marketing-claims-review

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/marketing-claims-review

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.

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

加载

~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md

→ 营销声明标准。

应用以下声明分类体系和审核工作流。
提取每一项声明，分类：夸大宣传/事实性/对比性/暗示性/绝对性。
针对每一项非夸大宣传的声明：进行证实性检查，并给出修改建议。
输出：逐项列出声明及审核结论，若内容简短则提供建议改写版本。

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

Matter context

事项上下文

Matter context. Check

## Matter workspaces

in the practice-level CLAUDE.md. If

Enabled

✗

(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

on

事项上下文：查看业务级CLAUDE.md中的

## Matter workspaces

。如果“Enabled”为

✗

（内部用户默认设置），则跳过本段剩余内容——技能将使用业务级上下文，事项机制不可见。如果已启用且没有活跃事项，请询问：“这是针对哪个事项的？请运行

/product-legal:matter-workspace switch <slug>

或说明‘业务级’。”加载活跃事项的

matter.md

以获取特定于该事项的上下文和覆盖规则。将输出写入事项文件夹

~/.claude/plugins/config/claude-for-legal/product-legal/matters/<matter-slug>/

。除非“Cross-matter context”为开启状态，否则切勿读取其他事项的文件。

Purpose

目的

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.

营销团队希望宣称产品是最佳的，而法务团队需要确保这些宣称真实，至少是无法被证伪的。本技能能够找出那些可能引发竞争对手索赔函或监管机构调查的声明，并建议如何在保留营销感染力的同时降低合规风险。

Load standards

加载标准

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)

读取

~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md

中的

## Marketing claims

部分：

对比性声明政策（允许需证实/不鼓励/严禁）
证实标准（声明发布前需满足的要求）
常见被驳回的声明（从历史案例中学习）

Research the applicable standards before clearing copy

在审核文案前研究适用标准

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.

研究适用司法管辖区和媒体当前有效的广告及证实标准（例如FTC、NAD、州UDAP制度、医疗/金融/儿童产品行业监管机构，以及平台特定政策）。明确特定声明所需的证实材料——由谁测量、何时测量、样本量、对比基准的一致性——而不仅仅是是否存有某些证实材料。对暗示性声明和对比性声明进行重点审查。验证时效性：代言和审查指南近期已更新且持续演变。引用带有精准参考的原始来源。如果无法验证当前标准，请标记需律师核实——切勿陈述未确认的规则。

仅引用与所审核特定声明相关的标准。罗列所有FTC指南、NAD实务说明或行业规则会使关键标准被掩盖。除非文案包含代言、推荐或网红内容，否则请勿引用《代言指南》（16 CFR Part 255）。除非资产中的声明触发披露覆盖规则，否则请勿引用该规则。除非文案针对或涉及特定行业，否则请勿引用行业监管机构。只有当标准与特定引用声明对应时，才将其纳入输出；否则予以舍弃。

禁止补充未知信息。如果向配置的法律研究工具发出的研究查询返回的适用标准（FTC规则、NAD裁决、州UDAP、行业规则、平台政策）结果很少或没有，请报告已发现的内容并停止。请勿未经询问就通过网络搜索或模型知识填补空白。请说明：“从[工具]搜索到[N]条结果。[标准/司法管辖区]的相关覆盖内容较少。可选方案：(1) 扩大搜索查询范围，(2) 尝试其他研究工具，(3) 进行网络搜索——结果将标记为
[web search — verify]
，在依赖前需对照发布机构核实，或(4) 标记为未验证并停止。您希望选择哪种方案？”由律师决定是否接受低可信度来源。
来源归因分层：为每个引用标记来源。对于模型知识引用，使用三个层级而非单一的“verify”标签：
[settled]
——稳定、知名的法规引用，不太可能发生变化（例如FTC Act § 5、Lanham Act § 43(a)的概念）。在批准文案前仍需核实，但优先级较低。
[verify]
——真实但需核实的模型知识引用：特定FTC执法行动、NAD裁决、州UDAP法规、行业特定规则、平台政策、案例裁决、阈值、生效日期、近期更新（《代言指南》和披露规则频繁更新）。
[verify-pinpoint]
——精准引用（特定小节字母、CFR分部引用、案例段落编号）存在较高的伪造风险，应始终对照原始来源核实。
工具检索的引用保留其来源标签（
[Westlaw]
、
[CourtListener]
、
[FTC site]
、
[NAD]
、
[platform policy]
或MCP工具名称）；网络搜索的引用保留
[web search — verify]
；用户提供的引用（来自证实文件）保留
[user provided]
。分层方式可明确实际需核实的内容——如果要求全部核实，等于没有重点核实。切勿移除或合并标签。

Claim taxonomy

声明分类体系

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.

以下类别是审核人员应能识别的结构模式。某一表述是否可执行取决于适用司法管辖区当前有效的规则、可用的特定证实材料以及受众——在得出结论前需进行相关研究。

Vague / subjective claims

模糊/主观声明

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"

无可衡量内容的主观断言。是否可执行取决于司法管辖区、上下文和受众——得出结论前需进行研究。

示例
"The best way to manage your projects"
"You'll love it"
"Revolutionary"

Specific factual claims

特定事实性声明

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

可衡量、具体，合理用户可能会依赖的声明。

示例	需查找的证实材料
"50% faster than [competitor]"	基准数据、披露的方法论、日期
"Trusted by 10,000 companies"	实际数量（不是累计注册数——当前受信任的数量）
"Saves 5 hours per week"	研究或客户数据、披露的样本
"Enterprise-grade security"	具体指什么？SOC 2？明确说明，否则就是一种承诺
"HIPAA compliant"	具备BAA，实际已配置——这是一项合同承诺

Comparative claims (heightened scrutiny)

对比性声明（重点审查）

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

Example	Fix pattern
"Faster than Slack"	Either name Slack with head-to-head data you can defend, or abstract to "faster than legacy chat tools" with substantiation
"The only platform that does X"	False if anyone else does X — "The first platform to..." (if true) or drop "only"
"[Competitor] can't do this"	Show your feature. Let the viewer compare.

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.

提及竞争对手或暗示竞争对手。在审核通过前，研究相关司法管辖区和媒体中对比性广告的适用规则。

示例	修改模式
"Faster than Slack"	要么明确提及Slack并提供可辩护的直接对比数据，要么改为“比传统聊天工具更快”并提供证实材料
"The only platform that does X"	如果其他平台也能做到X则为虚假——改为“首个能做到……的平台”（如果属实）或删除“only”
"[Competitor] can't do this"	展示你的功能，让用户自行对比。

根据

~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md

——如果对比性声明被列为“严禁”，则标记所有此类声明；如果是“允许需证实”，则检查是否有证实材料。

Implied claims

暗示性声明

Not stated outright but a reasonable reader infers it. Research the treatment of implied claims under the applicable advertising regime — implied claims often carry the same substantiation burden as express ones.

Example	Implication	Fix
"Finally, a secure alternative"	Competitors are insecure	"Finally, security you can verify"
Customer logos without context	These companies endorse us	"Customers include..." is fine; "Trusted by..." implies more
"Built for healthcare"	HIPAA compliant	Clarify or qualify

未明确表述但合理读者会推断出的声明。研究适用广告制度下对暗示性声明的处理——暗示性声明通常与明确声明承担相同的证实责任。

示例	暗示内容	修改方案
"Finally, a secure alternative"	竞争对手不安全	"Finally, security you can verify"
无上下文的客户标志	这些公司为我们代言	“客户包括……”是可以的；“受……信任”暗示更多内容
"Built for healthcare"	符合HIPAA标准	明确说明或限定

Absolute claims

绝对性声明

No room for error. One counter-example makes them false. Research whether qualifications cure the issue in the applicable jurisdiction.

Example	Fix pattern
"Never goes down"	"99.9% uptime" (with SLA that defines it)
"100% accurate"	A specific, substantiated percentage tied to a benchmark
"Guaranteed"	Only if you actually offer a guarantee with terms — this creates warranty exposure
"Always" / "Every"	"Typically" / "Most"

无容错空间。一个反例即可使其虚假。研究在适用司法管辖区中，限定条件是否能解决问题。

示例	修改模式
"Never goes down"	"99.9% uptime"（附带定义该指标的SLA）
"100% accurate"	与基准绑定的具体、已证实的百分比
"Guaranteed"	仅当实际提供带有条款的保证时使用——这会产生担保风险
"Always" / "Every"	"Typically" / "Most"

The review

审核流程

Step 1: Extract every claim

步骤1：提取所有声明

Read the copy. List every sentence or phrase that asserts a fact, makes a comparison, or promises something. Ignore pure puffery in the list.

阅读文案，列出每一个断言事实、进行对比或做出承诺的句子或短语。在列表中忽略纯粹的夸大宣传内容。

Step 2: Classify and check

步骤2：分类与检查

For each claim:

markdown

**Claim:** "[exact quote]"
**Type:** [Specific factual | Comparative | Implied | Absolute]
**Substantiation on file:** [Yes — link | No | Unknown]
**Call:** [✅ Fine | ⚠️ Needs substantiation | ⚠️ Needs rewording | 🔴 Cut]
**Suggested fix:** "[alternative phrasing that keeps the energy]"
**Why:** [one line]

针对每一项声明：

markdown

**声明：** "[准确引用]"
**类型：** [特定事实性 | 对比性 | 暗示性 | 绝对性]
**已存档的证实材料：** [是 — 链接 | 否 | 未知]
**审核结论：** [✅ 合规 | ⚠️ 需证实 | ⚠️ 需改写 | 🔴 删除]
**建议修改方案：** "[保留感染力的替代表述]"
**原因：** [一句话说明]

Step 3: Check against the product

步骤3：对照产品核实

Does the product actually do what the copy says? Not a philosophical question — check the PRD or ask the PM.

Common drift: marketing copy written from an early spec, product changed, nobody updated the copy.

产品是否真的如文案所述那样运作？这不是哲学问题——查看PRD或询问产品经理。

常见偏差：营销文案基于早期规格撰写，产品已变更，但无人更新文案。

Step 4: Output

步骤4：输出

Prepend the work-product header from

~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md

## Outputs

(it differs by user role — see

## Who's using this

markdown

[WORK-PRODUCT HEADER — per plugin config ## Outputs]

添加

~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md

中

## Outputs

部分的工作产品页眉（根据用户角色不同而有所差异——查看

## Who's using this

）。

markdown

[工作产品页眉 — 按插件配置的## Outputs]

Marketing Review: [Campaign/Asset name]

营销文案审核：[活动/资产名称]

Reviewed: [date] Asset: [landing page / email / ad / etc.]

审核日期： [日期] 资产类型： [着陆页 / 邮件 / 广告 / 等]

Summary

摘要

[N] claims reviewed. [N]✅ [N]⚠️ [N]🔴

Ready to ship: [Yes | With changes below | No — rewrite needed]

Before emitting "Ready to ship: Yes" (i.e., approving a claim for external use / publication): Read
## Who's using this
in
~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md
. If the Role is Non-lawyer:
Approving a marketing claim for publication is a legal act — once published, substantiation gaps and comparative-claim exposure become enforcement or competitor-challenge risk. Have you reviewed this with an attorney? If yes, proceed. If no, here's a brief to bring to them:

[Generate a 1-page summary: asset, claims approved, claim types (specific factual / comparative / implied / absolute), substantiation on file for each, any implied claims flagged, and the three things to ask the attorney before the copy goes live.]

If you need to find a lawyer: your professional regulator's referral service is the fastest starting point (state bar in the US; SRA/Bar Standards Board in England & Wales; Law Society in Scotland/NI/Ireland/Canada/Australia; or your jurisdiction's equivalent).

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.

共审核[N]项声明。[N]✅ [N]⚠️ [N]🔴

可发布状态： [是 | 需按以下修改后发布 | 否 — 需重写]

在标记“可发布状态：是”（即批准声明用于外部发布/公开）之前： 阅读
~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md
中的
## Who's using this
。如果角色为非律师：
批准营销声明用于发布是一项法律行为——一旦发布，证实材料缺口和对比性声明风险将引发执法或竞争对手挑战。您是否已与律师审核过此内容？如果是，请继续。如果否，请准备以下简报提交给律师：

[生成1页摘要：资产信息、已批准的声明、声明类型（特定事实性/对比性/暗示性/绝对性）、每项声明的已存档证实材料、已标记的暗示性声明，以及文案发布前需向律师询问的三个问题。]

如果您需要寻找律师：所在地区的专业监管机构推荐服务是最快的起点（美国为州律师协会；英格兰和威尔士为SRA/律师标准委员会；苏格兰/北爱尔兰/爱尔兰/加拿大/澳大利亚为律师协会；或所在司法管辖区的等效机构）。

未获得明确同意前，请勿标记“可发布状态：是”。“需按以下修改后发布”和“否 — 需重写”无需此环节——这些是审核结论，而非批准。

Claim-by-claim

逐项声明审核

[All the claim blocks from Step 2, grouped: 🔴 first, then ⚠️, then ✅]

[步骤2中的所有声明块，按以下顺序分组：🔴 首先，然后是⚠️，最后是✅]

Suggested revision

建议改写版本

[For short assets — under 50 words, or a tweet, headline, one-liner, tagline, short ad — the output in this block is the actual revised copy with the fixes applied inline, not a description of what changed. The reader should be able to copy-paste this block into the asset. For longer assets (>50 words but <300 words), show the revised copy with fixes applied inline. For longer assets (300+ words), summarize the changes as a bulleted diff ("Strip Claim 1. Rewrite Claim 3 to drop 'any.' Soften Claim 4 for regulated-domain risk.") rather than pasting the whole asset. 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.]

[对于短资产——50字以内，或推文、标题、单行标语、短广告——此区块的输出是应用修改后的实际改写文案，而非修改说明。读者应能直接复制粘贴此区块到资产中。对于中等长度资产（50-300字），展示应用修改后的改写文案。对于长资产（300字以上），以项目符号差异总结修改内容（例如“删除声明1。改写声明3以移除‘any’。弱化声明4以降低监管领域风险。”），而非粘贴整个资产。对于短资产，绝不能仅输出修改说明——当资产为单行内容时，输出应为修改后的单行内容。]

Substantiation needed before ship

发布前需补充的证实材料

Claim	Need	From whom
[claim]	[data type]	[PM / data team / eng]

声明	所需材料	提供方
[声明内容]	[数据类型]	[产品经理 / 数据团队 / 工程师]

Citation check

引用核查

Any FTC rules, NAD decisions, state UDAP statutes, sector regulations, or platform policies cited in this review were generated by an AI model and have not been verified against a primary source. Before relying on a specific rule to clear or reject copy, verify it against a legal research tool (Westlaw, CourtListener, or your firm's research platform) for accuracy and current effective date — endorsement guides, platform rules, and state UDAP regimes all update frequently. Source tags on each citation (e.g.,

[FTC site]

[web search — verify]

) show where it came from;

verify

tags carry higher fabrication risk and should be checked first.

undefined

本审核中引用的所有FTC规则、NAD裁决、州UDAP法规、行业监管规定或平台政策均由AI模型生成，未对照原始来源核实。在依赖特定规则审核或驳回文案前，请通过法律研究工具（Westlaw、CourtListener或您公司的研究平台）验证其准确性和当前生效日期——代言指南、平台规则和州UDAP制度均频繁更新。每个引用的来源标签（例如

[FTC site]

、

[web search — verify]

）显示其来源；

verify

标签的伪造风险较高，应优先核查。

undefined

Disclosure overlays

披露覆盖规则

Copy that involves any of the fact patterns below sits inside an additional disclosure regime. Research the currently operative disclosure requirements in the applicable jurisdictions (including any platform policies and sector-specific rules) and verify currency — these regimes are updated frequently.

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

涉及以下任一情况的文案需遵守额外的披露制度。研究适用司法管辖区当前有效的披露要求（包括任何平台政策和行业特定规则）并验证时效性——这些制度频繁更新。

推荐/评价——发言者与广告主之间的重大关联通常需披露；研究当前的形式和放置规则
网红内容——研究针对渠道和受众的当前标记、清晰度和显著性要求
“结果可能不同”/非典型结果——研究当展示的结果不具代表性时是否需要披露（以及何种形式）
免费试用/自动续费/负面选项——研究自动转换条款的当前显著性和同意要求

Close with the next-steps decision tree

以下一步决策树收尾

End with the next-steps decision tree per CLAUDE.md

## Outputs

. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.

根据CLAUDE.md中

## Outputs

部分的下一步决策树收尾。根据本技能生成的内容自定义选项——五个默认分支（起草X、升级、获取更多事实、观望、其他）是起点，而非固定模板。决策树是输出内容，由律师选择下一步。

What this skill does not do

本技能不执行的操作

It doesn't write the marketing. It fixes what's wrong with it. The suggested rewrites keep the energy, but the marketer owns the voice.
It doesn't substantiate claims. It identifies which ones need it and who has the data.
It doesn't review design or imagery — words only. If an image implies a claim (competitor logo with a red X through it), flag it, but visual review is a human judgment.

不撰写营销文案，仅纠正其中的问题。建议的改写版本保留营销感染力，但营销人员拥有内容话语权。
不证实声明，仅识别哪些声明需要证实以及谁拥有相关数据。
不审核设计或图像——仅处理文字内容。如果图像暗示某种声明（例如带有红色叉号的竞争对手标志），请标记，但视觉审核属于人工判断范畴。