Editable Figure Designer
yzhao062/anywhere-agents
Designs editable PowerPoint overview figures, especially Figure 1 for papers and proposals, from source material and the author's own visual preferences.
Rebuilds or restyles diagrams as editable native Visio shapes from a reference image or .vsdx file, then exports .vsdx, PNG, SVG, PDF or PPTX.
$ npx skills add pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pengjunchi0/codex-visio-paper-figure-skill visio-image-rebuilder --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 "visio-image-rebuilder" agent skill from https://github.com/pengjunchi0/codex-visio-paper-figure-skill/tree/main into .claude/skills/visio-image-rebuilder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visio-image-rebuilder", 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 pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pengjunchi0/codex-visio-paper-figure-skill visio-image-rebuilder --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "visio-image-rebuilder" agent skill from https://github.com/pengjunchi0/codex-visio-paper-figure-skill/tree/main into .agents/skills/visio-image-rebuilder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visio-image-rebuilder", 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 pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pengjunchi0/codex-visio-paper-figure-skill visio-image-rebuilder --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 "visio-image-rebuilder" agent skill from https://github.com/pengjunchi0/codex-visio-paper-figure-skill/tree/main into .cursor/skills/visio-image-rebuilder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visio-image-rebuilder", 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 pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pengjunchi0/codex-visio-paper-figure-skill visio-image-rebuilder --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 "visio-image-rebuilder" agent skill from https://github.com/pengjunchi0/codex-visio-paper-figure-skill/tree/main into .gemini/skills/visio-image-rebuilder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visio-image-rebuilder", 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 pengjunchi0/codex-visio-paper-figure-skill visio-image-rebuilderInstalls 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 pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -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 "visio-image-rebuilder" agent skill from https://github.com/pengjunchi0/codex-visio-paper-figure-skill/tree/main into .github/skills/visio-image-rebuilder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visio-image-rebuilder", 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 pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pengjunchi0/codex-visio-paper-figure-skill visio-image-rebuilder --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 "visio-image-rebuilder" agent skill from https://github.com/pengjunchi0/codex-visio-paper-figure-skill/tree/main into .opencode/skills/visio-image-rebuilder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visio-image-rebuilder", 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.
visio-image-rebuilderRebuilds or restyles diagrams as editable native Visio shapes from a reference image or .vsdx file, then exports .vsdx, PNG, SVG, PDF or PPTX.
The core rule is that a rebuild must produce real Visio content, never a page with the reference picture pasted in. A reference image may serve only as a temporary tracing layer, and it has to be removed or hidden before delivery so the .vsdx keeps native shapes, text, connectors and groups. The .vsdx file is treated as the source of truth, and PNG, SVG, PDF or PPTX exports come only after the page has been rebuilt and checked.
The workflow starts by confirming paths, exporting the current page to PNG, inspecting the package and backing up the target before any write. The reference is then decoded into an inventory of containers, titles, boxes, icons, charts, connectors and captions, with the canvas and each major panel calibrated by explicit bounds before small details are drawn. Edits go through Visio COM automation on Windows, with package XML edits kept for narrow, deterministic changes. PowerShell scripts cover page tools, a rebuild scaffold and format export, and a reference file holds rebuild guidelines.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 816960d. 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.
Ships 3 files in scripts/ (PowerShell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From 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.
Visio Image Rebuilder loads about 2k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 146 tokens; SKILL.md has 966 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); the scripts in this folder are not scanned.
The full file from pengjunchi0/codex-visio-paper-figure-skill at commit 816960d, republished under its MIT licence (© pengjunchi0). 966 words, ~2,035 tokens.
.claude/skills/visio-image-rebuilder/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.Recreate the reference as editable Visio content. Do not satisfy a rebuild request by inserting the whole reference image into the page. Embedding the reference image is only allowed as a temporary locked tracing layer if it is removed or hidden before delivery and the final .vsdx remains native shapes, text, connectors, and groups.
Treat .vsdx as the source of truth. Export PNG, SVG, PDF, or PPTX only after the Visio page has been rebuilt or restyled and checked for native editability.
Inspect inputs.
.vsdx, reference image, requested output formats, and output directory..vsdx package for pages, media entries, and shape counts.Decode the reference image.
Prefer Visio automation for native edits.
DrawRectangle, DrawOval, DrawLine, Page.Import only for small source assets, and shape cells such as FillForegnd, LineColor, LineWeight, Char.Size, Char.Color, Rounding.RectRel, TextRel, LineRel, and OvalRel so child shapes are constrained by their calibrated parent panel.Use package XML edits only for narrow, deterministic changes.
Cell nodes should be before Section, Text, or child Shapes.Export requested formats from the verified Visio source.
scripts/visio_page_tools.ps1 for export-only jobs.scripts/visio_rebuild_scaffold.ps1 with -ExportFormats for rebuilds that should immediately create deliverables.Verify without overtrusting a single signal.
.vsdx package to confirm that no full-size reference PNG/JPG was left in visio/media.For full rebuilds, generate a script that:
.vsdx with Visio COM.Start from scripts/visio_rebuild_scaffold.ps1 when building a full reconstruction script. Copy it into the workspace and customize the Draw-ReferenceFigure function rather than editing the skill copy.
For style transfer, generate a script that:
.vsdx has been saved and inspected.For export-only requests, run:
powershell -ExecutionPolicy Bypass -File scripts\visio_page_tools.ps1 `
-VsdxPath "C:\path\figure.vsdx" `
-ExportFormats svg,pdf,pptx `
-OutputDir "C:\path\exports" `
-InspectPackageFor rebuild plus multi-format export, run:
powershell -ExecutionPolicy Bypass -File scripts\visio_rebuild_scaffold.ps1 `
-VsdxPath "C:\path\figure.vsdx" `
-PageW 16 `
-PageH 9 `
-RefW 1600 `
-RefH 900 `
-PreviewPath "C:\path\exports\figure.png" `
-ExportFormats svg,pdf,pptx `
-OutputDir "C:\path\exports"A Visio rebuild is acceptable only when:
.vsdx package has no full-page raster reference image in visio/media..vsdx and are non-empty.Use scripts/visio_page_tools.ps1 for common inspection, backup, preview export, multi-format export, and package checks. Use scripts/visio_export_formats.ps1 when a custom task script needs reusable export helpers. Use scripts/visio_rebuild_scaffold.ps1 as the starting point for native-shape drawing scripts; it includes both global top-left helpers and panel-local calibrated helpers. Read references/rebuild-guidelines.md when a task requires a full figure reconstruction or careful one-to-one scientific diagram matching.
© pengjunchi0, 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 7 other files (scripts, references) in the repository root of pengjunchi0/codex-visio-paper-figure-skill.
Open the folder on GitHubat commit 816960d
Visio Image Rebuilder 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 |
|---|---|---|---|---|---|---|
| Visio Image Rebuilder this skillpengjunchi0/codex-visio-paper-figure-skill | 1k | — | ~2k | Automated safety check: Pass | MIT | |
| Editable Figure Designeryzhao062/anywhere-agents | 253 | — | ~7.2k | Automated safety check: Pass | Apache-2.0 | |
| Xiaobei Skill Image To Vbaxiao24bei/xiaobei-skill | 586 | — | ~6.9k | Automated safety check: Pass | Apache-2.0 | |
| Cn Academic Spark Ppt Enginewycmochi/cn-academic-spark | 121 | — | ~8.9k | Automated safety check: Notes | MIT | |
| Ccf Visual Composermikubaka88/CCFA-Skills | 3k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Astra Figure WorkflowIamJerryXu/AstraDraw | 148 | — | ~1.9k | Automated safety check: Pass | None |
yzhao062/anywhere-agents
Designs editable PowerPoint overview figures, especially Figure 1 for papers and proposals, from source material and the author's own visual preferences.
xiao24bei/xiaobei-skill
A skill your agent uses when users want XiaoBei skill / xiaobei-skill / 小北在读研 style academic image-to-VBA reconstruction: convert academic figures, scientific diagrams, slides, screenshots, or other…
wycmochi/cn-academic-spark
Convert a complete academic source package, such as a paper, report, proposal, review outline, PDF, Word document, Markdown file, or pasted text, into a Chinese academic .pptx deck.
mikubaka88/CCFA-Skills
Render and redesign CCF figures, visual tables, and method/architecture diagrams from supplied content.
IamJerryXu/AstraDraw
Design research method figures from an existing paper, retrieve visual priors from component or private PPTX libraries, produce editable diagrams, and revise selected objects while preserving…
xstongxue/best-skills
根据论文或汇报内容生成多页 Draw.io 格式 PPT,支持论文答辩与通用汇报两种模式,自动导出为 .pptx。当用户提到论文答辩 PPT、答辩幻灯片、通用 PPT、汇报 PPT、根据模板生成 PPT、drawio2pptx 时使用。
Works with
Categories
Rebuilds or restyles diagrams as editable native Visio shapes from a reference image or .vsdx file, then exports .vsdx, PNG, SVG, PDF or PPTX. The core rule is that a rebuild must produce real Visio content, never a page with the reference picture pasted in.vsdx keeps native shapes, text, connectors and groups.
Visio Image Rebuilder fits situations like: recreating a diagram from a PNG, JPG or screenshot as an editable Visio file; changing colors, typography or layout in an existing .vsdx; fixing shifted or overlapping submodules in a multi-panel scientific figure; exporting a finished Visio page as PDF, SVG or PPTX for a paper or slides.
Run `npx skills add pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -a claude-code`. Or copy the skill folder (the pengjunchi0/codex-visio-paper-figure-skill repository) into .claude/skills/visio-image-rebuilder in your project. Claude Code loads it when a task matches its description.
Run `npx skills add pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -a codex`. Or copy the skill folder (the pengjunchi0/codex-visio-paper-figure-skill repository) into .agents/skills/visio-image-rebuilder 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 pengjunchi0/codex-visio-paper-figure-skill --skill visio-image-rebuilder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visio-image-rebuilder, .gemini/skills/visio-image-rebuilder, .github/skills/visio-image-rebuilder and .opencode/skills/visio-image-rebuilder in your project.
Going by SKILL.md and its folder, Visio Image Rebuilder needs PowerShell for the scripts in its folder. Our summary lists: Windows with Microsoft Visio installed; PowerShell.
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.
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.
Visio Image Rebuilder 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.
About 2k tokens (SKILL.md is roughly 8.1k 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 2.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Visio Image Rebuilder: Editable Figure Designer (yzhao062/anywhere-agents, 253 stars), Xiaobei Skill Image To Vba (xiao24bei/xiaobei-skill, 586 stars), Cn Academic Spark Ppt Engine (wycmochi/cn-academic-spark, 121 stars) and Ccf Visual Composer (mikubaka88/CCFA-Skills, 3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
pengjunchi0 (a GitHub user) maintains it in pengjunchi0/codex-visio-paper-figure-skill, which has 1,006 GitHub stars. The repository was last updated on August 16, 2026.
Source: pengjunchi0/codex-visio-paper-figure-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.