Nano Banana
EvoScientist/EvoSkills
Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing.
Agent skill
by dracohu2025-cloud in dracohu2025-cloud/draco-skills-collection
A skill your agent uses when generating PPT-style image slides, poetic presentation covers, quiet paper-texture visual pages, report pages, invitations, social cards, or slide-image sets with…
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill gpt-image-2-paper-ppt-images -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection gpt-image-2-paper-ppt-images --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/gpt-image-2-paper-ppt-images .claude/skills/gpt-image-2-paper-ppt-images && 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 "gpt-image-2-paper-ppt-images" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/gpt-image-2-paper-ppt-images into .claude/skills/gpt-image-2-paper-ppt-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-paper-ppt-images", 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/gpt-image-2-paper-ppt-imagesType 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 gpt-image-2-paper-ppt-images -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection gpt-image-2-paper-ppt-images --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/gpt-image-2-paper-ppt-images .agents/skills/gpt-image-2-paper-ppt-images && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gpt-image-2-paper-ppt-images" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/gpt-image-2-paper-ppt-images into .agents/skills/gpt-image-2-paper-ppt-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-paper-ppt-images", 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 gpt-image-2-paper-ppt-images -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection gpt-image-2-paper-ppt-images --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/gpt-image-2-paper-ppt-images .cursor/skills/gpt-image-2-paper-ppt-images && 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 "gpt-image-2-paper-ppt-images" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/gpt-image-2-paper-ppt-images into .cursor/skills/gpt-image-2-paper-ppt-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-paper-ppt-images", 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 gpt-image-2-paper-ppt-images--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 gpt-image-2-paper-ppt-images -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection gpt-image-2-paper-ppt-images --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/gpt-image-2-paper-ppt-images .gemini/skills/gpt-image-2-paper-ppt-images && 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 "gpt-image-2-paper-ppt-images" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/gpt-image-2-paper-ppt-images into .gemini/skills/gpt-image-2-paper-ppt-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-paper-ppt-images", 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 gpt-image-2-paper-ppt-imagesInstalls 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 gpt-image-2-paper-ppt-images -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/gpt-image-2-paper-ppt-images .github/skills/gpt-image-2-paper-ppt-images && 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 "gpt-image-2-paper-ppt-images" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/gpt-image-2-paper-ppt-images into .github/skills/gpt-image-2-paper-ppt-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-paper-ppt-images", 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 gpt-image-2-paper-ppt-images -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 gpt-image-2-paper-ppt-images --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/gpt-image-2-paper-ppt-images .opencode/skills/gpt-image-2-paper-ppt-images && 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 "gpt-image-2-paper-ppt-images" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/gpt-image-2-paper-ppt-images into .opencode/skills/gpt-image-2-paper-ppt-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-paper-ppt-images", 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.
gpt-image-2-paper-ppt-imagesA skill your agent uses when generating PPT-style image slides, poetic presentation covers, quiet paper-texture visual pages, report pages, invitations, social cards, or slide-image sets with…
Gpt Image 2 Paper Ppt Images is an agent skill from dracohu2025-cloud/draco-skills-collection. Use when generating PPT-style image slides, poetic presentation covers, quiet paper-texture visual pages, report pages, invitations, social cards, or slide-image sets with GPT-Image-2 via imagegenerate.
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including assets (for example `README.md`).
It sits in Documents & Office, covering Image generation, Slides and decks and PowerPoint presentations. It works with Microsoft PowerPoint. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 26e8975. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
x.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Gpt Image 2 Paper Ppt Images loads about 3.9k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 1,348 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.
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.
The full file from dracohu2025-cloud/draco-skills-collection at commit 26e8975, republished under its MIT licence (© dracohu2025-cloud). 1,348 words, ~3,930 tokens.
.claude/skills/gpt-image-2-paper-ppt-images/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.This skill generates PPT-style image pages with a light, quiet, paper-breathing visual language.
Use Hermes image_generate for rendering. In this environment, image_generate is backed by GPT-Image-2, so call it directly unless the user explicitly asks for another image backend.
Source credit: 小小东 — https://x.com/xiaoxiaodong01
Source posts:
The style is useful for:
The goal is not a normal slide template. The goal is quiet paper texture + soft floating visual nodes + restrained typography + strong whitespace control.
Use this skill when the user asks for:
Do not use for editable .pptx production. If the user needs an editable PowerPoint file, use the PowerPoint / slide-generation skills instead.
This skill contains multiple GPT-Image-2 prompt templates under one shared PPT-image workflow. Pick by intent:
If the user only says “PPT 风格图片” and gives no style, use Template A. If the topic has cultural, craft, tea, humanities, architecture, heritage, or editorial-publication flavor, prefer Template B. If the user asks for 小红书卡片、3:4、书卷气、强文字骨架、巨大汉字裁切, prefer Template C; add Template D when the brief says 暗色背景 or serious/revolutionary palette.
Lock these shared properties:
Use this as the default base template. Replace the final topic and usage fields with the user's actual content.
请把画面处理成一种轻盈、安静、带纸面呼吸感的视觉作品:大面积温白或浅灰白背景像细颗粒印刷纸,略有噪点、纤维和柔和的旧胶片质感,不要做成干净塑料感或高饱和商业海报。主体不必照搬蓝莓,可以是任何与当前内容相关的物件、信息节点、人物局部、产品、数据点、概念符号或抽象形状,但它们应像柔软的色团一样悬浮在画面里,边缘被轻微雾化,中心有更深的色值,外圈向背景自然扩散,形成“靠近才发现层次”的细腻渐变。每个主体最好带一个小而清晰的暗部细节、切口、星形、标签、符号、编号或纹理锚点,让模糊的色团有记忆点,也让视线能从一个点跳到另一个点。
色彩遵循参考图的角色关系,而不是固定复制紫色。背景承担空气和留白,保持低饱和、偏温、轻颗粒;主体色根据内容气质改变,可以变得更学术、更清洁、更甜润、更锋利、更复古或更技术,但仍保持单一主色系的柔雾渐层,不要彩虹化。强调色只占很小面积,用在主体的中心、边缘细节、关键数字或微小标注上,负责情绪转折和阅读停顿。文字色使用低饱和的橄榄灰、旧金、烟褐、墨灰或与主题相称的沉静深色,像印在纸上的细线,而不是抢眼标题。阴影和深度也从主色内部生成,靠透明度、颗粒、模糊半径和轻微叠色形成层次。
版式要有明确的空白控制:主体散落但不是随机,整体沿一条隐约的斜向、弧线或呼吸式阅读路径移动,形成上轻下稳、左松右紧或中部漂浮的节奏。对象之间保持距离,让每个色团周围有安静的空气;可以有局部靠近、错位或轻微重叠,但不要排成机械网格。文字是画面结构的一部分:角落放置很小的英文、日期、页码、署名或元信息;一侧可以使用竖排中文、日文、数字、章节名或关键词,笔画细、间距松、像边界线一样拉住画面。标题不需要巨大,必要时让短句、竖排字、数字和注释成为构图重心的反向平衡。所有文字都要克制、清晰、留有边距,像设计学院作业、独立出版物、视觉实验海报或诗性信息图,而不是模板封面。
整体气质应是低声的、聪明的、有一点奇异感:少量颜色在白纸上发光,柔软和尖锐并存,空白比装饰更重要。适用于海报、PPT封面、报告页、信息图、排行榜、数据可视化、产品页、人物介绍、菜单、展览导视或社交卡片时,都把内容转化为若干有呼吸的视觉节点,用轻颗粒、雾化色彩、边缘文字和稀疏节奏组织阅读。现在把这种美学用于我的实际内容,让画面自然长成它需要的形式。
本次主题:
{主题}
每页的信息你自己规划
——————
用途:ppt、课件,最少10张pptUse this template when the deck should feel like a refined Chinese editorial booklet: quiet, restrained, publication-grade, with rice paper, pale ink, warm wood, moon-gate / arch / folding-fan / lifted-page windows, sparse line drawings, and modern information hierarchy.
Source: 小小东 — https://x.com/xiaoxiaodong01/status/2056412276593410537
请把画面处理成一种安静、克制、带有东方编辑感的高级视觉:它像一页被精心排过的纸本册页,又能自然适应现代信息设计。整体不要追求炫技和饱满,而要让留白成为主要结构,让内容在米纸、浅灰、淡墨、温润木色之间缓慢显形。画面可以有一两个柔和的图像窗口,像拱门、月洞、折扇或被风掀开的纸页,以大曲线切开空间,让照片、插图、数据或文字像被安放在旧院落的一角;这些窗口不必对称,边缘要干净,比例要有呼吸感,避免硬盒子、廉价圆角卡片和过度装饰。
如果出现影像,尽量让它带有低饱和、微雾、柔焦、侧光和时间感,像茶席、器物、手作、建筑、植物、文献或人物的一个片段,而不是完整说明一切。物体可以少,位置要准,宁可只露出半盏、一段桌面、一层纸纹、一束线描,也不要堆满素材。线描元素应像手边随笔留下的细线,轻、准、留有空隙,可用于手势、花枝、器物、路径、关系或隐喻,但不能变成花哨插画。色彩保持温和而有层次,主色接近宣纸和陈木,辅以墨灰、烟绿、茶褐、陶土、暗金或极淡的冷灰;任何醒目的颜色都应像印章或小标记,只承担必要的强调。
文字是画面气质的一部分,而不是贴上去的说明。中文可以有竖排、窄列、细长分行、古籍式停顿,也可以和现代无衬线数字、英文小字形成距离感;标题要像一块安静的重石,正文要像低声叙述,数字、日期、排名、图例、注释和索引要被整理成细线、短横、微小刻度或稀疏坐标。不要使用模板化的信息块,不要把所有内容平均分配到网格里,要让主次像书页气口一样自然形成:一处大留白,一处沉静主体,几组细小信息,少量线条把它们轻轻牵住。
当内容是PPT或报告,页面要像一组可翻阅的章节,每页只承担一个清晰判断,信息密度可以高,但必须有静气和秩序;当内容是信息图或数据可视化,图表应像墨线、案几、器物边缘或折页刻度那样被简化,重点数字要被安放而不是喊出;当内容是封面、海报、社媒卡片或排行榜,要让标题、图像和信息之间保持可被凝视的距离,既有东方审美的含蓄,也有现代编辑的准确。避免复古仿品感、茶文化套壳、空洞禅意、AI油亮质感、堆砌书法和廉价国风素材;它应该更像一种成熟的版面判断:淡、准、疏、稳,视觉很轻,但每个位置都有分量。
现在把这种美学用于我的实际内容:请根据我接下来提供的主题、文字、数据或用途,让画面自然长成它需要的形式,在静默留白中建立清晰的信息层级与可记住的视觉气质。
本次主题:
{主题}
用途:ppt、课件,不低于10张。每页信息和知识点由你规划,要求有趣、有料、生动。Use this template for a bookish, high-pressure Chinese editorial system: huge cropped characters / numbers / symbols act as the spatial skeleton, while tiny annotations create dense but breathable knowledge layers. It is especially good for 3:4 小红书卡片, PPT covers, report homepages, information graphics, rankings, product cards, and cultural / food / craft / knowledge topics.
Source: 小小东 — https://x.com/xiaoxiaodong01/status/2057338307051508107
请生成一种东方编辑美学的视觉方案:画面像铺在温润纸面上的一页克制刊物,整体安静、留白充足,却被少量高压的文字与色块牢牢钉住。不要把参考对象理解成固定题材,而要提取它的工作方式:用极大的汉字、数字或关键符号作为空间骨架,让它们可以被画面边缘裁切,只露出局部笔画、弧线、竖线和横线,像建筑结构一样支撑版面;再用极小的正文、英文注音、日期、标签、脚注或数据说明形成细密而有呼吸的阅读层级。标题不必完整陈列,可以成为画面里的形状、边界和节奏,正文则保持清瘦、疏朗、字距微开,像被认真排过的博物馆说明牌。
色彩系统以大面积低饱和浅底承载空气感,可以是米白、宣纸灰、淡粉、冷白或轻暖灰,具体温度根据内容气质调整;主内容颜色保持沉稳克制,用墨灰、炭黑、深褐、深青或低明度主题色承担信息重量;强调色只占小到中等面积,继承参考图那种“朱印式”的权威感和节奏感,但不要机械固定为红色。若内容偏学术,强调色可以变得更冷、更干净,像深蓝或铁灰中的细线;若内容偏节庆、文化、食物或手作,可以更温热、更颗粒化,像朱砂、陶土、枣红或熟橘;若内容偏科技、金融或医疗,则让强调色变得锋利、低饱和、面积更小,承担定位、警示或关键数据的职责。无论颜色如何变化,都保持原图的关系:浅底是空气,深色是文字秩序,强调色是情绪转折,灰色纹理是时间感与深度。
版式采用不完全对称的东方网格:边缘允许大字被切出画外,中心保留大片安静空白,信息块像漂浮的小岛,彼此之间有清楚距离。阅读动线不要直白从上到下,而是由大字残影、弧形或扇形纹样、细小说明文字、局部插图和底部色块共同引导,让视线在开阔与紧缩之间移动。可以加入纸纹、版画颗粒、淡淡的伞骨/扇骨/放射线/弧面纹理,作为低声背景;也可以把主体物、数据图形、人物轮廓、产品剪影或场景细节处理成水墨、炭笔、拓印、淡彩或低对比照片,使它们不喧宾夺主,而是像一枚安静证物。避免满版装饰、复杂渐变、过亮荧光、模板化卡片和商业海报式喊话。
文字设计是画面的核心:让中文、数字、英文和注释各自拥有不同尺度与语气,最大字负责视觉重量,中等字负责章节感,小字负责知识密度,英文或拼音只作为节奏性的细标。可以使用竖排与横排混合、字距拉开、局部旋转的极小标签、灰底小章、二维码式信息块、日期或编号,但都要服务于秩序,不要堆砌。最终画面应像一张可以被反复阅读的文化海报,也能自然转化为PPT封面、报告首页、信息图、排行榜、产品卡、人物专题或数据页:内容越复杂,留白越要坚定;信息越重要,强调色越要精确;主体越具象,周围越要轻。现在把这种美学用于我的实际内容,让它适合我给出的主题、文字、数据、物件或页面用途。
本次主题:{主题}
用途:ppt / 课件,请生成不低于10张图片
比例3:4
注意不是要你一张图片集合所有图片,是逐张生成。Use this as the dark-background variant of Template C. It keeps the same cropped-glyph editorial skeleton, but changes the atmosphere to dark paper, low-key historical weight, deep reds / iron gray / muted gold, and serious-report tension.
Source: 小小东 — https://x.com/xiaoxiaodong01/status/2057338307051508107
请生成一种东方编辑美学的视觉方案:画面像铺在温润纸面上的一页克制刊物,整体安静、留白充足,却被少量高压的文字与色块牢牢钉住。不要把参考对象理解成固定题材,而要提取它的工作方式:用极大的汉字、数字或关键符号作为空间骨架,让它们可以被画面边缘裁切,只露出局部笔画、弧线、竖线和横线,像建筑结构一样支撑版面;再用极小的正文、英文注音、日期、标签、脚注或数据说明形成细密而有呼吸的阅读层级。标题不必完整陈列,可以成为画面里的形状、边界和节奏,正文则保持清瘦、疏朗、字距微开,像被认真排过的博物馆说明牌。
色彩系统以暗色低饱和纸面承载空气感,可以是深墨黑、旧报纸黑、炭灰、深褐、铁灰或低明度主题色,具体温度根据内容气质调整;主内容颜色保持沉稳克制,用灰白、旧金、暗红、深青、陶土或低明度主题色承担信息重量;强调色只占小到中等面积,继承参考图那种“朱印式”的权威感和节奏感,但不要机械固定为红色。若内容偏历史、政治、革命、社会议题或严肃报告,强调色可以变得更厚重、更颗粒化,像暗红、朱砂、铁锈、旧金或深军绿;若内容偏科技、金融或医疗,则让强调色变得锋利、低饱和、面积更小,承担定位、警示或关键数据的职责。无论颜色如何变化,都保持关系:暗底是空气,亮色是文字秩序,强调色是情绪转折,灰色纹理是时间感与深度。
版式采用不完全对称的东方网格:边缘允许大字被切出画外,中心保留大片安静空白,信息块像漂浮的小岛,彼此之间有清楚距离。阅读动线不要直白从上到下,而是由大字残影、弧形或扇形纹样、细小说明文字、局部插图和底部色块共同引导,让视线在开阔与紧缩之间移动。可以加入纸纹、版画颗粒、淡淡的伞骨/扇骨/放射线/弧面纹理,作为低声背景;也可以把主体物、数据图形、人物轮廓、产品剪影或场景细节处理成水墨、炭笔、拓印、淡彩或低对比照片,使它们不喧宾夺主,而是像一枚安静证物。避免满版装饰、复杂渐变、过亮荧光、模板化卡片和商业海报式喊话。
文字设计是画面的核心:让中文、数字、英文和注释各自拥有不同尺度与语气,最大字负责视觉重量,中等字负责章节感,小字负责知识密度,英文或拼音只作为节奏性的细标。可以使用竖排与横排混合、字距拉开、局部旋转的极小标签、灰底小章、二维码式信息块、日期或编号,但都要服务于秩序,不要堆砌。最终画面应像一张可以被反复阅读的文化海报,也能自然转化为PPT封面、报告首页、信息图、排行榜、产品卡、人物专题或数据页:内容越复杂,留白越要坚定;信息越重要,强调色越要精确;主体越具象,周围越要轻。现在把这种美学用于我的实际内容,让它适合我给出的主题、文字、数据、物件或页面用途。
本次主题:{主题}
用途:ppt / 课件,请生成不低于10张图片
暗色背景,配色根据主题选择:历史 / 革命 / 严肃报告可用暗红、铁灰、旧金、深军绿;技术 / 金融 / 医疗可用冷灰、深蓝、低饱和警示色。
注意不是要你一张图片集合所有图片,是逐张生成。portrait / 3:4 when making social cards; use landscape / 16:9 only when the user explicitly wants PPT widescreen.image_generate once per page. Never ask GPT-Image-2 to pack 10 pages into one image.image_generateimage_generate returns one image per call. For a multi-page PPT image set, do not ask one call to generate 10 tiny slides in one canvas.
Instead:
image_generate.Page N / Total and a small metadata line in each page prompt.aspect_ratio='landscape' for normal PPT 16:9.For N pages, use this common structure unless the user specifies otherwise:
For fewer pages, compress. For more pages, expand sections 3-8.
Use this compact prompt block inside the canonical template:
本次主题:
<deck topic>
页面:<N>/<TOTAL>
页面标题:<short title>
页面目的:<what this page should make the viewer understand>
可见文字:
- <main title or short phrase>
- <small metadata / date / page number>
- <1-3 short labels only>
视觉节点:
- <object / person detail / concept symbol / data node>
- <texture anchor or tiny accent detail>
构图:<diagonal / arc / left-loose-right-tight / floating center / top-light-bottom-stable>
色彩:<single main color family + tiny accent>
用途:PPT 16:9 单页图片If the user wants only one PPT-style image, generate one page:
landscapeGPT image models can distort long text. Keep visible text short:
PAGE 03 / NOTESAvoid:
If the user needs accurate long text, generate a cleaner background image first, then add text with a local HTML/SVG/PPT pipeline.
image_generate per page.landscape / 16:9image_generate.© 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
SKILL.md and 9 other files (assets) in gpt-image-2-paper-ppt-images of dracohu2025-cloud/draco-skills-collection.
Open the folder on GitHubat commit 26e8975
Gpt Image 2 Paper Ppt Images 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 |
|---|---|---|---|---|---|---|
| Gpt Image 2 Paper Ppt Images this skilldracohu2025-cloud/draco-skills-collection | 227 | — | ~3.9k | Automated safety check: Pass | MIT | |
| Nano BananaEvoScientist/EvoSkills | 478 | 2 repos | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Slide Deck Image GeneratorSpaceZephyr/design-buddy | 176 | — | ~6.5k | Automated safety check: Pass | None | |
| Image-Based PPT Deck Generatorningzimu/codex-ppt-skill | 6.6k | — | ~2.6k | Automated safety check: Notes | MIT | |
| Gpt Image2 PptJuneYaooo/gpt-image2-ppt-skills | 1.3k | — | ~8.9k | Automated safety check: Notes | Apache-2.0 | |
| Ppt Image2 Editable Rebuildwwe-dog/ppt-image2-editable-rebuild | 200 | — | ~2.2k | Automated safety check: Pass | Unlicense |
EvoScientist/EvoSkills
Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing.
SpaceZephyr/design-buddy
Turns written content into designed slide images from an outline, merges them into PPTX or PDF, and can borrow styles from a registry of brand design systems.
ningzimu/codex-ppt-skill
Builds visually unified PowerPoint decks from articles, reports, papers, notes or outlines, with every slide generated as a full 16:9 image and assembled into a .pptx.
JuneYaooo/gpt-image2-ppt-skills
Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<collection/STYLEID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx.
wwe-dog/ppt-image2-editable-rebuild
Create editable PowerPoint decks or pages from image2/imagegen reference PNGs while keeping text and structure editable.
ZhiweiWei-NAMI/PPT-Visual-Replica
Create and edit editable PowerPoint decks, recreate slides or infographics from reference images, and develop scientific talks, teaching slides, and thesis defenses by generating slide drafts with…
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.
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…
dracohu2025-cloud/draco-skills-collection
Production pipeline for Motion Canvas — TypeScript-based programmatic vector animation with real-time preview.
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.
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…
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…
Works with
Categories
A skill your agent uses when generating PPT-style image slides, poetic presentation covers, quiet paper-texture visual pages, report pages, invitations, social cards, or slide-image sets with…. Gpt Image 2 Paper Ppt Images is an agent skill from dracohu2025-cloud/draco-skills-collection. Use when generating PPT-style image slides, poetic presentation covers, quiet paper-texture visual pages, report pages, invitations, social cards, or slide-image sets with GPT-Image-2 via imagegenerate.
Gpt Image 2 Paper Ppt Images fits situations like: generating PPT-style image slides; poetic presentation covers; quiet paper-texture visual pages; slide-image sets with GPT-Image-2 via imagegenerate.
Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill gpt-image-2-paper-ppt-images -a claude-code`. Or copy the skill folder (gpt-image-2-paper-ppt-images in dracohu2025-cloud/draco-skills-collection) into .claude/skills/gpt-image-2-paper-ppt-images in your project. Claude Code loads it when a task matches its description.
Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill gpt-image-2-paper-ppt-images -a codex`. Or copy the skill folder (gpt-image-2-paper-ppt-images in dracohu2025-cloud/draco-skills-collection) into .agents/skills/gpt-image-2-paper-ppt-images in your project. Codex loads it when a task matches its description.
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 gpt-image-2-paper-ppt-images -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gpt-image-2-paper-ppt-images, .gemini/skills/gpt-image-2-paper-ppt-images, .github/skills/gpt-image-2-paper-ppt-images and .opencode/skills/gpt-image-2-paper-ppt-images in your project.
SKILL.md names no scripts, command-line tools or credentials: Gpt Image 2 Paper Ppt Images is instructions for the agent only.
SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.
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.
Gpt Image 2 Paper Ppt Images is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Gpt Image 2 Paper Ppt Images: Nano Banana (EvoScientist/EvoSkills, 478 stars), Slide Deck Image Generator (SpaceZephyr/design-buddy, 176 stars), Image-Based PPT Deck Generator (ningzimu/codex-ppt-skill, 6.6k stars) and Gpt Image2 Ppt (JuneYaooo/gpt-image2-ppt-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.