SenseNova-Skills is a collection of modular skills that extend SenseNova models with office-assistant capabilities such as image generation, presentation creation, spreadsheet analysis, and research. The skills are designed for use in agent runtimes and can be combined into productivity workflows; the catalogue entries are individual skills and agents from this collection.
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 OpenSenseNova/SenseNova-Skills --skill sn-md-to-html-reportgit clone --depth 1 https://github.com/OpenSenseNova/SenseNova-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/opensensenova/sensenova-skills/sn-md-to-html-report)<a href="https://agentmods.dev/skills/opensensenova/sensenova-skills/sn-md-to-html-report"><img src="https://agentmods.dev/badge/skills/opensensenova/sensenova-skills/sn-md-to-html-report/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/opensensenova/sensenova-skills/sn-md-to-html-report"><img src="https://agentmods.dev/badge/skills/opensensenova/sensenova-skills/sn-md-to-html-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.02297 |
| Opus 5 | $0.00069 | $0.01149 |
| Sonnet 5 | $0.00028 | $0.00459 |
| Haiku 4.5 | $0.00014 | $0.00230 |
Grade A, and why
sn-md-to-html-report 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report HTML
把报告文本创作为一份有编辑判断、网页美感、证据秩序、且只属于这份主题的单文件 HTML。
核心原则:保留事实断言,重构阅读和视觉体验,让设计从报告所属领域和内容任务里长出来。主题自己的世界——它的材质、工具、器物与语汇——是产生独特设计选择的来源。
设计判断原则
- 首屏即论点:首屏先找到这份报告所属领域里最有识别度、最能承载主题气质的事物或机制,并用最适合它的形式呈现:标题、图片、动画、实时演示或一个可互动瞬间。这个选择必须有明确判断;不要默认使用“大数字 + 小标签 + 辅助统计 + 渐变强调”,只有当它确实是主题最自然、最有力的入口时才使用。
- 文字系统承载页面性格:标题字体与正文字体要被有意搭配,不要沿用任何项目都能套上的常用字体组合;同时建立清晰的字阶,并有意识地设置字重、字宽和间距。让文字排印本身成为设计中可被记住的一部分,而不是只负责传递内容的中性容器。
- 结构即信息:编号、眉题、分隔线、标签等结构性手段,应该传递内容的真实信息,而不是装饰内容。许多通用设计都使用编号标记(01/02/03),但这仅适用于内容本身就是一个序列的情况——例如一个真实的流程或一份文字时间线,其中顺序承载着读者所需的信息。在使用编号标记之前,请先思考其是否真的有意义。
- 有意识地使用动效:先判断动效是否能服务主题、阅读或信息理解,再决定用在哪里:页面加载序列、滚动触发展示、悬停微交互或环境氛围。一个被编排好的关键动效通常比零散特效更有力量;动效选择必须服从整体美学方向。有些主题更适合克制处理,额外动画反而会削弱专业感,并让页面显得像 AI 生成的模板作品。
- 复杂度匹配愿景:视觉方向越繁复,执行就越需要足够的层次、细节和完成度;视觉方向越极简,间距、字阶、对齐和微细节就越要精准。优雅不等于少,也不等于多,而是把选定的方向执行到位。
- 认真处理文案:标题、导语、标签、按钮和说明都要被当作设计的一部分处理。可以对源报告的内容重写、压缩、合并和组织表达,但不得发明事实、口径或结论强度。文案和视觉一样会产生模板感。
设计知识的使用方式
- 层级:先决定读者第一眼、第二眼、第三眼分别看什么,再分配尺度、重量、留白和位置。
- 对比:用字体气质、字号、明暗、密度、动静和空间关系制造差异;不要只靠颜色强调。
- 对齐与网格:正文、图表、卡片、注释和导航都落在同一套网格和宽度档里,避免右边缘和左基线随手漂移。
- 邻近与分组:证据靠近判断,注释靠近对象,相关项成组,不相关项拉开。
- 重复与变奏:重复建立秩序,变奏表达章节差异;整页不能一章一个系统,也不能每章完全同形。
- 图地关系:纹理、背景、氛围和动效永远退到内容之后,不能抢走正文和证据的可读性。
- 节奏:长报告要有轻重、疏密、转场和停顿;不是把所有模块等权堆叠。
硬规则
- Markdown 是素材,不是页面结构;不要逐段照搬,也不要把所有内容塞进卡片。
- 先写
plan.md,再写 HTML;没有完整 plan 不动 HTML。 - 页面默认是单文件 HTML:语义 HTML + 内联 CSS;除非用户要求或项目已有资源体系,不拆分文件、不引 CDN。
- 可以用领域隐喻组织视觉和结构,但页面里的数字、来源、案例、判断、结论强度必须来自原报告。
- 不发明 logo、客户、证言、排名、地图点位、图表数据、置信度或看似合理但原文无法支撑的归纳。
- 图表、流程、时间线、地图式分组等必须自包含手写。
工作流
- 读内容与任务:通读源报告,确认主题、领域、受众、用途、核心判断、证据、限制、重复内容、表格、图示和附录。
- 第一遍:brainstorm 短设计计划:先根据 brief、报告领域、内容任务、证据结构和受众发散 2-3 个与内容契合的设计方向,不碰具体 HTML。每个方向用 compact token system 表达:Color 为 4-6 个命名 hex 值并说明语义用途;Type 定义 display、body,必要时定义 utility / mono;Layout 用一句话概念和 ASCII wireframe 描述;Signature 定义这页唯一会被记住的设计元素。
- 审查并修订短设计计划:对照 brief 和报告内容检查每个方向是否真有内容来源。如果任何部分像类似页面的通用默认答案,而不是为当前报告做出的选择,必须修订该部分,并写明改了什么、为什么改。确认相对独特性后,选择 1 个方向进入完整计划。
- 第二遍:完整页面计划:基于修订后的短设计计划,展开信息结构、首屏策略、页面拓扑、导航、章节版面、转场节奏和证据贴附方式;用层级、对比、对齐、邻近、分组、重复 / 变奏来组织信息。
- 逐章做内容设计:每章写清
内容形状 -> 章节版面 -> 呈现形式 -> 排版处理。颗粒度到段或判断,不要整章放过;长论述也要做导语、拉引、边注或判断提块。 - 定设计契约与 checklist:写 HTML 前把 tokens、字体角色、宽度档、章版面映射、动效策略、响应式降级、事实边界、泛模板自检和检查角度落到
plan.md。checklist 是开工前的契约,不是事后补救。 - 写 HTML:只实现
plan.md,不要在 HTML 阶段另起一套视觉或结构。先搭全页骨架,再填内容和图表;所有颜色、字体和关键布局选择都必须从短设计计划派生。 - 按检查角度审查:从事实保真、主题契合、美学一致性、字体层级、布局网格、内容塑形、动效克制、可访问性、响应式和分享性逐项检查;未通过就修正。
What ships with it
4 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.
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 · 76 lines · 138 tokens per session scan A 37b197056575
sn-md-to-html-report is a skill published in the GitHub repository OpenSenseNova/SenseNova-Skills (5,570 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 2,297 once invoked, about $0.0007 per session on Opus 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 2026-09-03.
Other skills, from other repositories
feishu
A toolkit for working with Feishu, also called Lark, a workplace collaboration platform. It covers documents, spreadsheets, files, wikis, approvals, calendars, and contacts.
ha-data-analytics
A local-first data-analysis and reporting skill for CSV and spreadsheet files. It produces decision-ready analyses and shareable offline reports while separating facts, calculations, interpretations, and recommendations.
office-docx
Use when the user asks to create, edit, inspect, polish, verify, or deliver Word .docx documents, Google Docs-targeted drafts, business briefs, forms, reports, tables, checklists, redraft-ready document sections, or PDF/Word source-to-DOCX transformations.
office-pptx
Use when the user asks to create, inspect, verify, polish, or deliver PowerPoint .pptx decks, Google Slides-targeted deck artifacts, strategy narratives, operating reviews, pitch decks, teaching decks, section slides, bullet slides, or source-to-PPTX transformations.
office-xlsx
Use when the user asks to create, inspect, verify, analyze, format, or deliver Excel .xlsx workbooks, Google Sheets-targeted spreadsheet artifacts, trackers, budgets, models, tables, dashboards, formulas, CSV/TSV-to-XLSX conversions, or spreadsheet-ready data packs.
youdaonote
A command-line skill for managing Youdao Cloud Notes, a Chinese note-taking service. It supports notes, to-do items, saved web pages, searches, and folders.