Skip to content
Back to skills

Marketing Claims Review

ASecurity

Audit or, when authorized, rewrite persuasive product claims against shipped-product evidence. Use for landing pages, marketing-heavy READMEs, feature or pricing pages, comparisons, and calls to action.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 17, 2026
developmentperformance

Security analysis

A100/100

Scanned October 17, 2026

npx -y skills add yarlson/yarstack --skill marketing-claims-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Marketing Claims Review?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Marketing Claims Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yarlson-marketing-claims-review/badge)](https://www.skillsdirectory.com/skills/yarlson-marketing-claims-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: marketing-claims-review
description: Audit or, when authorized, rewrite persuasive product claims against shipped-product evidence. Use for landing pages, marketing-heavy READMEs, feature or pricing pages, comparisons, and calls to action.
---

# Marketing Claims Review

Own claim substantiation, positioning, comparisons, and first-visitor clarity regardless of file location.

## Workflow

1. Confirm pages, audience, and audit-only or authorized rewrite mode.
2. Build a capability map with implementation and runtime evidence taking precedence over marketing prose, demos, and roadmap material.
3. Classify material claims as `accurate`, `unclear`, `unsupported`, `exaggerated`, `stale`, or `false`. A performance, scale, or adoption number is `accurate` only when its source exists: the benchmark or data, its method, and the version measured.
4. Test whether a first-time visitor can identify the product, intended user, problem, mechanism, difference, limitations, and next action.
5. For each problematic claim, cite evidence and recommend `keep`, `rewrite`, `move`, `remove`, `qualify`, or `prove`.
6. Rewrite only when authorized, preserving distinctions between shipped, partial, experimental, planned, and unsupported behavior.
7. After an authorized rewrite, use `text-improve` to improve the prose without weakening substantiation, necessary qualifications, or intentional voice.

Use `docs-review` for repository-document structure and discoverability, and `docs-drift-review` only for drift caused by the current change. Mark a comparative claim about another product unverified unless current, authoritative public evidence supports it, and cite that evidence.

Do not infer capabilities from aspirations or invent proof.

Finish with scoped claims, evidence, dispositions, authorized edits, and unresolved proof needs.

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.