跳到正文
cccskills
免费在 GitHub 公开

figure-table-planner

Plan the smallest set of diagnostic, comparison, paper, and appendix figures or tables needed to support verified mathematical-modeling decisions and claims.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Purpose

Make every visual evidence-bearing. Prefer fewer useful visuals over a decorative inventory.

Inputs

  • method card and decision ledger;
  • run summaries and final result analysis;
  • robustness evidence;
  • solution package and frozen numbers in submission mode;
  • existing figures/tables.

Figure Types

  • Type 1 diagnostic: internal debugging; never in the paper.
  • Type 2 comparison: main vs usable baseline or a genuinely tested alternative; optional in paper.
  • Type 3 paper: directly supports a main claim; required only when the claim benefits materially from a visual.
  • Type 4 appendix: supplementary evidence referenced from the main text.

Workflow

  1. List verified claims that need visual or exact tabular support.
  2. Reuse an existing artifact when it already communicates the claim.
  3. For each proposed visual record:
    • ID and Qx;
    • type;
    • source artifact and frozen claim IDs when applicable;
    • one core claim;
    • chart/table form;
    • target section;
    • status and render needs.
  4. Ask the human to confirm judgment-bearing Type 3 claims through one compact choice card when they are not already in the decision ledger.
  5. Save methods/Qx/qx_figure_table_plan.md only when durable planning is needed. In lean exploration, a compact in-conversation plan is sufficient.

Planning Heuristics

  • Use tables for exact values, parameters, and small comparisons.
  • Use plots for trends, distributions, sensitivity, or many-item comparisons.
  • Use diagrams for mechanisms, dependencies, and workflows.
  • A main-vs-baseline figure needs compatible metrics and the same evaluation setup.
  • Do not create a multi-method comparison merely to imply breadth.

Rules

  • Type 1 never enters the paper.
  • Type 3 uses final validated sources and a human-confirmed core claim.
  • Do not use unresolved exploratory figures as paper evidence.
  • Do not fabricate data, captions, or claims.
  • Do not fill plans with placeholder sentinels; pause for one human choice instead.
  • Every visual must have a source and purpose.

Verification

  • Each planned visual supports a verified claim.
  • Types, sources, sections, and statuses are explicit.
  • Type 3 claims trace to human decisions and frozen evidence.
  • No unnecessary or decorative visual remains.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Detect whether approved modeling code is Python or MATLAB/Beita Tianyuan and route it to the matching reviewer using the compact named-check review contract.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10602026年9月24日 更新

Audit whether the semantic evidence required by the active lean or submission profile exists and is current, without requiring one verbose artifact per skill or an arbitrary number of pass bullets.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10602026年9月24日 更新

Run scoped or final cross-media consistency checks for mathematical-modeling artifacts, comparing canonical numbers, symbols, parameters, decisions, files, and paper claims without performing full-workspace audits for low-risk changes.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10602026年9月24日 更新

Map contest attachments to subquestions, audit and clean raw data, and emit one reusable data profile with quality, coverage, imbalance, concentration, and method-readiness evidence for downstream risk screening.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10602026年9月24日 更新

Build one compact choice card at a genuine mathematical-modeling judgment point. Use before method screening, after a meaningful experiment, or before final claim/freeze approval so the human chooses the trade-off while AI handles mechanical consequences.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10602026年9月24日 更新

Build the authoritative final method explanation for a submission-ready subquestion from the method card, human decision ledger, code plan, final results, and robustness evidence.

中文简介正在准备中。当前显示原文说明。

zhnnky329/MathModeling-skills10602026年9月24日 更新

查看 zhnnky329 的全部技能

报告此技能的问题