Brand ReviewSAFE

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: brand-review
description: Review content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before/after fixes. Use when checking a draft before it ships, when auditing copy for voice consistency and terminology, or when screening for unsubstantiated claims, missing disclaimers, and other legal flags.
argument-hint: "<content to review>"
---

# Brand Review

> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).

Review marketing content against brand voice, style guidelines, and messaging standards. Flag deviations and provide specific improvement suggestions.

## Trigger

User runs `/brand-review` or asks to review, check, or audit content against brand guidelines.

## Inputs

1. **Content to review** — accept content in any of these forms:
   - Pasted directly into the conversation
   - A file path or ~~knowledge base reference (e.g. Notion page, shared doc)
   - A URL to a published page
   - Multiple pieces for batch review

2. **Brand guidelines source** (determined automatically):
   - If a brand style guide is configured in local settings, use it automatically
   - If not configured, ask: "Do you have a brand style guide or voice guidelines I should review against? You can paste them, share a file, or describe your brand voice. Otherwise, I'll do a general review for clarity, consistency, and professionalism."

## Review Process

### With Brand Guidelines Configured

Evaluate the content against each of these dimensions:

#### Voice and Tone
- Does the content match the defined brand voice attributes?
- Is the tone appropriate for the content type and audience?
- Are there shifts in voice that feel inconsistent?
- Flag specific sentences or phrases that deviate with an explanation of why

#### Terminology and Language
- Are preferred brand terms used correctly?
- Are any "avoid" terms or phrases present?
- Is jargon level appropriate for the target audience?
- Are product names, feature names, and branded terms used correctly (capitalization, formatting)?

#### Messaging Pillars
- Does the content align with defined messaging pillars or value propositions?
- Are claims consistent with approved messaging?
- Is the content reinforcing or contradicting brand positioning?

#### Style Guide Compliance
- Grammar and punctuation per style guide (e.g., Oxford comma, title case vs. sentence case)
- Formatting conventions (headers, lists, emphasis)
- Number formatting, date formatting
- Acronym usage (defined on first use?)

### Without Brand Guidelines (Generic Review)

Evaluate the content for:

#### Clarity
- Is the main message clear within the first paragraph?
- Are sentences concise and easy to understand?
- Is the structure logical and easy to follow?
- Are there ambiguous statements or unclear references?

#### Consistency
- Is the tone consistent throughout?
- Are terms used consistently (no switching between synonyms for the same concept)?
- Is formatting consistent (headers, lists, capitalization)?

#### Professionalism
- Is the content free of typos, grammatical errors, and awkward phrasing?
- Is the tone appropriate for the intended audience?
- Are claims supported or substantiated?

### Legal and Compliance Flags (Always Checked)

Regardless of whether brand guidelines are configured, flag:
- **Unsubstantiated claims** — superlatives ("best", "fastest", "only") without evidence or qualification
- **Missing disclaimers** — financial claims, health claims, or guarantees that may need legal disclaimers
- **Comparative claims** — comparisons to competitors that could be challenged
- **Regulatory language** — content that may need compliance review (financial services, healthcare, etc.)
- **Testimonial issues** — quotes or endorsements without attribution or disclosure
- **Copyright concerns** — content that appears to be closely paraphrased from other sources

## Brand Voice Reference

Use these frameworks to evaluate content against brand standards or to help the user document their brand voice.

### Brand Voice Documentation Framework

A complete brand voice document should cover these areas:

1. **Brand Personality** — Define the brand as if it were a person. Example: "If our brand were a person, they would be a knowledgeable colleague who explains complex things simply, celebrates your wins genuinely, and never talks down to you."
2. **Voice Attributes** — 3-5 attributes that define how the brand communicates, each defined with what it means in practice, what it does NOT mean (to prevent misinterpretation), and an example.
3. **Audience Awareness** — Who the brand is speaking to (primary and secondary), what they care about, their level of expertise, and how they expect to be addressed.
4. **Core Messaging Pillars** — 3-5 key themes the brand consistently communicates, the hierarchy of these messages, and how each pillar connects to audience needs.
5. **Tone Spectrum** — How the voice adapts across contexts while remaining recognizably the same brand.
6. **Style Rules** — Specific grammar, formatting, and language rules.
7. **Terminology** — Preferred and avoided terms.

### Voice Attribute Spectrums

When defining or evaluating brand voice, position attributes on a spectrum:

| Spectrum | One End | Other End |
|----------|---------|-----------|
| Formality | Formal, institutional | Casual, conversational |
| Authority | Expert, authoritative | Peer-level, collaborative |
| Emotion | Warm, empathetic | Direct, matter-of-fact |
| Complexity | Technical, precise | Simple, accessible |
| Energy | Bold, energetic | Calm, measured |
| Humor | Playful, witty | Serious, earnest |
| Innovation | Cutting-edge, forward-looking | Established, proven |

For each chosen attribute, document it in this format:

**[Attribute name]**
- **We are**: [what this means in practice]
- **We are not**: [common misinterpretation to avoid]
- **This sounds like**: [examp

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

[![ModelsAtlas audit: Brand Review](https://modelsatlas.com/skills/anthropics/brand-review/badge.svg)](https://modelsatlas.com/skills/anthropics/brand-review/)

Not your listing, or something out of date? Claim or update your listing.