word-documents

word-documents is a skill for Claude Code, Codex from nimadorostkar/Claude-Skills-collection. It costs 40 tokens per session (1,283 once invoked), scanned A, original, MIT.

A toolkit for creating, reading, and editing Word documents in the .docx format, with real headings, styles, tables, images, headers, and tracked changes. It can also fill templates and extract structured content.

In plain words
What is it for?
Use it to produce reports, letters, contracts, and memos, extract text or tables, fill templates, and work with comments or tracked changes.
Why use it?
It prevents document edits from turning into inconsistent manual formatting or losing the original structure. It keeps styles and formatting intact during replacements and template-based generation.

Skill for Claude CodeCodex

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

Good fit Use it to produce reports, letters, contracts, and memos, extract text or tables, fill templates, and work with comments or tracked changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nimadorostkar/claude-skills-collection/word-documents
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 nimadorostkar/Claude-Skills-collection --skill word-documents
Clone the repo
git clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collection

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 word-documents

README.md
[![agentmods](https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/word-documents/github.svg)](https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/word-documents)
Your own site
<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/word-documents"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/word-documents/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 word-documents

Your own site · 80×15
<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/word-documents"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/word-documents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,283 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00040 $0.01283
Opus 5 $0.00020 $0.00642
Sonnet 5 $0.00008 $0.00257
Haiku 4.5 $0.00004 $0.00128

Measured 9d ago against content hash 95e1ba038866, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

word-documents 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.

skills/documents/word-documents/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Word Documents

Purpose

Produce and manipulate .docx files programmatically, with real styles and structure rather than a wall of manually formatted paragraphs.

When to Use

  • Generating a report, memo, letter, or contract as a Word document.
  • Extracting text, tables, or comments from an existing .docx.
  • Performing find-and-replace across a document while preserving formatting.
  • Filling a template with data.
  • Working with tracked changes or comments.

Capabilities

  • Document generation with headings, tables, images, headers, and footers.
  • Style application and modification.
  • Content extraction, including tables and embedded objects.
  • Find-and-replace preserving runs and formatting.
  • Template filling.
  • Tracked changes and comments.

Inputs

  • The content and its structure.
  • A template or style reference, if the output must match a house style.
  • The source document, when reading or editing.

Outputs

  • A valid .docx with a proper style hierarchy.
  • Extracted content in a structured form.
  • An edited document that preserves the formatting it should preserve.

Workflow

  1. Use styles, never direct formatting — A heading is Heading 1, not 18pt bold. Styles produce a navigable document, a working table of contents, and a document that can be restyled in one operation.
  2. Start from a template when the house style matters — Load the organization's .dotx or a reference .docx and write into its styles rather than recreating them.
  3. Structure before content — Headings, then the body. The outline is what makes a long document usable.
  4. Preserve formatting when editing — A naive find-and-replace on the XML destroys runs. Replace within runs, and handle text split across runs.
  5. Verify the output — Open it. A .docx that a library writes without error can still be malformed in ways Word will complain about.

Best Practices

  • Direct formatting (bold, a font size, a colour applied by hand) makes a document unmaintainable. Every visual property should come from a style.
  • Text in Word is stored in runs, and a single sentence is frequently split across several. A replace that only handles single-run text will silently miss matches where formatting changes mid-word.
  • Tables need a table style, or they render with no borders and are unreadable when printed.
  • Images need explicit dimensions. Without them, Word inserts at native resolution, which is usually enormous.
  • A table of contents field must be marked for update, and Word will prompt the user on open. This is expected behavior, not a bug.
  • For a document that will be edited by humans, keep the structure simple. Deeply nested tables and text boxes are fragile.

Read the full file on GitHub · 131 lines

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. 9d ago First seen · 131 lines · 40 tokens per session scan A 95e1ba038866

Subscribe to this mod's changes

word-documents is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 25d ago), licensed MIT. It adds 40 tokens to every session and 1,283 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

okf-open-knowledge-format

Create, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter. Use when the user mentions 'OKF', 'Open Knowledge Format', 'knowledge bundle', 'OKF bundle', 'create a knowledge base for agents', 'validate OKF', 'convert…

fabricioctelles/skills · 168 tokens

okf-frontmatter

Maintain openInvest's docs (docs/wiki chapters + docs/wiki/adr) under Google's Open Knowledge Format (OKF). Two jobs. (1) Teach agents to maintain docs the OKF way — every doc carries a small YAML frontmatter block as the single source of truth (type, title, tags, intent, schemasource, documents); schema details link…

longsizhuo/openInvest · 243 tokens

agent-wiki

Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.

Dianel555/DSkills · 89 tokens

pdf

Summarize document text and identify its main claims, evidence, and unanswered questions.

Kyure-A/agent-skills-nix · 19 tokens

LaTeX工具

A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.

XiaoMaColtAI/math-modeling-skill · 46 tokens

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…

XiaoMaColtAI/math-modeling-skill · 92 tokens