office-doc-tools

office-doc-tools is a skill for Claude Code, Codex from cass-2003/local-workflow-skill. It costs 81 tokens per session (1,696 once invoked), scanned A, original, MIT.

A set of tools for creating, editing, checking, and reviewing PowerPoint, Word, PDF, Excel, and CSV files.

In plain words
What is it for?
Use it to build presentations, revise documents, inspect PDFs, clean or analyse spreadsheets, create charts, and prepare formal file deliverables.
Why use it?
It helps produce editable files with checked content, formulas, formatting, page layout, and rendering instead of relying only on plain text.

Skill for Claude CodeCodex

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

Good fit Use it to build presentations, revise documents, inspect PDFs, clean or analyse spreadsheets, create charts, and prepare formal file deliverables.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cass-2003/local-workflow-skill/office-doc-tools
Install

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.

Any agent
npx skills add cass-2003/local-workflow-skill --skill office-doc-tools
Clone the repo
git clone --depth 1 https://github.com/cass-2003/local-workflow-skill

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 office-doc-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/office-doc-tools/github.svg)](https://agentmods.dev/skills/cass-2003/local-workflow-skill/office-doc-tools)
Your own site
<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/office-doc-tools"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/office-doc-tools/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 office-doc-tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/office-doc-tools"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/office-doc-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,696 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 $0.00081 $0.01696
Opus 5 $0.00041 $0.00848
Sonnet 5 $0.00016 $0.00339
Haiku 4.5 $0.00008 $0.00170

Measured 6d ago against content hash 7fb4ee92d2b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

office-doc-tools 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.

skills/content-authoring/codex/office-doc-tools/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

coff0xc-office-doc-tools

快速规则(日常任务先读这里)

[文件优先] 先确认输入/输出文件类型、可编辑性、原件保留、目标受众和交付路径。 [结构门禁] PPT 看叙事和视觉系统;Excel 看数据形状/公式/图表;DOCX/PDF 看样式、批注、分页和渲染证据。 [验证证据] 能打开结构就打开结构,能渲染/截图就渲染/截图;不能验证要明说。 [PPT 重写] 论文/报告 DOCX + 旧 PPTX 重写答辩 deck 时读取 references/pptx-defense-rewrite.md,不要卡在 Presentations 路径版本不一致。 [硬边界] 上传外部服务、覆盖原件、接受全部修订、客户/隐私/合同/财务数据处理先确认。

普通 Office 文件任务按本节先推进;只有 artifact quality eval、正式发版或跨文件复杂交付时再展开全部门禁。

能力定位

面向 PowerPoint、Word、PDF、Excel/CSV 这类正式文件交付的 Office 文档工具能力。它解决的不是“写一段内容”,而是把内容做成别人能打开、能编辑、能审阅、能打印、能继续使用的文件。

这个 skill 适合用户说“帮我做一份 PPT / 改一个 DOCX / 检查 PDF / 处理 Excel / 生成可交付文件”的场景。它会把产物质量放在第一位:文件要存在、内容要对、格式要稳、公式要算、版式要看过,不能只凭文本猜测就说完成。

能交付什么

  • 可编辑 .pptx 演示文稿:页面结构、图表、表格、图片、讲述逻辑、导出检查和预览 QA。
  • 可编辑 .docx 文档:报告、方案、SOP、合同草稿、批注、修订、表格、目录、页眉页脚、元数据清理建议。
  • .pdf 阅读、审阅、生成或检查:页面渲染、文字提取、版式问题、页码、表格、图片和引用检查。
  • .xlsx / .csv / .tsv 工作簿:数据清洗、公式、透视/汇总、图表、仪表盘、条件格式、校验列和导出文件。
  • 交付说明:最终文件路径、验证方式、未验证原因、剩余风险和建议的人工复核点。

可以接收什么输入

  • 现有 PPTX、DOCX、PDF、XLSX、CSV、TSV、Markdown、图片、截图、网页导出的表格。
  • 用户给的文字大纲、会议纪要、报告草稿、审计发现、实验数据、财务/运营数据、品牌要求或模板文件。
  • 批注要求、改写要求、格式要求、目标受众、页数限制、打印/展示/归档用途。
  • 多个来源文件,例如“把 PDF 数据整理到 Excel,再做一页 PPT 摘要”。

放心使用的边界

  • 可直接处理本地、可逆、可检查的文件创建、编辑、转换、分析和格式整理。
  • 不上传用户文档到外部服务,不调用付费生成/转换服务,不发布或发送文件,除非用户明确确认。
  • 含个人信息、客户数据、合同、财务、医疗、身份信息或内部资料时,先确认脱敏、保留范围和输出目录。
  • 不伪造来源、签名、印章、审计结论、法律意见、财务真实性或官方认证。
  • 修改现有文件时默认保留原件,输出新文件;批量覆盖、删除、接受所有修订、清空批注或移除水印前必须确认。
  • 默认只处理本地、可逆、可验证的低风险工作;涉及生产、凭据、付费、远程写入、删除、发布或权限变更时必须先确认。

为什么可以放心

  • 文件型交付必须有“文件存在 + 内容检查 + 视觉/结构验证”的证据链。
  • PPT/DOCX/PDF 不能只靠文本抽取判断质量;版式任务要渲染或预览检查。
  • Excel/XLSX 不能只看表面格式;关键公式、引用范围、错误值和图表来源要检查。
  • 现有文件编辑采用最小改动原则,保留结构、样式和原始文件,避免不可追踪覆盖。
  • 最终回复区分“已验证”“未能验证”和“需要人工复核”,不把未运行的检查说成通过。

典型使用方式

使用 coff0xc-office-doc-tools 把这份 Markdown 做成可编辑 PPTX,包含图表、讲述逻辑和预览验证。
使用 coff0xc-office-doc-tools 给这个 DOCX 加批注和修订,不覆盖原件,最后渲染检查版式。
Use coff0xc-office-doc-tools to turn this CSV into a formatted Excel workbook with formulas, charts, and a formula error scan.
Use coff0xc-office-doc-tools to review this PDF report for layout, missing pages, broken tables, and export-ready issues.

Read the full file on GitHub · 78 lines

Files

What ships with it

2 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. 6d ago First seen · 78 lines · 81 tokens per session scan A 7fb4ee92d2b2

Subscribe to this mod's changes

office-doc-tools is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 1,696 once invoked, about $0.0004 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.