Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Word Revision Workflow

ASecurity

Use when an agent must perform editorial revision of .docx files with reviewer comments, Track Changes, claim checks against a source, restricted edits, and selective accept. Triggers on \"word revision\", \"docx review\", \"track changes\", \"claim check\", \"brand guidelines\". Non-triggers: Google Docs Sheets or Slides editing (use google-workspace-ops), format conversion without editorial review (use nutrient-document-processing). Outcome: reviewed .docx with triaged comments, verified cl...

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill word-revision-workflow --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Word Revision Workflow?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Word Revision Workflow
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-word-revision-workflow/badge)](https://www.skillsdirectory.com/skills/majinmagros-word-revision-workflow)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: word-revision-workflow
description: "Use when an agent must perform editorial revision of .docx files with reviewer comments, Track Changes, claim checks against a source, restricted edits, and selective accept. Triggers on \"word revision\", \"docx review\", \"track changes\", \"claim check\", \"brand guidelines\". Non-triggers: Google Docs Sheets or Slides editing (use google-workspace-ops), format conversion without editorial review (use nutrient-document-processing). Outcome: reviewed .docx with triaged comments, verified claims, restricted Track Changes edits, and selective accept log."
metadata:
  origin: ECC
---

# Word Revision Workflow

Editorial revision of .docx files with an agent, end to end: triage reviewer
comments -> edit with Track Changes -> check each claim against its source ->
apply restricted edits -> run a brand-guidelines pass -> accept selectively.

This skill covers the Office gap: `google-workspace-ops` is Google-only and
`nutrient-document-processing` is conversion, not editorial review.

## When To Activate

- The user says Word revision, docx review, Track Changes, reviewer comments,
  accept or reject changes, or brand-guidelines pass on a document.
- A .docx file has open comments or pending tracked changes that need triage
  before any edit.
- Factual claims in the document must be verified against a stated source
  (for example a shared drive folder or content repository) before acceptance.
- The revision must keep an audit trail of what was accepted, rejected, or
  left pending.

## Workflow

### 1. Collect inputs and freeze scope

- Gather the .docx file, the list of reviewers, the source of truth for
  claims, and the brand or style guide to enforce.
- Record document name, revision date, and reviewer list in a short header
  at the top of the working log (`output/revision-log.md`).
- Do not start editing until inputs are complete. Missing source = stop.

### 2. Triage comments

- Extract every comment with author, page or paragraph anchor, and status.
- Classify each comment as [x] actionable, [ ] question for the author,
  or [ ] out of scope.
- Order actionable comments by document order, not by reviewer.
- Questions for the author go to a pending list; never guess the answer.

### 3. Enable Track Changes and draft edits

- Turn Track Changes on before any edit so every insertion and deletion
  is visible to the reviewer.
- Make one edit per comment where possible so accept can stay selective.
- Keep formatting edits separate from content edits.

### 4. Check each claim against the source

- For every factual claim touched by an edit, locate the matching passage
  in the declared source and quote it in the working log.
- Mark each claim as OK (source supports it), MISMATCH (source
  contradicts it), or UNVERIFIED (no source found).
- MISMATCH and UNVERIFIED block acceptance of that edit until resolved.

## Exemplo

```text
.docx com 12 comentários: tria ([x] acionável / [ ] pergunta / fora) por ordem do doc
Track Changes ligado; 1 edit por comentário; claim "cresceu 40%" → fonte citada OK
MISMATCH trava o aceite; log registra aceito/rejeitado/pendente por item
```

### 5. Apply restricted edits

- Allowed: grammar, spelling, punctuation, consistent terminology,
  formatting required by the style guide, and claim corrections backed
  by a quoted source.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →