chart-selection

chart-selection is a skill for Codex from xiaomaolu/bluue-ai-skills. It costs 52 tokens per session (1,388 once invoked), scanned A, original, MIT.

A chart-selection guide that matches a dataset and the conclusion to communicate with an appropriate chart type. It covers charts for trends, comparisons, composition, flows, and other common data relationships.

In plain words
What is it for?
It helps select charts and define their labels, fields, and visual encodings for reports, dashboards, infographics, and data-visualisation prompts.
Why use it?
Choosing a chart by habit can hide the important pattern or suggest a relationship the data does not support.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit It helps select charts and define their labels, fields, and visual encodings for reports, dashboards, infographics, and data-visualisation prompts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiaomaolu/bluue-ai-skills/chart-selection
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add xiaomaolu/bluue-ai-skills --skill chart-selection
Clone the repo
git clone --depth 1 https://github.com/xiaomaolu/bluue-ai-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for chart-selection

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaomaolu/bluue-ai-skills/chart-selection/github.svg)](https://agentmods.dev/skills/xiaomaolu/bluue-ai-skills/chart-selection)
Your own site
<a href="https://agentmods.dev/skills/xiaomaolu/bluue-ai-skills/chart-selection"><img src="https://agentmods.dev/badge/skills/xiaomaolu/bluue-ai-skills/chart-selection/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for chart-selection

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiaomaolu/bluue-ai-skills/chart-selection"><img src="https://agentmods.dev/badge/skills/xiaomaolu/bluue-ai-skills/chart-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01388
Opus 5.5 $0.00021 $0.00555
Sonnet 5.5 $0.00010 $0.00278
Haiku 4.5 $0.00005 $0.00139

Measured 7d ago against content hash 3ff22c3f0c39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chart-selection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

chart-selection/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

图表选型

优先选择能让读者“一眼看出结论”的图表。适用于任意领域;资金、地址、钱包和链仅为示例,不限制使用范围。

使用方式

  • 先明确一个核心问题或结论,再检查数据是否具有所需的时间、分类、数值、层级或连接字段。没有数据支持时,把结论写成待验证的问题,不编造数值或关系。
  • 根据下面的类型库选图;类型库不是必须覆盖的清单,普通条形图、折线图、散点图等能说清时优先采用。
  • 只要求选型时,简洁给出推荐图、理由、字段与视觉编码;复杂图补一句读法。要求制作时继续完成图表并检查实际渲染。
  • 用于修改已有 prompt 时,只替换相关选图段落,保留其他风格与交付要求。

图表类型库

① 流向 / 转移:资金从哪来、到哪去

  • 桑基图 Sankey:多级流向,宽度 = 金额。
  • 冲积图 Alluvial:同一批对象在不同阶段的分类变化。
  • 弦图 Chord:多个主体之间的双向往来;需要区分方向时明确标示方向。
  • 弧线图 Arc diagram:节点排成一行,上方弧线表示连接,适合地址或机构之间的关联。
  • 力导向网络图 Network:地址、钱包、实体之间的关系与聚类。
  • 流向地图 Flow map:跨地区、跨链的资金路径;链或地区可抽象成节点,抽象节点不暗示地理位置。

② 时间与顺序:什么时候发生、节奏如何

  • 蜂群图 Beeswarm:每个事件一个点,按时间排布,避免重叠。
  • 气泡时间轴 Bubble timeline:时间 + 规模,圆面积编码规模。
  • 条码图 / 带状图 Barcode / Strip plot:密集事件的分布与聚集。
  • 泳道时间线 Swimlane / Gantt:多条链、多个主体并行的时间段。
  • 带注释的折线 Annotated line:趋势 + 关键事件标注。
  • 地平线图 Horizon chart:多条长时间序列的紧凑对比。
  • 日历热力图 Calendar heatmap:按天或按小时的活跃度。
  • 河流图 Streamgraph:多类别随时间的此消彼长。

③ 对比与排名:谁多谁少、怎么变化

  • 哑铃图 Dumbbell:同一对象的前后两个值,例如冻结前 / 冻结后。
  • 斜率图 Slope chart:两个时间点之间各项的升降。
  • 凹凸图 Bump chart:排名随时间的变化。
  • 棒棒糖图 Lollipop:比条形图更轻的排序对比。
  • 瀑布图 Waterfall:从总额到结余的逐项增减,例如被盗 → 冻结 → 兑换 → 剩余;各项必须能按统一口径加减,不能重复扣除同一笔金额。
  • 子弹图 Bullet chart:实际值与目标或阈值的比较。

④ 构成与占比:整体由什么组成

  • 华夫图 Waffle:每格一个单位,适合倍数、百分比的直观对比。
  • 单位图 / 象形图 Unit / Isotype:用重复的小图标表示数量。
  • 马赛克图 Marimekko:列宽 = 规模,列高 = 内部占比。
  • 矩形树图 Treemap:层级构成,面积 = 金额。
  • 圆堆积图 Circle packing:层级构成的柔和版本,适合“大户 + 长尾”。
  • 旭日图 / 冰柱图 Sunburst / Icicle:多层级结构的占比。
  • 比例面积图 Proportional area:几个数量级差异很大的值并排对比;标出数值以辅助准确比较。

⑤ 分布与密度:数值集中在哪里

  • 山脊图 Ridgeline:多组分布的叠放对比。
  • 小提琴图 Violin / 箱线图 Box:分别突出分布形状、分位数与离散程度。
  • 六边形分箱图 Hexbin:大量点的二维密度。
  • 热力矩阵 Heatmap matrix:两个维度交叉的强度,例如链 × 时间段。

⑥ 多维与小图组合

  • 小倍数图 Small multiples:同一种图按类别重复,便于横向比较。
  • 平行坐标 Parallel coordinates:多指标下的对象画像。
  • 雷达图:仅在指标少于 6 个、且需要整体轮廓时使用。

选图原则与核验

  • 先确定要传达的一个结论,再选最能直接呈现它的图。
  • 能用简单图说清的,不用复杂图;复杂图必须配副标题说明读法。
  • 避免饼图超过 5 块、3D 图、双 Y 轴和纯装饰性的环形图。
  • 同一组图里,相同含义的数据用同一种图形编码,保持颜色、单位、类别顺序和尺度含义一致。小倍数图若需不同尺度,明确标注。
  • 面积编码按面积而非半径与数值成正比;流向宽度使用统一尺度;占比写清分母;时间序列写清时间粒度;缺失值不冒充零值。
  • 实际制作后检查标题结论是否有数据支持、图例与标注能否读懂、标签有无重叠,以及数值和编码是否一致。无法查看实际渲染时,明确说明验证范围。

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 79 lines · 52 tokens per session scan A 3ff22c3f0c39

Subscribe to this mod's changes

chart-selection is a skill published in the GitHub repository xiaomaolu/bluue-ai-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,388 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.

Related

chart-selection compared with skills from other repositories

chart-selection next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
chart-selectionxiaomaolu/bluue-ai-skillsSkill62d agoMITA52Codex
webgl-holographic-foilnexu-io/open-designSkill106ktodayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106ktodayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106ktodayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34ktodayMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6ktodayMITA47Claude Code