# Marketing claims review Human Guide

## What This Is For
Reviews marketing claims for legal and compliance risk, helping teams classify claims, identify support needs, and tighten language before publishing. It gives the agent a clearer input/output frame for marketing claims review: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Marketing claims review agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for marketing claims review.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Marketing claims review guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- Load `~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md` → Marketing claims standards.
- Apply the claim taxonomy and review workflow below.
- Extract every claim. Classify: puffery / factual / comparative / implied / absolute.
- For each non-puffery claim: substantiation check, suggested fix.
- Output: claim-by-claim with calls, suggested revision if short enough.
- Comparative claims policy (allowed with substantiation / discouraged / never)
- Substantiation standard (what's required before a claim ships)
- Common rejected claims (learn from history)
- **Testimonials / reviews** — material connections between the speaker and the advertiser are typically disclosable; research the current form and placement rules
- **Influencer content** — research the current tagging, clarity, and conspicuousness requirements for the channel and audience
- **"Results may vary" / atypical results** — research whether a disclosure (and what form) is required when shown results aren't representative
- **Free trial / auto-renewal / negative option** — research the current conspicuousness and consent requirements for auto-conversion terms

## Decision Points And Nuance
The original skill emphasizes: Matter context, Purpose, Load standards, Research the applicable standards before clearing copy, Claim taxonomy, Vague / subjective claims, Specific factual claims, Comparative claims (heightened scrutiny), Implied claims, Absolute claims.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- Comparative claims policy (allowed with substantiation / discouraged / never)
- Substantiation standard (what's required before a claim ships)
- Per `~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md` — if comparative claims are "never," flag all of them. If "allowed with substantiation," check for the substantiation.
- | "Never goes down" | "99.9% uptime" (with SLA that defines it) |
- > Do not proceed past this gate to "Ready to ship: Yes" without an explicit yes. "With changes below" and "No — rewrite needed" do not require the gate — those are review calls, not approvals.
- A meta-description of changes is never an acceptable output for a short asset — when the asset is one line, the output should BE the revised one line.]
- **"Results may vary" / atypical results** — research whether a disclosure (and what form) is required when shown results aren't representative

## Copy-And-Paste Prompt
```text
Use the Marketing claims review human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the anthropics/claude-for-legal skill entry for `marketing-claims-review`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# /marketing-claims-review

1. Load `~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md` → Marketing claims standards.
2. Apply the claim taxonomy and review workflow below.
3. Extract every claim. Classify: puffery / factual / comparative / implied / absolute.
4. For each non-puffery claim: substantiation check, suggested fix.
5. Output: claim-by-claim with calls, suggested revision if short enough.

```
/product-legal:marketing-claims-review
[paste landing page copy]
```

---

## Matter context

**Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run `/product-legal:matter-workspace switch <slug>` or say `practice-level`." Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~/.claude/plugins/config/claude-for-legal/product-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

## Purpose

Marketing wants to say the product is the best. Legal needs it to be true, or at least not provably false. This skill finds the claims that will get a demand letter from a competitor or an inquiry from a regulator, and suggests how to keep the energy while fixing the exposure.

## Load standards

Read `~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md` → `## Marketing claims`:
- Comparative claims policy (allowed with substantiation / discouraged / never)
- Substantiation standard (what's required before a claim ships)
- Common rejected claims (learn from history)

## Research the applicable standards before clearing copy

Research the currently operative advertising and substantiation standards for the applicable jurisdictions and media (for example, FTC, NAD, state UDAP regimes, sector regulators for healthcare / financial / children's products, and platform-specific policies). Identify what substantiation the *specific claim* requires — who measured it, when, sample size, apples-to-apples basis — not just whether *some* substantiation exists on file. Flag implied claims and comparative claims for heightened scrutiny. Verify currency: endorsement and review guides have been updated recently and continue to evolve. Cite primary sources with pinpoint references. If you cannot verify the current standard, flag for attorney verification — do not state a rule you haven't confirmed.

> **Only cite the standards that apply to the specific claims under review.** A blanket list of every FTC guideline, NAD practice note, or sector rule makes the load-bearing ones invisible. Do not cite the Endorsement Guides (16 CFR Part 255) unless the copy contains an endorsement, testimonial, or influencer content. Do not cite disclosure-overlay rules unless a claim in the asset triggers the overlay. Do not cite a sector regulator unless the copy targets or implicates that sector. A standard earns its place in the output by mapping to a specific quoted claim; otherwise drop it.

> **No silent supplement.** If a research query to the configured legal research tool returns few or no results for the applicable standard (FTC rule, NAD decision, state UDAP, sector rule, platform policy), report what was found and stop. Do NOT fill the gap from web search or model knowledge without asking. Say: "The search returned [N] results from [tool]. Coverage appears thin for [standard / jurisdiction]. Options: (1) broaden the search query, (2) try a different research tool, (3) search the web — results will be tagged `[web search — verify]` and should be checked against the issuing authority before relying, or (4) flag as unverified and stop. Which would you like?" A lawyer decides whether to accept lower-confidence sources.
>
> **Source attribution tiering.** Tag every citation with its source. For model-knowledge citations, use one of three tiers rather than a single blanket "verify" tag:
>
> - `[settled]` — stable, well-known statutory and regulatory references unlikely to have changed (e.g., FTC Act § 5, Lanham Act § 43(a) as a concept). Still verify before approving copy, but lower priority.
> - `[verify]` — model-knowledge citations that are real but should be verified: specific FTC enforcement actions, NAD decisions, state UDAP statutes, sector-specific rules, platform policies, case holdings, thresholds, effective dates, recent updates (the Endorsement Guides and disclosure rules update frequently).
> - `[verify-pinpoint]` — pinpoint citations (specific subsection letters, CFR subpart references, case paragraph numbers) carry the highest fabrication risk and should ALWAYS be verified against a primary source.
>
> Tool-retrieved citations keep their source tag (`[Westlaw]`, `[CourtListener]`, `[FTC site]`, `[NAD]`, `[platform policy]`, or the MCP tool name); web-search citations remain `[web search — verify]`; user-supplied citations (from substantiation files) remain `[user provided]`. The tiering surfaces the real verification work — a reader who verifies everything verifies nothing. Never strip or collapse the tags.

## Claim taxonomy

The categories below are structural patterns the reviewer should be able to recognize. Whether a given phrase is actionable depends on the currently operative rule in the applicable jurisdiction, the specific substantiation available, and the audience — research that before concluding.

### Vague / subjective claims

Subjective assertions with no measurable content. Whether they are actionable depends on jurisdiction, context, and audience — research before concluding.

| Example |
|---|
| "The best way to manage your projects" |
| "You'll love it" |
| "Revolutionary" |

### Specific factual claims

Measurable, specific, a reasonable person might rely on it.

| Example | Substantiation to look for |
|---|---|
| "50% faster than [competitor]" | Benchmark data, disclosed methodology, date |
| "Trusted by 10,000 companies" | Actual count (not cumulative signups — *currently* trusted) |
| "Saves 5 hours per week" | Study or customer data, disclosed sample |
| "Enterprise-grade security" | What does that mean? SOC 2? Spell it out or it's a promise |
| "HIPAA compliant" | BAA available, actually configured for it — this is a contractual promise |

### Comparative claims (heightened scrutiny)

Naming a competitor or implying one. Research the applicable rules for comparative advertising in the relevant jurisdictions and media before clearing.

| Example | Fix pattern |
|---|---|