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 gy910210/hermes-research-skills --skill report-html-publisher-zhgit clone --depth 1 https://github.com/gy910210/hermes-research-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/gy910210/hermes-research-skills/report-html-publisher-zh)<a href="https://agentmods.dev/skills/gy910210/hermes-research-skills/report-html-publisher-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/report-html-publisher-zh/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/gy910210/hermes-research-skills/report-html-publisher-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/report-html-publisher-zh.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 | $0.00028 | $0.01960 |
| Opus 5.5 | $0.00011 | $0.00784 |
| Sonnet 5.5 | $0.00006 | $0.00392 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
report-html-publisher-zh 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 3d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Report HTML Publisher(中文)
把已有研究稿转换为可直接在浏览器打开的静态阅读页。保留事实、限定条件和引用,不重新总结论文、不补造图表、不替用户公开资料。默认只生成本地页面;公网部署是需要另行授权并验证的后续动作。
何时使用
- 用户要求“把这篇 Markdown 报告生成 HTML / 网页 / 阅读版”。
- 需要把稳定主稿、精读笔记或专题稿做成带目录、引用跳转和打印样式的页面。
- 需要研究主稿与经批准的附页组成一个可移植静态目录。
- 不用于:改写论点、从 PDF 直接猜排版、制作营销落地页或自动开通公网托管。应先完成文本提取/研究成稿。
前提
- Python 3.10+;依赖清单为 requirements.txt,使用
markdown-it-py,不需要账号/API key。 - 用
skill_view返回的 skill 目录定位脚本;仓库内路径示例见下,安装后替换成实际 skill 目录,不硬编码个人目录。 - 若缺依赖,通过
terminal在当前项目虚拟环境安装 requirements;不要为了转换一份报告修改 Hermes 全局配置。
输入 / 输出
输入:report_path、output_dir,以及显式选择的 include_linked、copy_attachments、overwrite、可选 title。
输出:index.html、可选附页/附件、manifest.json;代理另交付 html_publication_packet,记录页面入口、导出范围、验证结果及是否真正部署。详见 output-contract.md。
How to Run
通过 terminal 执行,下面以仓库目录为工作目录。路径有空格时按实际shell安全引用。
terminal(command="python -m pip install -r skills/report-html-publisher-zh/requirements.txt")
terminal(command="python skills/report-html-publisher-zh/scripts/publish_report.py research/report.md --output research/site-v1")
默认不递归公开内部笔记,不复制原论文PDF,不提供原Markdown下载。被省略的本地链接保留文字但不提供失效点击入口,详情进入manifest。只有用户同意导出范围后才扩展:
terminal(command="python skills/report-html-publisher-zh/scripts/publish_report.py research/report.md --output research/site-v2 --include-linked --copy-attachments")
| 选项 | 行为 |
|---|---|
--output DIR |
独立输出目录;默认拒绝覆盖非空目录 |
--include-linked |
递归导出源稿目录内、实际被链接的Markdown附页 |
--copy-attachments |
复制实际引用的允许类型附件;先检查隐私与再分发许可 |
--overwrite |
只更新本工具管理的既有输出,不能当作清空任意目录的开关 |
--title TEXT |
自定义页面标题;保留原文正文 |
工作流
- 用
read_file读取原稿,检查标题、章节、表格、代码、来源列表与本地链接。若只是转换,保持已存在的证据边界,不重新做研究。 - 决定公开范围与输出路径:默认单篇、本地、新目录。不得默认打包
.meta/、个人路径、凭据或用户未批准的附件;不得直接覆盖Markdown。 - 使用脚本生成,而不是手工复制全文。验收:输出入口和manifest真实存在,源稿不变,没有联网加载依赖。
- 用manifest复核实际导出/省略范围;检查引用跳转、页内/跨页锚点和附件。链接不支持或越出源根目录时解决来源问题,不关闭路径保护。
- 连续来源条目必须逐条显示,不能把Markdown软换行当作浏览器已换行。
- 用户要求“项目文件链接可打开”时,使用显式附页/附件选项生成完整本地包,并检查每个条目;不得把禁用链接或“未包含”提示当成满足该要求。公开发布仍需另行授权。
- 用浏览器打开实际生成页;检查桌面与窄屏、目录交互、引用、横向表格、控制台及打印媒体样式。脚本不等于浏览器验证;无法打开时说明静态检查的局限。
- 若用户明确要公网发布,先按 publishing-boundary.md 确认托管目标、账号和公开目录。完成部署后读取真实线上URL复核,不以本地文件或部署日志冒充公网成功。
- 交付入口路径、导出范围、验证结果和部署状态。保存更新命令,便于下一轮由Markdown重新生成,不直接修改生成HTML形成两份事实源。
What ships with it
6 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.
- 3d ago First seen · 98 lines · 28 tokens per session scan A 3ea9af71df61
report-html-publisher-zh is a skill published in the GitHub repository gy910210/hermes-research-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 1,960 once invoked, about $0.0001 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 2026-10-18.
Other skills, from other repositories
ppt-assistant
A presentation-planning assistant that turns a topic into a complete outline and draft package for making a PowerPoint presentation.
ppt-slide-writer
A slide-by-slide writing assistant for PowerPoint presentations. It creates titles, key points, and suggestions for charts or other visuals from an existing structure.
ppt-slide-polisher
A presentation finishing assistant for PowerPoint slides. It adds speaker notes, suggests cuts, and writes transitions between slides.
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.