Agent skill · Audited from source

Docx Toolkit

skill · borghei/Claude-SkillsNOASSERTION licenceAudited 19 Oct 2026 · source 6e3fcbdbb5cf

★ 949pushed 12 days agoversion 1.0.0
!CAUTIONGrade B · 89/100 · 5 findings · 6e3fcbd
949repo stars · whole borghei/Claude-Skills

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 6e3fcbdbb5cf and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 5 findings, 0 critical or high. What it does: Audit Microsoft Word (.docx) documents for heading hierarchy, comments, tracked changes, broken cross-references, and style consistency. Use when reviewing a contract draft, preparing a document for handoff, or…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Docx Toolkit (borghei/Claude-Skills)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/borghei/docx-toolkit

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high5 medium0 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN5
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (5)

Audit 0.4.1 · source sha 6e3fcbdbb5cf · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherborghei GitHub userOwner of the repository this skill is read from
  • Source folderborghei/Claude-Skills/documents/docx-toolkitThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdict6e3fcbdbb5cfA new audit runs when the source changes
  • Repository statusNot archivedLast push 12 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Audit Microsoft Word (.docx) documents for heading hierarchy, comments, tracked changes, broken cross-references, and style consistency. Use when reviewing a contract draft, preparing a document for handoff, or…

---
name: docx-toolkit
description: >
  Audit Microsoft Word (.docx) documents for heading hierarchy, comments,
  tracked changes, broken cross-references, and style consistency. Use when
  reviewing a contract draft, preparing a document for handoff, or enforcing a
  style guide.
license: MIT + Commons Clause
metadata:
  version: 1.0.0
  author: borghei
  category: documents
  domain: document-automation
  updated: 2026-05-04
  python-tools: docx_auditor.py
  tech-stack: docx, OOXML
---

# Docx Toolkit

Audit `.docx` files using the standard library only — no `python-docx` required. Reads OOXML directly with `zipfile` + `xml.etree`.

---

## Table of Contents

- [Keywords](#keywords)
- [Quick Start](#quick-start)
- [Core Workflows](#core-workflows)
- [Tools](#tools)
- [Reference Guides](#reference-guides)
- [Templates](#templates)
- [Best Practices](#best-practices)

---

## Keywords

docx, Word, Microsoft Word, document, document review, comments, tracked changes, redline, headings, style guide, word count, document audit

---

## Clarify First

Before running the audit, confirm these inputs. If any is unknown or vague, ASK — do not assume:

- [ ] **Audit purpose (pre-handoff cleanup, contract-review triage, or style-guide enforcement)** — selects the workflow and the thresholds you apply
- [ ] **Recipient (external customer, opposing counsel, internal)** — sets the tolerance for leftover comments and tracked changes
- [ ] **Allowed style set (for style-guide enforcement)** — defines what counts as a non-conforming style

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

## Quick Start

```bash
python scripts/docx_auditor.py contract.docx
```

Outputs: word count, paragraph count, heading hierarchy, comment count, tracked-changes status, hyperlink count, list of unique paragraph styles used.

---

## Core Workflows

### Workflow 1: Pre-Handoff Document Audit

**Goal:** Catch the issues that embarrass a sender — leftover comments, unresolved track changes, broken heading hierarchy — before the document leaves.

**Steps:**
1. Run: `python scripts/docx_auditor.py document.docx`
2. Review the audit output:
   - Comment count > 0 → resolve or remove before sending
   - Tracked changes detected → accept or reject before sending
   - Heading-hierarchy gaps (H1 → H3 with no H2) → restructure
   - Style sprawl (more than 8 paragraph styles) → consolidate
3. Re-run until clean

**Time Estimate:** 5-15 minutes per document.

### Workflow 2: Contract Review Triage

**Goal:** Quantify how much rework a returned contract needs before reading it line-by-line.

**Steps:**
1. Run audit on the returned `.docx`
2. Comment count > 20 or tracked-change paragraphs > 30% → expect a heavy review pass; schedule time
3. Comment count < 5 → likely cosmetic; quick turnaround possible
4. Use `references/docx_review_checklist.md` for the actual content review

**Time Estimate:** 1 minute per document for triage.

### Workflow 3: Style-Guide Enforcement

**Goal:** Detect documents drifting from your style guide before they ship to a customer.

**Steps:**
1. Define allowed styles in your style guide (see `assets/style_compliance_template.md`)
2. Run audit on candidate documents
3. Flag any document using styles outside the allowed set
4. Map non-conforming paragraphs back to standard styles

**Time Estimate:** 2-5 minutes per document.

---

## Tools

### docx_auditor.py

Reads a `.docx` file as a ZIP archive and parses OOXML directly. No external dependencies.

```bash
# Human-readable
python scripts/docx_auditor.py document.docx

# JSON
python scripts/docx_auditor.py document.docx --json
```

**Reports:**
- Word and paragraph counts
- Heading hierarchy (with gap detection)
- Number of comments
- Whether tracked changes are present
- Unique paragraph styles used
- Hyperlink count
- Image count
- Table count

**Limits:** This tool reads existing docx files. For *generating* docx, use the templates in `assets/` and edit in Word, or install `python-docx` separately.

---

## Reference Guides

- **`references/docx_review_checklist.md`** — Pre-handoff checklist; common rework triggers; mistakes that survive automated audits

---

## Templates

- **`assets/style_compliance_template.md`** — Format for declaring allowed paragraph styles
- **`assets/handoff_checklist_template.md`** — Pre-send checklist with sign-off boxes

---

## Best Practices

- **Audit before every external send.** A 30-second audit catches 80% of avoidable embarrassment.
- **Resolve comments before "Final v3.docx".** Files named "final" with active comments are how lawyers get tickled.
- **Lock heading hierarchy.** H1 → H3 with no H2 breaks navigation, accessibility, and table-of-contents generation.
- **Prefer styles over inline formatting.** A style change in one place beats hundreds of inline overrides.

---

## Integration Points

- Pairs with `legal/` skills for contract redlines
- Pairs with `marketing/copywriting/` for content review
- Used by `c-level-advisor/board-deck-builder` for board-pack documents

Excerpt, first 5,143 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 6e3fcbd

Download folder ↗
git clone https://github.com/borghei/Claude-Skills
git -C Claude-Skills checkout 6e3fcbdbb5cf

The author documents no install command, so this uses the repository directly. Our verdict covers commit 6e3fcbdbb5cf only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source 6e3fcbdbb5cf

A11y Audit!CAUTION

borghei/Claude-Skills

This skill should be used when the user asks to "check accessibility", "audit WCAG compliance", "scan HTML for a11y issues", "check color contrast", or "find accessibility violations in web pages".

★ 949Grade B
Agent Designer!CAUTION

borghei/Claude-Skills

Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent…

★ 949Grade B
Agent Protocol!CAUTION

borghei/Claude-Skills

Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging. Use when building multi-agent systems, defining tool interfaces, or implementing agent-to-agent communication.

★ 949Grade B
Agent Workflow Designer!CAUTION

borghei/Claude-Skills

Design multi-agent orchestration with workflow DAGs, routing, handoff protocols, and state management. Use when building pipelines of specialized agents, designing fan-out/fan-in patterns, or implementing fault-tolerant…

★ 949Grade B
Agenthub!CAUTION

borghei/Claude-Skills

Multi-agent DAG orchestration for workflows where AI agents collaborate via dependency graphs, covering agent spawning, output merging, and quality evaluation. Use when a task needs multiple specialized agents or to…

★ 949Grade B
Analytics Engineer!CAUTION

borghei/Claude-Skills

Analytics engineering across data modeling, dbt, transformation, and semantic layers. Use when building dbt models, designing star schemas, writing staging or mart SQL, configuring data tests, or optimizing warehouse…

★ 949Grade B

Questions about Docx Toolkit

What does the Docx Toolkit skill do?
385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
Is Docx Toolkit safe to install?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Docx Toolkit access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (6e3fcbdbb5cf), read on 2026-10-19. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.