.
$ npx skills add 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install 2998980-hue/surreal-pop-collage surreal-pop-collage --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "surreal-pop-collage" agent skill from https://github.com/2998980-hue/surreal-pop-collage/tree/main into .gemini/skills/surreal-pop-collage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-pop-collage", 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 2998980-hue/surreal-pop-collage surreal-pop-collageInstalls 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 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "surreal-pop-collage" agent skill from https://github.com/2998980-hue/surreal-pop-collage/tree/main into .github/skills/surreal-pop-collage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-pop-collage", 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 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install 2998980-hue/surreal-pop-collage surreal-pop-collage --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "surreal-pop-collage" agent skill from https://github.com/2998980-hue/surreal-pop-collage/tree/main into .opencode/skills/surreal-pop-collage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "surreal-pop-collage", 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
surreal-pop-collage- GitHub stars
- 337
- Used in
- 1 other repo
- Token cost
- ~780 tokens
- SKILL.md length
- 274 words
- Files
- 5
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Turns a photo into a surreal pop collage: a black-and-white subject, huge flat color shapes for the background and exactly one impossible giant element.
- Works in 5 steps: 锚点可识别——3 秒内认出原图主体，脸部核心区不许压元素 → 只有一个不对劲——巨物唯一；出现第二个不可能元素就删 → 元素源于场景——巨物和色形都要能从原图/场景典故里指出处 → …
- Turning a landscape, portrait or city photo into surreal pop art
- SKILL.md covers 决策优先级(冲突时按此顺序), 授权与隐私, 第一步：场景卡 and 第二步：色形推导(禁止默认红日蓝天), plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This Chinese-language skill builds image-generation prompts that turn a photo into a surreal pop collage. The subject is desaturated and kept as a reality anchor, the background is replaced by two or three huge flat color shapes with no gradients, and the whole image contains exactly one impossible giant object. A priority list settles conflicts: a recognizable anchor, only one wrong thing, elements drawn from the scene, flat color discipline and a bright overall look.
The method runs in steps: write a scene card (anchor, regions, native colors, dominant direction and landmark references), derive the color shapes with one of three color strategies, choose a single giant object, add a small group of elements and a few white doodle lines, then compile a four-part English prompt. A correction list allows one regeneration for problems such as a two-skinned look, clutter, several giants, gradients or garbled text. Giving a photo counts as permission to call the image service, and only the prompt and reference image are sent.
When your agent uses it
- Turning a landscape, portrait or city photo into surreal pop art
- Making a surreal poster for a social media platform
- Creating a black-and-white photo with flat color dream shapes
- Writing an image-generation prompt around one impossible giant element
Example prompts
- “Turn this photo of a lakeside pavilion into a surreal pop collage.”
- “Make a surreal poster from my street photo with one giant impossible object.”
- “把这张城市夜景照片做成超现实波普拼贴”
Requirements
- An image generation service the agent can call, using the original photo as reference
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 锚点可识别——3 秒内认出原图主体，脸部核心区不许压元素
- 只有一个不对劲——巨物唯一；出现第二个不可能元素就删
- 元素源于场景——巨物和色形都要能从原图/场景典故里指出处
- 平涂纪律——色形无渐变、无立体阴影，这是和照片真实感对撞的关键
- 明亮度——整体保持亮，禁止暗黑恐怖
What it can do on your machine
Read from SKILL.md and the folder at commit 5bcf6f5. 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
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
Surreal Pop Collage loads about 780 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 274 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: warnings
The automated check found patterns that need a careful read before installing.
- WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:22
- 用户给了照片并要求生成/改造，即视为已授权调用生图服务，不再追问
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 2998980-hue/surreal-pop-collage at commit 5bcf6f5, republished under its MIT licence (© 2998980-hue). 274 words, ~780 tokens.
Download SKILL.mdSave it as
.claude/skills/surreal-pop-collage/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- surreal-pop-collage
- description
- 把照片变成超现实波普拼贴画(surreal pop collage)——照片去色保留为"现实锚"，背景替换为巨大平涂色形，全图只有一个"不可能的巨物"。当用户想要超现实拼贴、现实超现实化、小红书/抖音超现实海报、黑白照片+平涂色块的梦境感图片，或要把风景/人物/城市照做成超现实艺术时使用。
超现实波普拼贴 Surreal Pop Collage
黑白现实、平涂梦境、一物不对劲、元素源于图、色从图中来。
照片还是那张照片，但世界被换掉了：主体去色成黑白保留为"现实锚"，背景被 2–3 个巨大平涂色形替换，全图只有一个不可能的巨物——超现实的全部力量在于"只有一处不对劲"。
决策优先级(冲突时按此顺序)
- 锚点可识别——3 秒内认出原图主体，脸部核心区不许压元素
- 只有一个不对劲——巨物唯一；出现第二个不可能元素就删
- 元素源于场景——巨物和色形都要能从原图/场景典故里指出处
- 平涂纪律——色形无渐变、无立体阴影，这是和照片真实感对撞的关键
- 明亮度——整体保持亮，禁止暗黑恐怖
授权与隐私
- 用户给了照片并要求生成/改造，即视为已授权调用生图服务，不再追问
- 只把最终 prompt 和参考图发给生图服务；不传播、不另存用户原图
第一步：场景卡
读原图，逐项写下：
- 锚点主体：最有识别度的主体(人/物/景)，位置与占比
- 区域边界：天空/地面/水面/墙面等可被平涂替换的区域
- 原生色：2–3 个主色(色形颜色的来源)
- 主导动势：最强方向线(对角/纵深/视线)
- 场景典故：若为文化地标，它最出名的一句话知识(巨物的首选来源)
第二步：色形推导(禁止默认红日蓝天)
- 形状：圆(日/月)、拱、地平线色块、整面天空，选 2–3 个，贴合场景原有区域边界
- 颜色三选一策略：①场景已有色提纯(草绿→翠绿) ②互补色对撞(暖橙场景→群青) ③情绪反转色(阴郁场景→明黄)
- 平涂无渐变
第三步：巨物选择(禁止默认海豚鲸鱼)
按优先级选一个：
- 典故巨物(文化地标首选)：从景点最出名的典故里选，但先翻译成"可见的物件或动作"——运石→船队拖石、渔隐→巨网罩园、贴水→离水漂浮、以壁为纸→真山从纸里晕出、碑刻→刻线流成真河。只取大众记忆点(3 秒要懂)。自检：能写出"白居易的灯笼升成月亮"这种一句话配文才算焊上
- 场景元素荒诞化：把图里已有的小东西放大到不合常理(咖啡杯大过楼房)
- 语义最远物：和场景距离最远的东西(沙漠里游泳的人)
- 尺度颠倒：人小物大或反之
第四步：小元素与涂鸦
- 成群小元素(飞鸟/落叶/纸船)3–5 个，大小梯度 100/60/30，沿一条弧线分布
- 白色手绘涂鸦线条 2–3 条(刷痕/波浪线/星星)，做手工痕迹
- 禁止孤立单个装饰
Prompt 编译器(四段式)
只写能变成像素的指令：
- 风格定位：
surreal pop collage, vertical 3:4 - 现实锚：
keep the [主体] clearly recognizable but desaturated to black and white, preserving its texture - 平涂世界与巨物：
the background replaced by huge flat matte color shapes: [色形+颜色，按推导规则], one impossible giant element: [巨物，按选择规则], flat matte colors, no gradients - 小元素与约束：
[小元素群] in graduated sizes following an arc, a few white hand-drawn graffiti strokes, the black-and-white reality collides with the flat color world, no text, no watermark
范例(纽约街景)：surreal pop collage, keep this city street canyon recognizable but desaturated to black and white, the sky replaced by one huge flat lemon-yellow plane purified from the taxis, the street replaced by a flat brick-red plane, one impossible giant element: a giant traffic light hanging between the towers like a chandelier, a flock of small pigeons in graduated sizes following an arc, a few white hand-drawn graffiti strokes, flat matte colors, no gradients, no text, no watermark
纠偏(最多重生成一次，只修观察到的失败)
- 装饰和场景两张皮 → 检查每个元素是否写明源形关系(extend into / becomes / continues as)
- 太满/发闷 → 删一组元素，加大平涂安静区
- 巨物超过一个 → 删到只剩一个
- 渐变/立体阴影 → 加
flat matte colors, no gradients, no shadows on the color shapes - 照搬参考图元素(红日/海豚/鲸鱼) → 重做事先走色形推导和巨物选择，照抄即抄袭
- 文字乱码 → 中文移出 prompt 改后期代码排；英文单词保持 4–6 字母
硬禁忌
第二个不可能的巨物；色形渐变；立体阴影；进口素材；暗黑恐怖基调；装饰压脸；相框式整圈包围；满版纹理覆盖；中文文字进 prompt(必乱码，后期排)；水印。
质量门(交付前逐项过)
- 3 秒内认出锚点？
- 全图只有一个"不对劲"？
- 巨物能说出出处(场景元素/典故)？
- 色形颜色能从原图主色指出处？
- 平涂无渐变、无明暗立体？
- 小元素成群有梯度、沿弧线？
- 眯眼看：画面明亮，黑白现实与平涂梦境对撞清晰？
输出格式
默认只返回：生成的图 + 1–3 句创作思路(说清色形推导和巨物出处，不暴露完整 prompt)。用户明确要求时才附 prompt。
关联
本 skill 是 maximalism skill 变体 5 的独立精修版。需要拼贴海报(模切碎片+大字排版)见 cutout-collage-poster skill；需要更多变体与拼贴理论见 maximalism skill 的 references。
© 2998980-hue, 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 4 other files in the repository root of 2998980-hue/surreal-pop-collage.
- SKILL.md
- LICENSE
- README.md
- agents/openai.yaml
- examples/README.md
Open the folder on GitHubat commit 5bcf6f5
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in 2998980-hue/surreal-pop-collage, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Surreal Pop Collage 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 |
|---|---|---|---|---|---|---|
| Surreal Pop Collage this skill2998980-hue/surreal-pop-collage | 337 | 1 repos | ~780 | Automated safety check: Warn | MIT | |
| Skywork Designaiskillstore/marketplace | 433 | 1 repos | ~1.9k | Automated safety check: Pass | None | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Generate Imageynulihao/AgentSkillOS | 618 | 10 repos | ~1.7k | Automated safety check: Notes | None | |
| GPT Image Generation CLIwuyoscar/GPT-Image2-Skill | 5.7k | — | ~2.5k | Automated safety check: Notes | MIT | |
| Photo Abstract EditorialZzzLc0405/photo-abstract-editorial | 5.9k | — | ~815 | Automated safety check: Pass | Proprietary |
Similar skills
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.
Generate Image
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
GPT Image Generation CLI
wuyoscar/GPT-Image2-Skill
Generates and edits images with GPT Image 2 or 2.5 through a packaged CLI and a prompt gallery, after settling which model fits the request.
Photo Abstract Editorial
ZzzLc0405/photo-abstract-editorial
Creates one vertical editorial image from an uploaded photo, keeping the photo untouched and adding an abstract panel and short English title derived from it.
BlockRun Image Generation
BlockRunAI/ClawRouter
Generates or edits images through ClawRouter's local image API, with a choice of models and sizes and payment handled automatically through x402.
Related
Categories
Questions about Surreal Pop Collage
What does Surreal Pop Collage do?
Turns a photo into a surreal pop collage: a black-and-white subject, huge flat color shapes for the background and exactly one impossible giant element. This Chinese-language skill builds image-generation prompts that turn a photo into a surreal pop collage. The subject is desaturated and kept as a reality anchor, the background is replaced by two or three huge flat color shapes with no gradients, and the whole image contains exactly one impossible giant object.
When should I use Surreal Pop Collage?
Surreal Pop Collage fits situations like: turning a landscape, portrait or city photo into surreal pop art; making a surreal poster for a social media platform; creating a black-and-white photo with flat color dream shapes; writing an image-generation prompt around one impossible giant element.
How do I install Surreal Pop Collage in Claude Code?
Run `npx skills add 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a claude-code`. Or copy the skill folder (the 2998980-hue/surreal-pop-collage repository) into .claude/skills/surreal-pop-collage in your project. Claude Code loads it when a task matches its description.
How do I install Surreal Pop Collage in Codex?
Run `npx skills add 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a codex`. Or copy the skill folder (the 2998980-hue/surreal-pop-collage repository) into .agents/skills/surreal-pop-collage in your project. Codex loads it when a task matches its description.
Can I use Surreal Pop Collage 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 2998980-hue/surreal-pop-collage --skill surreal-pop-collage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/surreal-pop-collage, .gemini/skills/surreal-pop-collage, .github/skills/surreal-pop-collage and .opencode/skills/surreal-pop-collage in your project.
What does Surreal Pop Collage need to run?
SKILL.md names no scripts, command-line tools or credentials: Surreal Pop Collage is instructions for the agent only. Our summary lists: An image generation service the agent can call, using the original photo as reference.
Does Surreal Pop Collage 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 Surreal Pop Collage safe to install?
Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.
What licence does Surreal Pop Collage use?
Surreal Pop Collage 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 Surreal Pop Collage use?
About 780 tokens (SKILL.md is roughly 3.1k 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 Surreal Pop Collage?
Skills that share tags, products or a category with Surreal Pop Collage: Skywork Design (aiskillstore/marketplace, 433 stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Generate Image (ynulihao/AgentSkillOS, 618 stars) and GPT Image Generation CLI (wuyoscar/GPT-Image2-Skill, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Surreal Pop Collage?
2998980-hue (a GitHub user) maintains it in 2998980-hue/surreal-pop-collage, which has 337 GitHub stars. The repository was last updated on August 8, 2026.
Source: 2998980-hue/surreal-pop-collage on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.