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.
npx skills add xiaomaolu/bluue-ai-skills --skill chart-selectiongit clone --depth 1 https://github.com/xiaomaolu/bluue-ai-skillsWrote 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.
[](https://agentmods.dev/skills/xiaomaolu/bluue-ai-skills/chart-selection)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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。
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.
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.
- 7d ago First seen · 79 lines · 52 tokens per session scan A 3ff22c3f0c39
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.
chart-selection compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chart-selectionxiaomaolu/bluue-ai-skills | Skill | 6 | 2d ago | MIT | A | 52 | Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 47 | Claude Code |