Research-Pi: Skill for Claude Code

.pi/skills/research-html/SKILL.md

research-html is a skill for Claude Code, Codex from RosMarinas/Research-Pi. It costs 63 tokens per session (2,221 once invoked), scanned A, original, MIT.

A guide for turning research plans, system processes, or technical explanations into interactive HTML documents that work offline. It covers diagrams, evidence, formulas, and document structure.

In plain words
What is it for?
Use it to create offline research reports, process diagrams, evidence-based explanations, and technical documents with expandable sections.
Why use it?
It helps present complex research clearly without relying on a live website or adding charts and controls that do not answer the reader’s question.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is RosMarinas/Research-Pi's own configuration. It tells Claude Code and Codex how to work on Research-Pi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Research-Pi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RosMarinas/Research-Pi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RosMarinas/Research-Pi/main/.pi/skills/research-html/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/RosMarinas/Research-Pi

Made for: Claude Code, 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 research-html

README.md
[![agentmods](https://agentmods.dev/badge/skills/rosmarinas/research-pi/research-html/github.svg)](https://agentmods.dev/skills/rosmarinas/research-pi/research-html)
Your own site
<a href="https://agentmods.dev/skills/rosmarinas/research-pi/research-html"><img src="https://agentmods.dev/badge/skills/rosmarinas/research-pi/research-html/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 research-html

Your own site · 80×15
<a href="https://agentmods.dev/skills/rosmarinas/research-pi/research-html"><img src="https://agentmods.dev/badge/skills/rosmarinas/research-pi/research-html.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,221 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 $0.00063 $0.02221
Opus 5.5 $0.00025 $0.00888
Sonnet 5.5 $0.00013 $0.00444
Haiku 4.5 $0.00006 $0.00222

Measured 9d ago against content hash daabc00266a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

research-html 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.

The scan reads SKILL.md. This mod also ships 1 executable file (runtime/fonts.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.pi/skills/research-html/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research HTML

这是一份完整的创作规范。直接使用本包组件与资源,无需串联其他设计、写作或可视化 skill。所有创作规则在此;具体语法按需查 components.md,来源记录不参与日常创作。

从读者的问题组织内容

先确定读者需要理解的关系、判断或选择,再选择表现形式。一个比较表能说清就用表;流程关系用图;参数探索确实有用时才增加互动。不要为填充模板添加图表、决策、指标卡或工具栏。

默认采用左侧目录、编号折叠章节、宽主文列、图下状态说明。顶层标题连起来能读懂主线,展开层提供机制与证据,通常不超过三层。每个单元围绕一个主要问题,按研究含义而非文件名拆分;有明确用户版式时遵循该版式。

写作与证据

  • 默认中文;用户指定英文时使用简洁技术英语。状态、事件、API、变量、命令和领域关键词保留英文,首次出现按读者需要解释。同一概念使用同一名称,不逐句重复中英翻译。
  • 标题表达判断或待解问题;节点标概念;箭头标条件或传递内容;图注说明读图所需的关系与边界;展开层给依据。按钮写清点击的结果。
  • 先说当前判断,再解释理由与条件。用具体主语和动词,一段推进一个问题。标题能扫读,正文能连读;不把正常说明切成电报式片段,不用营销口号代替机制。
  • 保留否定、比较对象、适用范围、条件、时间、完成状态和归因。观察、解释、机制猜测与尚未执行的方案分清;不能把“可能”“预期”润色成“已证实”。缺少信息就标明未知,不补造数字或来源。
  • 只修改实际的重复、空话和歧义。自然不等于强行口语化;连接词、被动句、三项列表、四字词和专业术语不设机械黑名单。已通顺的文字可保留。
  • 润色不改数值、代码、ID、路径、链接或 LaTeX。真实源码引用路径和行号,提议代码标 sketch;设计图不证明行为已经实现。收尾核对有无遗漏、强化或错误归因。

例:“CPU worker 解码输入并构造 batch”比“全面协同释放系统潜能”有信息;“该次运行的取样窗口内队列多次为空”不能改成“输入供给始终不足”。更多资源带来的耗时下降,不能直接称为同资源算法效率提升。

流程与状态图

  • 生命周期用 doc-machine;组件或数据流用 doc-flow;参与者之间的先后交互用 doc-seq。保持三种语义清楚,不将调用、状态和数据流混为同一类边。
  • 节点与事件用简短英文关键词,完整中文说明放在图旁或图下。主路径沿稳定方向,分支和回路单独布线;状态机优先显式网格。标签避开节点与箭头。
  • 点击状态显示对应说明、示意界面或证据。选择状态只是浏览演示,不启动实验。重要内容不依赖 hover 才能读到。
  • 虚线、颜色和终态描边都有明确含义,并用文字或图例解释。失败、取消、重试和完成按实际语义区分,重试次数不凭空编造。
  • 根据最终显示尺寸检查可读性。窄屏先重排或分图,必要时局部横向滚动;不要整体缩小到标签不可读。示例的 readable-graph 类为宽状态图保留滚动空间。

数据图表

先确定比较对象、单位、样本或时间范围、聚合方式及来源,再选图:配置比较用点/柱或配对图,趋势用曲线与观测点,取舍用散点,波动用原始点与适当分布,CPU/GPU/通信重叠用共享时间轴。图的数量取决于有效比较,不追求模板多样。

  • 视觉编码准确:柱长、面积、颜色各自对应声明的量;半径不直接等于面积值。明确对数轴、截断、归一化、平滑和单位转换。重叠阶段耗时不能直接相加。
  • 同类比较尽量共享尺度和颜色。轴范围覆盖真实点、区间及相关参考线;误差带来自实际计算。缺测与零值分开,插值与观测分开,示例数据明确标注。
  • 提示框指向真实记录或明确的聚合值;筛选同时更新系列、图例和说明。装饰不伪装成样本。窄屏重排图例和次要刻度,保留单位、长标签与关键数据;触屏和键盘可访问必要细节。
  • 出版级科研图使用标准绘图工具并保留独立可导出的图件。普通 HTML 中的轻量 SVG/Canvas 可直接编写,本包不附带统计图模板库或某个宿主专用 API。

排版、颜色与字体

以暖白 #faf9f5、白色内容面、深灰 #141413、细边框和陶土橙 #c6613f 为默认。颜色表达稳定角色;橙色强调当前状态或重点,不平均撒满页面。留白与字号体现层级,不用大量卡片、渐变或持续动画制造层级。

正文、主标题、节标题与一般节点默认用清晰无衬线;用户明确选择时主标题可用衬线;代码、变量和事件标签用等宽;公式使用数学字体。字体、间距和颜色通过 CSS 变量统一管理。正文保持舒适行距和阅读宽度,装不下时改写、分层或重排,不牺牲条件和准确性。

runtime/fonts/ 已内置 Inter 可变字体、思源黑体 CN 的 Regular/Bold 字符分片和 JetBrains Mono Regular,默认主标题也用无衬线。思源衍生字体在文件内命名为 Research Han Sans;回退为苹方/微软雅黑与系统等宽。保留原始 OFL 许可。

Read the full file on GitHub · 73 lines

Files

What ships with it

60 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.

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. 9d ago First seen · 73 lines · 63 tokens per session scan A daabc00266a4

Subscribe to this mod's changes

research-html is a skill published in the GitHub repository RosMarinas/Research-Pi (7 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 2,221 once invoked, about $0.0003 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 2026-10-28.

Related

research-html compared with skills from other repositories

research-html next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
research-htmlRosMarinas/Research-PiSkill7yesterdayMITA63Claude Code, Codex
read-aloud-edge-ttsusefulmove/ensoSkill25mo agoMITA43Claude Code, Codex
google-drive-sheetsyc-software/qmSkill16kyesterdayMITA32Claude Code, Codex
last30Dayschaitanyagiri/munder-difflinSkill9.3k6d agoMITA83Claude Code
thisQuarterchaitanyagiri/munder-difflinSkill9.3k6d agoMITA78Claude Code
thisWeekchaitanyagiri/munder-difflinSkill9.3k6d agoMITA77Claude Code
harnessrevfactory/harnessSkill9.3k1mo agoApache-2.0A184Claude Code