← 返回 Skills 市场
Ad Claim Risk Checker
作者
LeroyCreates
· GitHub ↗
· v1.0.0
· MIT-0
173
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ad-claim-risk-checker
功能描述
Analyzes ad copy to identify and reduce risky claims by flagging unsupported, absolute, or sensitive wording and providing safer rewrite alternatives.
使用说明 (SKILL.md)
Ad Claim Risk Checker
Review ecommerce ad copy for claim risk before it gets turned into paid ads, creator briefs, PDP language, or live selling scripts.
Use this skill when a user wants to pressure-test ad copy, hooks, product claims, or creator talking points that might create compliance, platform, or credibility risk. It is useful for spotting overclaims, unsupported promises, absolute wording, implied guarantees, and phrases likely to trigger ad review issues or customer distrust.
Use when
- Reviewing paid ad copy before launch
- Checking creator talking points for risky wording
- Sanitizing PDP or landing page claims before amplification
- Comparing a bold claim version with a safer alternative
- Reducing platform review risk without making copy useless
Do not use when
- The user needs formal legal advice or regulatory opinions
- There is no claim language to review
- The task is general brand writing with no risk concern
Inputs to ask for
- Exact copy to review
- Channel: TikTok, Meta, landing page, PDP, live, creator script, email
- Product category
- Evidence level: testimonials, studies, internal data, none
- Market / geography if relevant
- Desired tone: aggressive / balanced / conservative
Workflow
- Extract the explicit and implied claims
- Classify claim risk by type
- Flag unsupported, absolute, or sensitive wording
- Rewrite the copy into safer alternatives
- Explain what changed and why
Output requirements
Return:
- Original claim breakdown
- Risk rating by line or claim cluster
- Why the risk exists
- Safer rewrites
- Optional stronger-but-still-safer variation
Risk types to watch
- Absolute outcomes
- Time-bound guarantees
- Health / body / financial outcomes
- Unqualified superiority claims
- Unsupported quantified performance claims
- Implied certainty or universal fit
Quality bar
- Practical for operators and growth teams
- Clear risk explanations
- Rewrites still usable in real ads
- Avoids robotic compliance-speak
- No fake legal certainty
Example prompts
- Check this TikTok ad script for risky claims and rewrite it safely
- Review these creator talking points before we send the brief
- Flag the dangerous lines in this landing page hero copy
安全使用建议
This skill appears safe to install from a permissions perspective because it is instruction-only and requests no credentials or installs. Before using, avoid pasting any sensitive personal data or non-public business secrets into prompts. Remember the skill is not a substitute for legal or regulatory advice—for high-risk claims consult legal/compliance professionals. If you need offline or auditable processing, prefer workflows that keep source material on your systems rather than pasting it into third-party tools.
功能分析
Type: OpenClaw Skill
Name: ad-claim-risk-checker
Version: 1.0.0
The skill bundle is a set of instructions for an AI agent to analyze advertisement copy for compliance and credibility risks. It contains no executable code, no network requests, and no instructions that would lead to data exfiltration or unauthorized access. The files (SKILL.md, _meta.json, and references/output-template.md) are entirely focused on the legitimate task of reviewing and rewriting ad claims.
能力评估
Purpose & Capability
Name, description, and SKILL.md all align: the skill reviews ad copy for risky claims and produces safer rewrites. It declares no binaries, env vars, or installs that would be unrelated to that purpose.
Instruction Scope
Runtime instructions only ask for ad copy, channel, product category, evidence level, tone, and then outline a reasonable workflow (extract claims, classify risk, rewrite). There are no instructions to read files, access system paths, or send data to external endpoints.
Install Mechanism
No install spec and no code files — purely instruction-only. This is the lowest-risk install footprint and appropriate for the stated function.
Credentials
The skill requests no environment variables, credentials, or config paths. Inputs requested (copy, channel, product category, evidence level, tone) are proportional to the task.
Persistence & Privilege
Flags show always: false and model invocation is allowed (default). The skill does not request persistent system presence or modify other skills/configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ad-claim-risk-checker - 安装完成后，直接呼叫该 Skill 的名称或使用
/ad-claim-risk-checker触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of Ad Claim Risk Checker skill.
- Reviews ecommerce ad copy and claims for compliance, platform, and credibility risks.
- Flags overclaims, unsupported promises, absolute wording, and high-risk phrasing.
- Provides safer rewrites and explains risk levels for each claim.
- Supports review for ads, creator briefs, PDPs, and live selling scripts.
- Tailors advice based on channel, product, evidence level, geography, and desired tone.
元数据
常见问题
Ad Claim Risk Checker 是什么？
Analyzes ad copy to identify and reduce risky claims by flagging unsupported, absolute, or sensitive wording and providing safer rewrite alternatives. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 173 次。
如何安装 Ad Claim Risk Checker？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ad-claim-risk-checker」即可一键安装，无需额外配置。
Ad Claim Risk Checker 是免费的吗？
是的，Ad Claim Risk Checker 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Ad Claim Risk Checker 支持哪些平台？
Ad Claim Risk Checker 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Ad Claim Risk Checker？
由 LeroyCreates（@leooooooow）开发并维护，当前版本 v1.0.0。
推荐 Skills