docx-operations

docx-operations is a skill for Claude Code, Codex from CodeInfinity1/Stram. It costs 31 tokens per session (467 once invoked), scanned A, original, MIT.

A workflow for planning, inspecting, creating, and editing Microsoft Word files, also called DOCX files. It uses local files and approved Python analysis when the built-in document tools are not enough.

In plain words
What is it for?
Use it to inspect or create DOCX files, prepare Word content, plan conversions, and check that generated documents exist and render correctly.
Why use it?
It helps keep document structure, formatting, and verification explicit while making clear when full Word automation is unavailable.

Skill for Claude CodeCodex

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

Good fit Use it to inspect or create DOCX files, prepare Word content, plan conversions, and check that generated documents exist and render correctly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/codeinfinity1/stram/docx-operations
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 CodeInfinity1/Stram --skill docx-operations
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

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 docx-operations

README.md
[![agentmods](https://agentmods.dev/badge/skills/codeinfinity1/stram/docx-operations/github.svg)](https://agentmods.dev/skills/codeinfinity1/stram/docx-operations)
Your own site
<a href="https://agentmods.dev/skills/codeinfinity1/stram/docx-operations"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/docx-operations/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 docx-operations

Your own site · 80×15
<a href="https://agentmods.dev/skills/codeinfinity1/stram/docx-operations"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/docx-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 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 $0.00031 $0.00467
Opus 5.5 $0.00012 $0.00187
Sonnet 5.5 $0.00006 $0.00093
Haiku 4.5 $0.00003 $0.00047

Measured 1mo ago against content hash 246568916961, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docx-operations 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 1mo 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/office-productivity/docx-operations/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DOCX Operations

Purpose

Support Word document work while respecting current native capability boundaries. Stram can read/write local files and run approved Python analysis; a dedicated DOCX adapter should be implemented natively before claiming full Word automation.

When To Use

Use for DOCX planning, drafting content for Word, reading provided document text, preparing conversion workflows, or implementing/reviewing a native DOCX tool.

Inputs And Evidence

  • DOCX path, desired edits, source text, formatting requirements, and output path.
  • Available Python libraries or future native DOCX tool status.

Tool Map

  • docx_document_create
  • docx_document_inspect
  • read_file
  • write_note
  • python_interpreter
  • python_interpreter_artifact
  • tool_search
  • capability_surface

Workflow

  1. Use docx_document_create for structured local DOCX artifacts.
  2. Use docx_document_inspect to verify generated or provided DOCX files.
  3. Keep document structure explicit: headings, tables, lists, styles, comments.
  4. Use approved Python only for capabilities not covered by the native DOCX tools.
  5. Verify generated artifacts by file existence and, where possible, rendered/parsed content.
  6. Report unsupported operations honestly.

Native Implementation Boundaries

  • Do not import Anthropic DOCX skill code or external reference document scripts.
  • Dedicated DOCX helpers are Stram-owned, tested, and schema-bound.
  • Upstream document skills are reference evidence only.

Safety And Approval

  • Documents may contain private data.
  • Do not overwrite source files without explicit instruction.
  • Preserve formatting requirements and review output before delivery.

Verification

  • Confirm output path and artifact size/content.
  • Note if visual/render verification was not available.
  • Validate edits against the requested change list.

Failure Modes

  • Claiming Word formatting was preserved without inspection.
  • Corrupting a DOCX by treating it as plain text.
  • Hiding missing adapter support.

Read the full file on GitHub · 68 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. 1mo ago First seen · 68 lines · 31 tokens per session scan A 246568916961

Subscribe to this mod's changes

docx-operations is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 467 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 2026-09-03.

Related

Other skills, from other repositories

sif-to-csv

Parse a SIF (Standard Interchange Format) input into a readable preview and optionally append canonical product rows to the project's CSV library. Use when asked to convert or inspect SIF dealer data. For the reverse direction use /as:csv-to-sif.

AlpacaLabsLLC/skills-for-architects · 58 tokens

impact-report-writer

Nonprofit/NGO impact report generation with data visualization suggestions, outcome metrics, narrative structure, and program data presentation. Use when writing impact reports, annual reports, or program evaluation summaries.

travisjneuman/.claude · 43 tokens

meeting-minutes-taker

Turn meeting transcripts into accurate minutes with decisions, actions, owners, and source evidence; also review or merge minutes and resolve speaker ambiguity.

seaworld008/Commonly-used-high-value-skills · 33 tokens

awesome-docs

Generate, convert, and maintain animated GitHub-safe Markdown documents with animated SVG diagrams. Covers four SVG patterns (architecture flow, lifecycle loop, field carousel, timeline phases), guided interview for any doc type (README, architecture guide, runbook, API reference, tutorial, RFC, post-mortem…

nitinjain999/platform-skills · 141 tokens

latex-polish

Inspect a cleanly compiling LaTeX document for source pathologies and rendered visual defects by linting and viewing selected PDF pages. Use when compilation succeeds but title pages, floats, tables, figures, or layout still need publication-quality review. Not for basic compilation health; use $latex-health-check.

flonat/flonat-research · 64 tokens

bib-coverage

Compare a project .bib against a Paperpile project/topic folder to find uncited papers or unfiled entries. Use when the user asks to compare a project .bib against a Paperpile project/topic folder to find uncited papers or unfiled entries.

flonat/flonat-research · 56 tokens