visual-style-ppt skill
A Codex skill that builds image-first decks: a saved visual style, one image per slide and assembly into a PPTX
- 398 ★ on the repository
- Last commit
Extended access
Why this level
- The skill calls an image generation model for every page and spends its quota
- The agent writes images, documents and an archive to the user's folder
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/visual-style-pptDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill calls an image generation model for every page and spends its quota
- The agent writes images, documents and an archive to the user's folder
This is third-party code. Review the repository files before installing.
What it does
The visual-style-ppt skill turns a visual style into a reusable asset and applies it to documents, articles and outlines. The result is slide images: each page is generated as a separate image such as `slide-01.png`, and the images are then assembled into a PPTX where one page consists of one picture. The work goes in steps. The skill classifies the task: extract a style, apply a saved one, turn a document into a deck or revise finished slides. Then it takes a style file, pulls the storyline, audience and page count from the text and writes `outline.md` and `prompts.md`. For a multi-page deck it recommends first making a thumbnail sheet to lock the rhythm. The instructions call for approval of the outline and images before PPTX assembly. The final archive combines images, prompts, the outline and style files. The library has three styles: a terminal-tech magazine for AI and developer tools, a grid with strong headlines for opinions and trends, and a French editorial style for brands and consumer topics. Every style carries a Style Lock block that fixes fonts, grid, colors, borders and negative constraints for the model. By default slide text is Chinese, a page holds at most two or three points and no dates appear.
Who it is for. For designers, marketers and content authors who turn articles and documents into consistent image-based decks and want to keep visual styles in a library.
Good fit when
- An article or Markdown file has to become an 8-page deck in one visual style
- You want to extract a style from a screenshot, someone else's deck or a web page and save it for reuse
- You need infographics for Xiaohongshu or article illustrations in one look
- Before generating images you want to approve the outline and prompts so attempts are not wasted
- A deck is already generated and individual pages need revisions
Not a fit when
- You need an editable PPTX where every text box, chart and shape can be changed separately: here a page is one whole picture
- You need the same logo on every page: the model does not guarantee drawing it consistently
- A page must hold tables and long paragraphs: the skill keeps text density low
- You need automatic dates and timestamps: without an explicit request the skill adds none
Example request
Use the terminal-tech magazine style and turn this article into an 8-page deck. Show outline.md and prompts.md first and generate images after my confirmationLimitations
Codex needs access to the generator the author calls Image 2.5. The skill requires that model, but its availability and a specific API are not defined in the instructions. PDF and Word reading and PPTX creation must also be provided separately; installing the skill does not add those tools.
Documents and visual references are sent to the generator and consume its quota. Plan and image approvals are textual instructions, so the agent must follow them. The author has not specified a license; rights to use and copy the material are undefined and should be clarified with the author.
How to disable. Delete the ~/.codex/skills/visual-style-ppt folder. Finished images, PPTX files and archives sit in the folder you chose for saving, and you can delete them separately.
FAQ
How do I install visual-style-ppt in Codex?
Clone the repository into the skills directory: cd ~/.codex/skills, then git clone https://github.com/irenerachel/visual-style-ppt-skill.git visual-style-ppt. Update the skill with git pull in that folder.
What does visual-style-ppt need to generate slides?
The author requires Image 2.5 accessible from Codex. Model access and PPTX creation need separate setup. Check that your environment provides both before installing.
Why can't I edit text in the final PPTX?
Each page is generated as a single picture and the PPTX is only a container. So changes are made by regenerating the page through the revision workflow.
How do I save my own visual style for decks?
Ask the skill to extract a style from an image and save it. A style is a Markdown file in the styles folder that holds the purpose, colors with hex values, font character, grid, border rules, a Style Lock block and negative constraints for Image 2.5.
How do I check a deck before images are generated?
The agent first prepares the outline and prompts for review before generation. For several slides, a thumbnail sheet helps you check the presentation’s rhythm and palette.
Discussion
No questions or reviews yet.
Related
SkillsA skill that builds a deck through dialog and previews: structure and style first, then page images generated and packed into PPTX
Skill turns the agent into a deck producer: brief, storyboard, slide posters, QA and a PDF or editable PPTX.
A skill that builds a deck from a topic or article, or restyles an old one from a reference image, keeping the text and editable slides
A skill that builds editable PowerPoint decks from outline.json with scripts and checks layout and density before delivery.
SlideMuse turns a PDF, paper or notes into an image-based deck in 15 styles and can rebuild it as an editable PPTX
A skill that builds decks with gpt-image-2: each slide is drawn as a full layout and packed into .pptx, optionally mimicking a reference template
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| visual-style-ppt (this card) | no | 398 | |
| gpt-image2-ppt-skills | no | 1,451 | draws each slide through gpt-image-2 as a complete layout and assembles the deck |
| ppt-image-first | no | 1,239 | builds a deck through dialogue and previews: structure and style first, then page generation |
README in short
The output retains source prompts and the selected style file, allowing an individual slide to be regenerated later. The default layout is 16:9; specify the desired text language in your request.
README badge
Original SKILL.md
--- name: visual-style-ppt description: Create style-driven slide images strictly with the Image 2.5 model, assemble those images into image-only PPTX decks, and manage reusable visual style libraries from documents or visual references. Use when the user asks for a "PPT Skill", "风格驱动 PPT", "提炼风格做 PPT", "调用某个风格做 PPT", "图片版 PPT", "保存 PPT 风格", "列出 PPT 风格", "文档生成 PPT", "文章生成 PPT", "把文档做成演示文稿", or wants to extract, save, reuse, and apply visual style keywords specifically for visual slide/image deck creation. --- # Visual Style PPT ## Highest Priority Rule: Image 2.5 Only This skill must use the Image 2.5 model to generate every final slide image, thumbnail board, visual page, infographic, article illustration, or PPT page image. HTML output is strictly forbidden for image generation. Do not create HTML/CSS pages, browser screenshots, SVG/HTML mockups, canvas renders, or local-script visual reproductions as final or intermediate image outputs. Do not use HTML as a fallback when Image 2.5 is unavailable; stop and state that Image 2.5 access is required. This rule has the highest priority in this skill and overrides every workflow, reference file, style file, packaging rule, user shortcut, or implementation convenience that might imply another image-production route. PPTX files may only be assembled after Image 2.5 has generated the approved page images; PPTX is a container, not an image-generation method. ## Core Idea Turn visual style into a reusable asset, then apply that asset to documents, outlines, image-only PPT decks, slide images, Xiaohongshu information graphics, and article illustrations. Use this skill as an Image 2.5-only visual slide workflow. The default deliverable is full-slide images generated by Image 2.5; when the user wants a PPT, place the generated images into a PPTX as full-slide image pages. Do not implement or optimize editable PPTX content unless the user explicitly overrides this skill direction. ## Required References - For the full operating workflow, read `references/workflow.md`. - For PPTX vs image output rules, read `references/output-package.md`. - For page type selection, read `references/page-types.md`. - For post-generation revisions, read `references/revision-workflow.md`. - For style extraction interviews, read `references/style-interview.md`. - For the default terminal-tech magazine visual style, read `styles/terminal-tech-magazine.md`. - When the user asks for a style library, list or read files in `styles/`. ## Default Behavior - Default output type: Image 2.5-generated slide images. If the user says "PPT", assemble those images into an image-only PPTX. - Default aspect ratio: 16:9. - Default image quality: Image 2.5, 16:9, high-resolution, sharp text, clean edges. - Default language: Chinese-first. Use Chinese for slide titles, section titles, module labels, captions, explanatory copy, and all generated support documents unless the user explicitly asks for another language. Keep proper nouns, product names, model names, code terms, and unavoidable domain terms in their original language when that is clearer. - Default style: `styles/terminal-tech-magazine.md` when the user says "终端风格", "CodeBuddy 风格", "科技杂志风格", or does not specify another saved style. - Default text density: low information by default, especially for PPT inner slides. Never create dense slides unless the user explicitly asks for a leave-behind, report page, or infographic. A normal inner slide should have one title, one short subtitle or takeaway, and at most 2-3 short information points. - Default layout direction: cover pages may be visually expressive; inner slides must be information-first, calm, readable, and spacious, with imagery/backgrounds kept subordinate. - Default style isolation: each deck must use exactly one selected style source and one `Style Lock`. Do not blend visual DNA from earlier tasks, previous reference images, or unrelated saved styles unless the user explicitly requests a hybrid. - Default component consistency: across one deck, borders, cards, containers, dividers, arrows, footer metadata, corner radius, and line weights must use one repeated system. Variation may come from layout and emphasis, not from changing the frame/container style on every slide. - Default slide header consistency: if a style uses small top titles with numbers, treat them as repeated content-section headers, not necessarily absolute slide/page numbers. Keep the same placement, size, spacing, and format across all applicable slides. If the style defines exceptions such as cover, contents, divider, or thank-you pages, preserve those exceptions deliberately; those exception pages do not consume a content-section number. The first applicable inner/content slide should usually start at `01` or `PART 1`. - Default logo behavior: do not ask Image2.5 to generate logos, brand wordmarks, reusable deck marks, watermarks, or repeated English identity labels by default. If the user needs a logo, keep it out of generated slide images and add it later as a fixed post-production asset/layer, or let the user add it after delivery. A reference logo image may guide visual shape but is not reliable enough for cross-page text/logo consistency inside Image2.5 output. - Default time/date behavior: do not add dates, times, timestamps, "today", export time, generated time, or current date to slides, prompts, metadata, footers, or visual elements by default. Include date/time only when the source article explicitly requires it, the user explicitly asks for it, or the slide topic itself is a timeline/schedule/date-sensitive report. A source document having a file timestamp, export timestamp, or local system date does not by itself justify visible date/time in the deck. - Default page count: ask the user how many pages/slides they want unless they already provided a count or explicitly asked the skill to decide. - Multiple outputs: keep one visual DNA while varying composition, page type, visual anchor, or emphasis. - No outer border rule: generated slide images and thumbnail boards must not have black borders, dark strokes, or frame lines on the outer canvas edge. Internal grid lines, dividers, and module borders are allowed, but keep them inset from the image edge or let imagery/white space bleed naturally. Never create a full-page rectangular outline around the slide. - Per-slide image rule: PPT pages must be generated and saved as separate single-slide image files, one image per slide. Do not request or deliver a multi-slide contact sheet, storyboard, PDF page, or collage as the final slide image output. Each final slide image must be independently usable as one full-bleed PPT page. - Thumbnail-first option: for multi-page decks, prefer a two-pass visual workflow when style consistency matters: first generate one small "thumbnail board / contact sheet" that shows the whole deck as tiny slide thumbnails to lock visual rhythm, grid, palette, and page-to-page variation; then generate each approved slide as an individual full-size image using that thumbnail board as the visual continuity reference plus the page-specific prompt. The thumbnail board is a planning/reference artifact, not a final slide.