Vivid Illustration Skill
A scientific graphics skill with 148 chart templates, 196 SVG architecture assets and export to editable PowerPoint
- 816 ★ on the repository
- Last commit
Extended access
Why this level
- The agent runs Python code to draw charts and launches Chromium for diagrams on your machine.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/vivid-illustration-skillDetects 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 agent runs Python code to draw charts and launches Chromium for diagrams on your machine.
This is third-party code. Review the repository files before installing.
What it does
Vivid Illustration Skill helps an agent produce illustrations for papers, modelling and reports. The repository holds 148 data chart templates (145 recipes and 3 complete sets), 196 SVG architecture assets and 7 colour palettes. The main `SKILL.md` only identifies the task and hands it to one of two channels: `vivid-figure-skill` for charts of real data or `vivid-architecture-diagram-skill` for system and method diagrams. The agent reads only the needed channel, selects a template, moves the data into it, checks the result and fixes it. Charts come out as an image plus source code; diagrams as SVG, PDF, native PPTX with editable text and modules, and a font pack. A local web page lets you pick and edit charts by hand.
Who it is for. Researchers and students who prepare a paper or report and want an agent to build charts and diagrams from ready templates.
Good fit when
- A paper needs charts comparing methods, distributions and errors from a results table.
- A model architecture diagram has to be prepared as SVG and handed to colleagues in PowerPoint with editable text.
- A whole series of figures must be brought to one colour palette and style.
- You want to pick a chart in a local web gallery and edit labels without code.
Not a fit when
- The result goes into a commercial product: the license forbids commercial use.
- The project must be modified and released as a derivative: not allowed without written permission.
- Interactive dashboards are needed rather than static scientific figures.
Example request
From this results table build a comparison chart of three methods with confidence intervals in a palette from the skill and return the image with the source code.Limitations
The license permits only personal non-commercial use; derivative work and commercial use need the author's written consent. Python 3.10 or newer and the dependencies from `requirements.txt` are needed, plus `requirements-architecture.txt` and Chromium for Playwright for diagrams and PPTX. The agent must be able to read files, run code and view images. The whole repository is installed as one: the sub-channels in `channels/` do not work alone. Descriptions and texts are mostly in Chinese and there is no Russian interface.
How to disable. Delete the `vivid-illustration-skill` folder and its `.venv` virtual environment. Working projects live in `workbench/workspace/`; save them before deleting.
FAQ
How do I install Vivid Illustration Skill?
Clone the whole repository, create a virtual environment and install `requirements.txt`. Detailed steps for Windows, macOS and Linux are in `docs/INSTALL.md`.
How do the two channels differ?
The data channel builds charts from numbers and tables, the architecture channel draws system and method diagrams in SVG. A task is routed by content rather than by file format.
Is PowerPoint needed to export PPTX?
No, native PPTX is produced without Office. Microsoft PowerPoint is needed only for verification on Windows.
Can the output be used in a commercial project?
No. The license limits use to personal non-commercial purposes; anything else needs the author's written permission.
Is a Chinese font needed?
For Chinese labels on charts, yes: on Linux install Noto Sans CJK, while Windows and macOS usually already have suitable fonts.
Discussion
No questions or reviews yet.
Related
SkillsA skill that picks a scientific chart from nearly 100 templates for CSV or Excel data and outputs PNG, SVG, PDF and Python code.
A skill for scientific figures to Nature, Cell and Science standards: 29 figure types, data checks and vector PDF output.
A Python and R skill for publication figures with a contract, layout QA and independent export, plus the FigureForge editor
A data visualization skill for agents: turns data into polished interactive HTML charts and full reports with one visual language
SciPilot Figure
scipilot-figure-skill
A scientific visualization advisor skill: it profiles the data and picks a chart for the argument first, then renders it to journal-grade quality
A skill that builds scientific figures from a table: it offers 2–3 chart candidates, assembles panels and checks image reuse.
README in short
The README introduces the two channels, a capability table, architecture examples, seven palettes and ready prompts. A separate section covers capability limits and the repository layout, and the personal non-commercial license is stated at the start.
README badge
Original SKILL.md
--- name: vivid-illustration-skill description: 科研与数学建模绘图总入口，按任务分派到独立的数据图或架构图子 Skill；支持完整图集规划、数据模板适配、SVG 架构设计及可编辑 PPTX 交付。 --- # Vivid Illustration Skill · 绘图总入口 本入口只负责识别任务与分派。先确定下面的通道，只读取所选子 Skill 及其当前任务需要的引用，不预先加载另一通道。用户直接指定通道、模板或已有作品时沿用选择。 | 当前任务 | 读取的子 Skill | |---|---| | 真实数据、统计结果、实验对比、分布、时序、空间数据、完整组合模板 | [数据图 · vivid-figure-skill](channels/vivid-figure-skill/SKILL.md) | | 系统/模型架构、方法框架、技术路线、结构示意、已有 SVG 修改、架构图可编辑 PPT；用户指定的 Draw.io/TikZ/HTML/Mermaid 技术图 | [架构图 · vivid-architecture-diagram-skill](channels/vivid-architecture-diagram-skill/SKILL.md) | 按要表达的内容分派，不按最终文件扩展名分派：数据曲线即使交付 SVG/PDF，仍属于数据图；包含数值的系统结构图也不因此改走统计绘图。边界不明时先读取用户材料，确认需要表达的是量值证据还是对象关系；无法判断且会改变结果时再澄清。 ## 完整图集与混合任务 完整论文或整题图集先读 [上游规划](original/upstream-planning.md) 与 [绘图入口](original/resources/ENTRYPOINT.md)，维护同一份 FIGURE_PLAN / FIGURE_MANIFEST，再按每项类别分派到对应子 Skill。分类、执行顺序、来源与最终对账沿用规划合同。 混合任务共享用户事实、图内语言和项目设置，不共享两条通道的制作限制：数据图按数据图的源码保真与验收；SVG 架构图按架构图的字体/图案与候选交付流程。可以分别执行；给独立生成任务只传其通道、必要输入与输出目录。明确单图或用户限定的小批任务不重启整题规划。 科学场景插图按 [绘图入口](original/resources/ENTRYPOINT.md) 中相应路线处理，不用插图代替数据证据或精确结构。 ## 路径与接入 `<SKILL>` 始终指本文件所在的完整包根目录；`<RES>` 为 `<SKILL>/original/resources`，`<WORKSPACE>` 为当前任务工作区。两个子 Skill 位于 `channels/` 内，读取子入口不会改变这些根路径。工作区中的 `_utils/`、`figures/` 和 `.vivid/` 不属于安装目录。 两个通道共用一份资源包，既可从本入口分派，也可直接读取相应子 `SKILL.md`。不要单独复制子目录安装；宿主是否自动发现嵌套 Skill 由其自身决定。安装与直接调用方式见 [安装说明](docs/INSTALL.md)。 [本地工作台](workbench/index.html) 提供图库与编辑入口，操作和自动化范围见 [工作台说明](workbench/README.md)。文件式 Skill 与网页 Agent 的执行边界在对应通道说明中定义。