Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
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 daymade/claude-code-skills --skill data-visualization-disciplinegit clone --depth 1 https://github.com/daymade/claude-code-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/daymade/claude-code-skills/data-visualization-discipline)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/data-visualization-discipline"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/data-visualization-discipline/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/daymade/claude-code-skills/data-visualization-discipline"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/data-visualization-discipline.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 | $0.00236 | $0.26208 |
| Opus 5.5 | $0.00094 | $0.10483 |
| Sonnet 5.5 | $0.00047 | $0.05242 |
| Haiku 4.5 | $0.00024 | $0.02621 |
Grade A, and why
data-visualization-discipline 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 9d 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 — 748 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数据可视化纪律
这是可视化判断层的唯一权威源。其他 skill 引用它、不复制它——一条规则出现在两处,就多一个将来会矛盾的地方。
边界:什么归我,什么不归我
| 问题 | 归属 |
|---|---|
| 这张图想让读者得出什么结论?该用什么图型?用均值还是中位数?能不能聚合?几个颜色? | 本 skill |
| 报告页怎么排、用哪个组件、什么皮、交互键位、浏览器渲染自验、认可语料 register | report-with-html:report-with-html |
| python-pptx 怎么落原生图表、次轴折线在 QuickLook 不渲染、中文掉字 | deck-creator:deck-creator |
| 图表用什么库实现 | 当前项目已声明的图表栈;没有就先调研选维护中的库,禁止手搓图表引擎 |
参考文件清单见下一节末尾的表(按阶段锚定,一处维护)。
这份 skill 怎么组织的(加规则之前先读这节)
规则按你在什么时刻会想起它排,不按主题分类:定意图 → 验数据 → 选形 → 编码 → 交付前自检。
阶段 1–4 各有一个「交接检查」,阶段 5 是交付闸(9 条)——合起来五个检查点,交付前那道最重。 这不是"一道闸抓所有规则"——那会把闸撑到十几条,而检查清单一超过 9 条就开始被跳过(Gawande)。成熟做法是多个停点各管各的:飞机有滑行、起飞、巡航、落地四张清单,不是一张。所以本 skill 的判据是:
每条规则都必须被五个检查点之一抓住。 不是每条都要进交付闸。
这个轴不是审美选择,是防膨胀装置。一份按主题堆叠的规则集会一直长——每收编一处沉淀就多几节,最后没人读得完,也没人知道新规则该放哪。所以:
加一条新规则前,先回答:它在第几阶段被想起?它的违反被哪个检查点抓住?
- 两个都答得上 → 写进那个阶段,正文里说清判据,并确认那个检查点的产物清单真的会暴露它。
- 答得出阶段、答不出检查点 → 把它加进那个阶段的交接检查(阶段交接不受 9 条预算限制,因为它只在那一刻问一次)。只有当它必须在交付前再查一遍时,才动交付闸——而交付闸是 5–9 条 killer items 的预算,加一条得说清挤掉谁。 这条准入规则同样管存量。 最容易漏的不是新规则——是规则立起来那天已经在文件里的内容,没人回头用它筛一遍("祖父豁免")。但也不能因此开一张无边界重构的许可证,所以判据是有范围的:每次实质改动这份文件时,顺手对你本次已经打开的那一节做一次同样的核对;不为找问题去打开本次不涉及的章节。
写完之后必须机械核一次,别靠记性——把新规则的关键词 grep 一遍,看它在检查点文字里出没出现。0 命中 = 它没挂上任何检查点,回到上面几条重新归位。
三条限定,缺一条这个动作就会骗你:
- 范围要说死:四个「阶段 N 交接检查」引用块 + 交付闸的编号条目正文、产物行、以及豁免表。豁免表要搜,但它的命中意义是相反的——见下一条。
- >0 命中 ≠ 挂上,必须读那一处。命中的可能是"这条闸在查这件事"(真挂上),也可能是"这条闸声明自己不管这件事"(豁免行)。只在豁免行命中 = 反向证据:它恰恰证明这条规则被明确排除在检查范围之外,等同 0 命中,要回去重新归位。
本文件里现成的例子:闸 8 的豁免行写着"纯 KPI 数字卡片",而闸 8 的正文与产物行里 0 次出现这个词。一条讲"KPI 卡片该怎么标"的新规则去 grep,会只命中那一行——把"这条闸不管 KPI 卡片"读成"已经挂上了",方向正好反过来。
- 换 2–3 个同义词再搜一遍:实测过一次假阴性——搜"色盲"全文 0 命中,但文件一直用"色觉障碍"讲同一件事,只搜一个词会误判成"完全没覆盖"。
- 这个动作只对「写进阶段正文」那条出口有验证力。直接写进交接检查的,grep 必然命中(那个词就是你刚放进去的),等于什么都没验证——那条路径要反过来问:"交接检查里这句,正文里有对应的判据吗?"没有的话它是一句无处可查的口令。判定为战例的则整个跳过这一步:战例本来就不该出现在检查点里,0 命中是正确结果,不是失败。
为什么必须机械化:这条准入规则在 2026-07 的一个月里被同一个作者连续违反四次——最典型的一次是他刚写完一条规则、当场忘了挂检查点,而那条规则的正上方就写着"每条规则都必须被某个检查点抓住"。四次都是"我知道有这条规则",四次都没执行:散文提醒对作者本人无效,他正处在"我刚想明白一件事"的兴奋里,那恰是最不会回头自查的时刻。能救的只有一条可以跑的命令。
What ships with it
7 files 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.
- evals/evals.json 1.8 KB
- references/chart-selection-and-statistics.md 14 KB
- references/graphical-perception-science.md 15 KB
- references/monthly-budget-disclosure.md 3.1 KB
- references/operational-state-matrix.md 4.1 KB
- references/transaction-status-colors.md 5.1 KB
- references/visual-form-selection.md 12 KB
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.
- 9d ago Changed · +7 lines 44802524a0e2
- 10d ago Changed · +3 lines a671697635fb
- 23d ago First seen · 738 lines · 236 tokens per session scan A d9156efc3c86
data-visualization-discipline is a skill published in the GitHub repository daymade/claude-code-skills (1,473 stars, last pushed today), licensed MIT. It adds 236 tokens to every session and 26,208 once invoked, about $0.0009 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 2026-09-25.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.