moderation
Checks content for compliance, risk, and platform-specific rules before publication.
Install
mkdir -p .claude/skills/moderation && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16859" && unzip -o skill.zip -d .claude/skills/moderation && rm skill.zipInstalls to .claude/skills/moderation
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
统一的内容审核 Skill，覆盖敏感词检测、平台规则检查、风险报告和合规修复建议。Key capabilities
- →Detect sensitive words and expressions
- →Check content against platform rules (e.g., TikTok, YouTube)
- →Generate structured risk reports
- →Provide compliance repair suggestions
- →Offer alternative expressions for fixable content
- →Flag content for manual review (e.g., copyright, financial promises)
How it works
This skill performs content moderation by detecting sensitive words, checking against platform rules, generating structured risk reports with suggestions, and offering alternative expressions.
Inputs & outputs
When to use moderation
- →Checking ad compliance
- →Moderating sensitive content
- →Preparing posts for social media
- →Risk assessment for new content
About this skill
内容安全审核专家
负责在内容生成、媒体生产和发布前进行合规检查。该 Skill 是原 content-moderator 与 moderation 的统一入口：moderation 负责正式调用，content-moderator 作为兼容别名保留。
核心能力
- 检测广告法绝对化用语、虚假宣传、违规导流、低俗内容和敏感表达。
- 按抖音、小红书、B站、微信公众号、YouTube 等平台规则输出差异化审核结果。
- 生成结构化风险报告，包含问题位置、风险等级、修改建议和平台适配情况。
- 对可修复内容给出替代表达，避免一刀切删除。
- 对版权、素材来源、商单标注、医疗/金融承诺等边界内容提示人工复核。
风险等级
| 等级 | 处理方式 | 说明 |
|---|---|---|
| block | 拦截 | 严重违规，禁止发布 |
| warn | 警告 | 可修改后继续 |
| review | 复核 | 需要人工判断 |
| pass | 通过 | 未发现明显风险 |
推荐输出结构
{
"status": "warn",
"score": 75,
"issues": [
{
"type": "advertising_law",
"text": "全网最好",
"level": "warn",
"suggestion": "建议替换为：体验出色"
}
],
"platforms": {
"douyin": { "status": "pass", "issues": [] },
"xiaohongshu": { "status": "warn", "issues": ["疑似站外导流"] }
}
}
审核原则
- 先指出明确违规，再提示潜在风险。
- 对边界内容给出依据和替代表达。
- 不输出或扩散敏感词库的完整高风险内容。
- 发布前优先调用项目工具完成实际检查。
When not to use it
- →When the content does not require moderation or compliance checks
- →When the user does not want a structured risk report or repair suggestions
- →When the task is not related to content generation, media production, or pre-publication checks
Limitations
- →Does not output or disseminate the complete high-risk content of sensitive word libraries
- →Requires project tools to be called for actual checks before publishing
- →Some boundary content requires manual review
How it compares
This skill provides a unified content moderation service with differentiated audit results based on specific platform rules and offers actionable repair suggestions, unlike a generic sensitive word filter.
Compared to similar skills
moderation side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| moderation (this skill) | 0 | 2mo | Review | Intermediate |
| compliance_review | 0 | 3mo | No flags | Beginner |
| generating-threat-intelligence-reports | 0 | 1mo | Review | Intermediate |
| reverse-engineering-tools | 73 | 4mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
compliance_review
hyc7511
内容安全与合规审核工具。在生成任何视觉内容前，必须确保不触碰平台红线。
generating-threat-intelligence-reports
yanacuti1121
Generates structured cyber threat intelligence reports at strategic,
reverse-engineering-tools
gmh5225
Guide for reverse engineering tools and techniques used in game security research. Use this skill when working with debuggers, disassemblers, memory analysis tools, binary analysis, or decompilers for game security research.
game-hacking-techniques
gmh5225
Guide for game hacking techniques and cheat development. Use this skill when researching memory manipulation, code injection, ESP/aimbot development, overlay rendering, or game exploitation methodologies.
solidity-security
wshobson
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
1password
openclaw
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.