Math Figure

Community

capwitf

math-figure

Use when 高教社杯/CUMCM 数学建模论文需要规划、选择、审查或修复图、图表、表格转图、图注、图像证据行、正文放置、附录降级或图后结论。

Overview

Publisher	capwitf
Repository	`My-MathModeling-skills`
Skill name	`math-figure`
Stars	57
Forks	1
Bundled files	90
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
90 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by capwitf on GitHub. Read the source before you install it.

Installation

Install the Math Figure AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/capwitf/My-MathModeling-skills/tree/main/math-figure
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/capwitf/My-MathModeling-skills.git /tmp/My-MathModeling-skills
mkdir -p .claude/skills
cp -r /tmp/My-MathModeling-skills/math-figure .claude/skills/math-figure

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Math Figure in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Math Figure on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Math Figure is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

图表证据

用途

Select, generate, or review figures that prove a claim. Main-body figures must carry mechanism, comparison, robustness, or decision evidence; diagnostic and dense support figures default to appendix.

Read math-hub/references/quality-contract.md only when promoting a figure to paper-ready, classifying blocked status, running a final gate, or writing a cross-module handoff. Local chart choice or visual repair can stay lightweight.

Figure First Principles

One main-body figure should prove one central claim.
Prefer tables for exact values and figures for patterns, mechanisms, tradeoffs, and robustness.
Do not include every generated figure.
Write a caption, one post-figure conclusion, and one boundary/risk note near the figure.
A figure with unknown source, unit, scenario, baseline, or validation status is not paper-ready.

Evidence Contract

figure_evidence.csv should record figure id, claim id, source output, role, caption target, post_figure_conclusion, risk note, and validation_status.

The validation_status must be paper_ready before a figure supports abstract, conclusion, or final answer wording. Otherwise, keep it planned, generated, checked, blocked, or diagnostic.

A paper_ready figure_evidence.csv row must include either render_check_status=passed or human_visual_check=passed, plus a final-size readability note. A generated file is not paper-ready simply because it exists in an experiment directory.

For simulation figures, raw traces stay appendix unless they directly prove a required mechanism or failure mode. A single-run screenshot is diagnostic, not a paper-ready simulation result.

Selection And Review

Identify the claim the figure must prove.
Select the smallest chart type that makes the claim visible.
Verify source output and units.
Generate or inspect the image.
Check caption, conclusion, and boundary sentence.
Decide main-body versus appendix.
Return blockers to math-code, math-model, math-verifier, or math-hub.

Read references/selection-guide.md for chart selection, references/paper-figure-style.md for Nature-style palette, title, and formal-paper figure defaults, references/high-impact-chart-assets.md when local templates are visually or structurally too weak, references/visual-readiness-loop.md for visual inspection, and math-hub/references/figure-evidence-rules.md when figure evidence rows matter.

When a requested figure matches a reusable chart family, read references/chart-template-index.md, apply references/paper-figure-style.md, and adapt the closest script from assets/high-impact-templates/ after the claim, source output, unit, and evidence boundary are known. Use assets/chart-templates/paper_style.py when a claim needs a bespoke matplotlib chart rather than a vendored Nature pattern. Treat templates as starting assets, not proof; every adapted figure still needs source, caption, post_figure_conclusion, risk note, and validation status.

For main-body figures, read references/paper-figure-style.md and use the Nature-style contest defaults: calm palette, vector-first export, no in-figure title, light grid, readable labels, and a single claim sentence before plotting. Use assets/chart-templates/paper_style.py when writing matplotlib code.

Visual Readiness

Inspect saved figures before labeling them paper-ready. Block or demote when text is unreadable, labels are clipped, units are missing, legends conflict, colors obscure groups, axes mislead, marks overlap, or the figure does not answer its claim.

For final evidence rows, keep figure_id, render_check_status, human_visual_check, and visual_check_note traceable to the saved file. Use the experiment output path until the claim, caption, units, and readability checks clear; only then copy or reference it as a paper figure.

Output Contract

Return:

selected or rejected figures;
figure role and claim id;
caption and post_figure_conclusion;
render or human visual check status;
figure_evidence.csv rows or edits;
main-body versus appendix decision;
blocked figures and repair owner.

Return to hub: math-hub.

Red Lines

Do not treat attractive figures as evidence.
Do not let a figure support a claim without source output and validation status.
Do not use screenshots as final simulation evidence.
Do not hide exact central results in a chart when a table is needed.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 30 more files.

Frequently asked questions

What does the Math Figure AI skill do?

Use when 高教社杯/CUMCM 数学建模论文需要规划、选择、审查或修复图、图表、表格转图、图注、图像证据行、正文放置、附录降级或图后结论。

Why use Math Figure on TypingMind?

Because you install it once and use it with any model. Math Figure is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Math Figure in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/capwitf/My-MathModeling-skills/tree/main/math-figure. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Math Figure?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Math Figure?

As many as you like. As long as a model supports skills, you can use Math Figure with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Math Figure AI skill free?

Yes. It is published on GitHub by capwitf under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Writing Skills

obra

CommunityPopular

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Skill Host Compat

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

图表证据

用途

Figure First Principles

Evidence Contract

Selection And Review

Visual Readiness

Output Contract

Red Lines

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now