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.
curl -O https://raw.githubusercontent.com/RosMarinas/Research-Pi/main/.pi/skills/research-html/SKILL.mdgit clone --depth 1 https://github.com/RosMarinas/Research-PiWrote 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/rosmarinas/research-pi/research-html)<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.
<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>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 | $0.00063 | $0.02221 |
| Opus 5.5 | $0.00025 | $0.00888 |
| Sonnet 5.5 | $0.00013 | $0.00444 |
| Haiku 4.5 | $0.00006 | $0.00222 |
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.
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 — 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。
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.
- examples/research-pi.html 5.8 KB
- PROVENANCE.md 3.4 KB
- references/components.md 5.8 KB
- runtime/fonts.mjs 1.6 KB runs code
- runtime/fonts/fonts.css 153 KB
- runtime/fonts/han-400-000.woff2 59 KB
- runtime/fonts/han-400-001.woff2 57 KB
- runtime/fonts/han-400-002.woff2 56 KB
- runtime/fonts/han-400-003.woff2 54 KB
- runtime/fonts/han-400-004.woff2 58 KB
- runtime/fonts/han-400-005.woff2 53 KB
- runtime/fonts/han-400-006.woff2 59 KB
- runtime/fonts/han-400-007.woff2 58 KB
- runtime/fonts/han-400-008.woff2 58 KB
- runtime/fonts/han-400-009.woff2 55 KB
- runtime/fonts/han-400-010.woff2 59 KB
- runtime/fonts/han-400-011.woff2 56 KB
- runtime/fonts/han-400-012.woff2 56 KB
- runtime/fonts/han-400-013.woff2 54 KB
- runtime/fonts/han-400-014.woff2 43 KB
- runtime/fonts/han-400-015.woff2 19 KB
- runtime/fonts/han-400-016.woff2 19 KB
- runtime/fonts/han-400-017.woff2 20 KB
- runtime/fonts/han-400-018.woff2 18 KB
- runtime/fonts/han-400-019.woff2 27 KB
- runtime/fonts/han-400-020.woff2 48 KB
- runtime/fonts/han-400-021.woff2 37 KB
- runtime/fonts/han-400-022.woff2 29 KB
- runtime/fonts/han-400-023.woff2 55 KB
- runtime/fonts/han-400-024.woff2 46 KB
- runtime/fonts/han-400-025.woff2 54 KB
- runtime/fonts/han-400-026.woff2 64 KB
- runtime/fonts/han-400-027.woff2 66 KB
- runtime/fonts/han-400-028.woff2 58 KB
- runtime/fonts/han-400-029.woff2 61 KB
- runtime/fonts/han-400-030.woff2 70 KB
- runtime/fonts/han-400-031.woff2 59 KB
- runtime/fonts/han-400-032.woff2 74 KB
- runtime/fonts/han-400-033.woff2 67 KB
- runtime/fonts/han-400-034.woff2 67 KB
- runtime/fonts/han-400-035.woff2 63 KB
- runtime/fonts/han-400-036.woff2 64 KB
- runtime/fonts/han-400-037.woff2 66 KB
- runtime/fonts/han-400-038.woff2 72 KB
- runtime/fonts/han-400-039.woff2 76 KB
- runtime/fonts/han-400-040.woff2 64 KB
- runtime/fonts/han-400-041.woff2 66 KB
- runtime/fonts/han-400-042.woff2 74 KB
- runtime/fonts/han-400-043.woff2 69 KB
- runtime/fonts/han-400-044.woff2 68 KB
- runtime/fonts/han-400-045.woff2 75 KB
- runtime/fonts/han-400-046.woff2 71 KB
- runtime/fonts/han-400-047.woff2 76 KB
- runtime/fonts/han-400-048.woff2 86 KB
- runtime/fonts/han-400-049.woff2 85 KB
- runtime/fonts/han-400-050.woff2 43 KB
- runtime/fonts/han-400-051.woff2 52 KB
- runtime/fonts/han-400-052.woff2 58 KB
- runtime/fonts/han-400-053.woff2 58 KB
- runtime/fonts/han-400-054.woff2 46 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 First seen · 73 lines · 63 tokens per session scan A daabc00266a4
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.
research-html compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research-htmlRosMarinas/Research-Pi | Skill | 7 | yesterday | MIT | A | 63 | Claude Code, Codex |
| read-aloud-edge-ttsusefulmove/enso | Skill | 2 | 5mo ago | MIT | A | 43 | Claude Code, Codex |
| google-drive-sheetsyc-software/qm | Skill | 16k | yesterday | MIT | A | 32 | Claude Code, Codex |
| last30Dayschaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 83 | Claude Code |
| thisQuarterchaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 78 | Claude Code |
| thisWeekchaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 77 | Claude Code |
| harnessrevfactory/harness | Skill | 9.3k | 1mo ago | Apache-2.0 | A | 184 | Claude Code |