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 cass-2003/local-workflow-skill --skill document-authoringgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote 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/cass-2003/local-workflow-skill/document-authoring)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/document-authoring"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/document-authoring/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/cass-2003/local-workflow-skill/document-authoring"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/document-authoring.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 | $0.00056 | $0.01588 |
| Opus 5 | $0.00028 | $0.00794 |
| Sonnet 5 | $0.00011 | $0.00318 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
document-authoring 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 6d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Authoring
Document Authoring 负责把内容交付为可审阅、可打印、可追踪版本的 Word/docx 文档。目标不是“生成一段文字”,而是交付结构、样式、目录、分页、批注修订和导出证据都可靠的文档成品。
适用范围
- Word、docx、合同、方案、手册、报告、交付文档、SOP、招投标材料和客户正式文档。
- 标题层级、自动目录、页眉页脚、页码、脚注尾注、题注、交叉引用、列表编号、表格和图片。
- 批注、修订、红线、版本对比、审批痕迹、模板套用和品牌样式。
- Markdown、纯文本、表格数据或结构化内容转换为可交付文档。
- 文档渲染、打开校验、分页检查、导出 PDF 和可读性修订。
不适用范围
- 文档/宏样本逆向、恶意宏、OOXML 样本取证和安全分析;这些走 docrev。
- 论文、学术写作、文献综述、引用规范和毕业论文;这些走 academic-writing。
- 只读学习、项目上手、仅整理概念,没有明确写作、编辑、转换或交付动作。
铁律
- 正式文档必须先确定读者、用途、交付格式、模板、语言、审批路径和截止版本。
- 标题层级必须驱动目录和导航;禁止用手动加粗字号伪装结构。
- 页眉页脚、页码、封面、目录、正文、附录和修订记录要有稳定分节策略。
- 合同和对外材料不能凭模型猜法律、价格、责任、日期、主体和承诺;缺证据必须标待确认。
- 批注和修订必须区分“建议修改”“已采纳修改”和“待用户确认”,不能悄悄改关键条款。
- Markdown 转 docx 要保留标题、列表、表格、链接、图片、代码样式和引用层级;不能只复制纯文本。
- 交付前必须真实打开或渲染检查,至少确认目录、分页、字体、图片、表格和导出结果。
强制流程
- 锁定目标:确认文档类型、读者、语气、长度、模板、品牌、语言、交付格式和是否需要 PDF。
- 梳理素材:区分已确认事实、待确认信息、用户原文、引用来源、图片表格和必须保留的条款。
- 建结构:确定封面、目录、章节、附录、修订记录和审批信息;先结构后润色。
- 套样式:统一标题、正文、表格、图片、列表、页眉页脚、页码和引用样式。
- 写正文:按用途压缩或展开内容;事实、金额、日期、主体、权限和承诺必须有来源或标待确认。
- 审阅修订:需要红线时保留修订意图;需要批注时给出位置、原因和建议动作。
- 渲染校验:打开文件或导出 PDF,检查目录、分页、断行、表格溢出、图片清晰度和链接可用性。
- 交付说明:列出改动点、未确认项、验证方式和剩余风险。
场景执行卡
验收证据模板
- 记录源文件、输出 docx、导出 PDF、打开工具/版本、页数、目录状态、截图或导出产物、失败项和未验证项。
- Word、LibreOffice、Google Docs、PDF 至少按目标交付格式选择一个真实查看器;说明字体替换、目录域、交叉引用、页眉页脚和分页差异。
- 批注/修订要写清保留、新增、接受、拒绝策略;记录作者、时间戳、红线 diff、批注位置、隐藏修订和合并文档风险。
- PDF 验证要检查可复制文本、书签/目录、链接可点击、页码一致、图片清晰和重新打开无修复提示。
合同与协议
- 查:主体、日期、金额、服务范围、责任、违约、隐私、争议解决和附件。
- 做:保留关键条款来源;不确定处用批注或待确认占位,不替用户作法律结论。
- 验:编号连续、交叉引用正确、签署页完整、修订痕迹符合要求。
方案与手册
- 查:受众、业务目标、流程、角色、术语、图表、截图和验收标准。
- 做:先搭章节和目录,再压缩重复内容;步骤类内容要编号、条件、输入输出和异常处理。
- 验:目录可更新、步骤连续、图片不糊、表格不跨页错乱。
Markdown 转文档
- 查:标题层级、表格、图片路径、链接、脚注、引用和代码块用途。
- 做:按文档模板映射样式;长表格、宽图和代码片段单独处理分页。
- 验:渲染前后结构一致,链接、图片、目录和 PDF 导出无异常。
复杂对象与低级错误
- 复杂表格要查跨页表头、合并单元格、横向节、图片环绕、脚注尾注、题注、编号连续性、长 URL 和代码块溢出。
- 低级错误包括手工加粗伪标题、目录没更新、链接断、图片糊、列表编号跳号、孤行孤段、隐藏占位符和未脱敏。
- Google Docs / 在线文档任务必须补账号权限、同步方向、导入导出格式、评论/建议模式、版本历史和分享范围验证。
- PDF 编辑/导出任务要区分原生文本、扫描件、OCR、表单、批注、签章和不可逆栅格化风险。
输出要求
- 给出文档结构、关键改动、待确认事实、批注/修订策略和渲染验证结果。
- 对合同、对外承诺、金额、法律责任和个人信息保持高亮边界。
- 未打开或未导出校验时,必须写未验证。
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.
- 6d ago First seen · 90 lines · 56 tokens per session scan A ad7b61e82b96
document-authoring is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 1,588 once invoked, about $0.0003 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.