agentCLAWHUBUnverified
Content Compliance Review
发布前审查多平台口播、文字、画面、音频及引导行为的合规风险 Skill: Content Compliance Review Owner: xiaoxiaochen5678-dot Summary: 发布前审查多平台口播、文字、画面、音频及引导行为的合规风险 Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-10T08:15:20.089Z | auto Initial release of content-compliance-review skill. - Reviews planned social-media content for legal, platform-policy, account-safety, privacy, copyright, advertising, and audience-safety risks. - Supports multi-surface and multi-platform revi
OpenClaw
Rank
62
Safety
84
Downloads
2.0k
Updated
Oct 9, 2026
Version
0.1.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 2K downloads reported by the source. Last updated 10/9/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 9, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 9, 2026
- Adoption signal
- 2K downloadsadoption · observed Oct 9, 2026
- Latest release
- 0.1.0release · observed Aug 10, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s17adyagdmfr5frw7b83h21yvn8c7sg4:content-compliance-review-skill- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-xiaoxiaochen5678-dot-content-compliance-review-skill/snapshot"
Documentation
CLAWHUB
67,073 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
--- name: content-compliance-review description: Review planned social-media content before publication for legal, platform-policy, account-safety, privacy, copyright, advertising, and audience-safety risks across scripts, captions, titles, comments, images, cover art, video frames, and audio. Use when a user asks for content compliance review, pre-publication risk checking, platform rule comparison, moderation-risk diagnosis, or safer revisions for one or more publishing platforms. --- # Content Compliance Review Review content conservatively, explain the evidence, and make the next edit concrete. Treat the result as decision support, not a guarantee of approval or legal advice. ## Review workflow 1. Identify the target platforms, intended audience, account type, commercial relationship, jurisdiction, publication date, and supplied media. Do not block a first-pass review when some context is missing; state assumptions and mark affected findings as uncertain. 2. Minimize sensitive data before analysis. Ask the user to redact passwords, identity numbers, payment details, private contact details, unpublished customer data, faces or voices lacking consent, and account recovery information. Never ask for login credentials or attempt to evade platform enforcement. 3. Inventory every review surface: spoken words, on-screen text, title, caption, hashtags, links, calls to action, claims, demonstrations, cover image, background objects, music, logos, comments, and metadata. If a medium cannot be inspected, say exactly what remains unchecked. 4. Read [references/common-risks.md](references/common-risks.md). For each target platform, read its core file and list every matching domain overlay under `references/platforms/<platform>-*.md`; load each overlay relevant to the content. For example, review Douyin medical content with both `douyin.md` and `douyin-medical.md`, and content involving minors with both `douyin.md` and `douyin-minors.md`. Distinguish WeChat Channels from WeChat Official Accounts; when the user only says “微信” and the content may be reused on both, read both rule files and state the assumption. For commercial content, sponsorship, product promotion, affiliate links, or purchase paths in mainland China, also read [references/laws/china-advertising.md](references/laws/china-advertising.md). Use [references/rule-schema.md](references/rule-schema.md) when adding or maintaining rules. 5. Separate four evidence layers: - applicable law or regulation; - current official platform policy; - campaign, category, or account-specific requirement; - practitioner heuristic or observed moderation pattern. 6. For time-sensitive conclusions, verify against current primary sources when web access is available. Record the source URL and verification date. If current verification is unavailable, label the conclusion `待核实` and never present an old rule or heuristic as confirmed policy. 7. Assess the content in context. Do not flag a word merely be
README.md
# 内容合规审查 Skill 面向中国大陆自媒体创作者的发布前内容合规筛查工具。它帮助你在发布到抖音、小红书、微信视频号和微信公众号之前，检查口播、文案、字幕、画面、链接、广告主张及互动引导中的风险，并给出可以直接执行的修改建议。 > 这是一套预审与决策辅助规则，不保证平台审核通过，也不替代律师或平台官方意见。 ## 能解决什么问题 - 同一内容准备发多个平台，不清楚平台差异。 - 带货、种草或品牌合作内容，担心虚假宣传、广告标识和功效承诺。 - 医疗、金融、教育、食品、法律等专业内容，不确定资质和表达边界。 - 视频文案看起来没问题，但画面、二维码、字幕或评论引导可能踩线。 - 内容被下架后，希望依据公开规则定位可能原因，而不是只扫描“敏感词”。 ## 审查范围 Skill 会根据实际提供的素材检查： - 标题、正文、话题标签和评论区话术 - 口播、字幕、背景音与声音仿冒 - 封面、视频帧、人物、产品、制服、二维码和背景物品 - 商品功效、销量、价格、排名、证言和前后对比 - 赞助、佣金、赠品、抽奖、购买链接和私域导流 - AI 生成或深度合成内容的标识、身份真实性和侵权风险 - 未成年人、隐私、版权、危险行为和其他受众安全问题 ## 已覆盖平台 | 平台 | 当前覆盖 | | --- | --- | | 抖音 | 社区规则、未成年人、医疗健康、营销、AI 生成内容及法律行业补充 | | 小红书 | 社区互动、商业合作、种草与效果对比、医疗医美、未成年人及珠宝文玩 | | 微信视频号 | 通用内容、直播、营销、金融与健康科普、AI 内容及微短剧版权 | | 微信公众号 | 原创与低质内容、导流互动、广告、金融医疗、流量作弊及 AI 内容 | | 中国大陆广告法律基线 | 广告真实性、可识别性、绝对化表达、医疗、保健食品、教育、投资、房地产、烟酒及 AI 标识 | 当前规则库包含 **125 条平台检查规则和 13 条广告法律检查规则**。 规则并非全部具有相同权威等级。每条记录都标注 `Authority`、`Status`、来源、日期和适用表面： - `law`：法律法规或监管机关文件 - `official`：能够定位的官方平台规则 - `campaign`：专项治理或阶段性要求 - `heuristic`：经验性风险模式 - `unknown`：来源或现行状态仍需核实 无法确认最新官方原文的规则，审查报告必须标为“待核实”，不能冒充当前平台政策。 ## 安装 ### Codex Codex 支持从用户级 `$HOME/.agents/skills` 或仓库级 `.agents/skills` 读取 skill。 用户级安装： ```bash mkdir -p "$HOME/.agents/skills" git clone https://github.com/xiaoxiaochen5678-dot/content-compliance-review-skill.git \ "$HOME/.agents/skills/content-compliance-review" ``` 仅在当前仓库使用： ```bash mkdir -p .agents/skills git clone https://github.com/xiaoxiaochen5678-dot/content-compliance-review-skill.git \ .agents/skills/content-compliance-review ``` Codex 通常会自动检测新 skill；如果没有出现，请重启 Codex。 ### Claude Code ```bash mkdir -p "$HOME/.claude/skills" git clone https://github.com/xiaoxiaochen5678-dot/content-compliance-review-skill.git \ "$HOME/.claude/skills/content-compliance-review" ``` 如果你的 Claude Code 版本使用其他 skill 目录，以该版本的官方说明为准。 ### WorkBuddy 当前仓库尚未验证已经上架 WorkBuddy 技能市场。若你的 WorkBuddy 版本支持从 GitHub 仓库或本地文件夹导入 skill，请选择本仓库或包含 `SKILL.md` 的根目录；具体入口以你安装版本的产品说明为准。 ### 更新 进入安装目录后执行： ```bash git pull --ff-only ``` 不要在已有同名真实目录上直接覆盖安装；先备份自己的修改和规则资料。 ## 使用示例 在 Codex 中可以直接调用： ```text $content-compliance-review 帮我审查这段口播，准备同时发抖音和小红书。 ``` 也可以自然地提出需求： ```text 这是一条品牌赞助的护肤品视频，请检查口播、字幕、前后对比图和购买引导。 ``` ```text 这段医疗科普准备发微信视频号，哪些地方需要资质、来源或风险提示？ ``` ```text 这篇公众号文章里有 AI 图片和抽奖活动，请做发布前合规审查。 ``` ## 输出内容 每次审查至少包含： 1. 发布结论：暂不发布、修改后再审、可发布但需人工确认或未发现明显风险。 2. 审查范围：已检查和无法检查的素材表面。 3. 问题清单：具体位置、风险等级、依据层级和可能后果。 4. 修改建议：尽量保留原意的最小安全修改。 5. 平台差异：同一内容在不同平台的处理区别。 6. 待确认事项：资质、授权、证据、同意和时效性缺口。 7. 边界提示：不承诺过审，不帮助规避审核或迁移违规行为。 ## 安全与隐私 - 审查前应删除或遮盖密码、验证码、身份证号、支付信息、账号恢复资料和未公开客户数据。 - 不要为认证或解封向非官方代办提交账号密码、证件原件或付款。 - Skill 本身不包含外部 API；但内容是否联网、发送到哪里、是否保存，取决于承载它的 Agent、模型服务、启用工具和用户配置。处理敏感素材前请核对宿主产品的数据政策。 - 不进行人脸身份识别，不推断敏感属性；只检查发布所需的合规风险。 ## 已知限制 - 主要面向中国大陆平台，不覆盖海外平台法律与社区规则。 - 平台规则持续变化，带日期或 `unknown` 状态的结论应在发布前查阅最新官方页面。 - “最、第一、治疗、收益”等词只是复核线索，不能脱离广告属性、语境和证据机械判违规。 - 无法查看的图片、视频、音频、链接落地页和评论区会明确列为未检查范围。 - 不能保证发布成功、流量表现、账号不受处罚或监管机关不采取行动。 ## 维护规则库 平台规则位于 [`references/platforms/`](references/platforms/)，广告法律基线位于 [`references/laws/`](references
_meta.json
{
"ownerId": "kn73r6r3dje5dmnjpvw04yvpj58c6v44",
"slug": "content-compliance-review-skill",
"version": "0.1.0",
"publishedAt": 1786349720089
}references/common-risks.md
# Common cross-platform risks Use this file as a screening map, not as proof that a platform prohibits a specific item. Confirm applicable law and official platform rules separately. ## Safety, legality, and exploitation - Instructions, encouragement, sale, or facilitation involving violence, self-harm, dangerous challenges, illegal goods, controlled substances, weapons, fraud, gambling, or exploitation. - Sexual exploitation, non-consensual intimate content, or any sexualized treatment of minors. - Evasion of enforcement, ban circumvention, deceptive account migration, or concealment intended to pass moderation. ## Misleading claims and commercial content - Fabricated credentials, testimonials, scarcity, prices, results, test data, media coverage, endorsements, or before-and-after evidence. - Absolute or guaranteed claims without adequate substantiation, especially for health, finance, education, beauty, food, and investment outcomes. - Undisclosed sponsorships, affiliate relationships, paid endorsements, synthetic spokespersons, or material commercial relationships. - Calls to action that obscure the seller, price, recurring payment, refund conditions, eligibility, material limitations, or risk. ## Health and financial sensitivity - Diagnosis, treatment, prescription, dosage, disease cure, investment return, loan approval, or wealth guarantees presented without appropriate authorization and evidence. - Advice likely to cause users to delay professional care, stop prescribed treatment, take unsafe financial actions, or misunderstand material risk. - Personal medical, biometric, insurance, banking, credit, or transaction data exposed without necessity and consent. ## Privacy, identity, and minors - Passwords, authentication codes, identity numbers, addresses, private messages, recovery details, payment information, or identifiable customer records. - Faces, voices, names, locations, school details, or private spaces shared without a valid basis and necessary consent. - Minors used in commercial, risky, humiliating, sexualized, or privacy-invasive contexts. - Impersonation, deceptive synthetic media, or realistic AI content without disclosures required by law or platform rules. ## Copyright and third-party rights - Music, footage, photographs, artwork, broadcasts, software interfaces, trademarks, or user comments used beyond permission or applicable exception. - False attribution, removal of ownership marks, or an instruction to evade copyright detection. - Defamation, harassment, doxxing, hate, targeted humiliation, or unsupported accusations presented as fact. ## Presentation and distribution mechanics - Title, cover, thumbnail, subtitles, or cropped screenshots that materially misrepresent the underlying content. - QR codes, external links, coded language, comment prompts, or private-message funnels used to move users into a prohibited transaction or conceal essential information. - Repetitive engagement manipulation, fake interact
references/laws/china-advertising.md
# 中国大陆互联网内容广告合规基线 Use this reference only when content directly or indirectly promotes goods or services in mainland China. It is a screening summary, not legal advice. Determine first whether the content is a commercial advertisement; do not apply advertising restrictions mechanically to all editorial speech. ## Primary sources and status - [中华人民共和国广告法（国家法律法规数据库）](https://flk.npc.gov.cn/detail?id=ff8081817ab231eb017abd6bd860052d&title=%E4%B8%AD%E5%8D%8E%E4%BA%BA%E6%B0%91%E5%85%B1%E5%92%8C%E5%9B%BD%E5%B9%BF%E5%91%8A%E6%B3%95), effective version published 2021-04-29; checked 2026-08-10. [市场监管总局正文镜像](https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/fgs/art/2023/art_5474cf75173c45d6a0379730fb4e8d97.html) was also checked for the sector-specific provisions added from the revised archive. - [互联网广告管理办法](https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/fgs/art/2023/art_d93a579afd45413e8576e4623fab348f.html), effective 2023-05-01; checked 2026-08-10. - [广告绝对化用语执法指南](https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/ggjgs/art/2023/art_64279265c896452f8f638f2de12b8003.html), published 2023-03-20; checked 2026-08-10. - [医疗广告管理办法](https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/ggjgs/art/2023/art_6584dc1c94c2408db7c73f0b5e3d225a.html), effective 2007-01-01; checked 2026-08-10. - [医疗广告监管工作指南](https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/ggjgs/art/2025/art_cd56662cf13b4ad59eabfe31cb1122e1.html), published 2025-05-14; checked 2026-08-10. - [医疗广告认定指南](https://www.samr.gov.cn/zt/ndzt/2025n/ggf/zyfb/art/2025/art_8daf3ed052d749fcbee6eb3909b29e10.html), published 2025-08-15; checked 2026-08-10. - [人工智能生成合成内容标识办法](https://www.cac.gov.cn/2025-03/14/c_1743654684782215.htm), effective 2025-09-01; checked 2026-08-10. ## CN-AD-001: 先判断是否属于广告 - Authority: law - Risk default: verify - Summary: 在中国境内利用网站、应用等互联网媒介，以文字、图片、音频、视频等形式直接或间接推销商品或服务的商业广告活动，适用广告法及互联网广告管理办法。自然人接受委托发布广告，也可能承担广告发布者责任。 - Review action: 核对是否存在商业关系、佣金、赠品、购买链接、联系方式、促销、品牌委托或交易目的。知识分享或个人体验并不当然排除广告属性。 ## CN-AD-002: 广告真实性与证据 - Authority: law - Risk default: high - Summary: 广告应真实合法；商品性能、功能、用途、成分、价格、销量、评价、荣誉、服务内容及效果等陈述须与实际相符。数据、统计、调查和引语应真实准确并标明出处。 - Review action: 对每个可验证主张要求证据、适用时间、地域、样本、口径和授权。不得用小字免责声明修复主体内容中的虚假或误导表述。 ## CN-AD-003: 绝对化用语必须结合语境 - Authority: law - Risk default: high - Summary: 广告法禁止“国家级”“最高级”“最佳”等以及含义相同或近似的绝对化用语，但执法指南要求结合内容、具体语境和所指对象判断，并列出不适用或可依法不予处罚的情形。 - Review action: 不要把“最、第一、首家、领先、最新”等词机械列为一律违法。检查它是否指向被推销商品的性能或竞争优势、是否误导或贬低他人、限定条件是否真实、完整且可证明。医疗、投资回报和教育效果相关绝对化主张从严处理。 ## CN-AD-004: 互联网广告可识别性 - Authority: law - Risk default: high - Summary: 互联网广告应使消费者能够辨明其广告属性。通过知识介绍、体验分享或消费测评推销商品服务并附加购物链接等购买方式时，应显著标明“广告”。 - Review action: 检查短视频、直播、种草、测评、探店、软文和达人推荐是否存在购买路径及商业关系；广告标识应清晰、显著且与内容同步，不能藏在折叠区或模糊小字中。 ## CN-AD-005: 禁投、审查和健康养生变相广告 - Authority: law - Risk default: prohibited - Summary: 禁止互联网烟草及处方药广告。医疗、药品、医疗器械、农药、兽药、保健食品和特殊医学用途配方食品等依法须审查的广告，未经审查不得发布，且应按审查通过内容发布。禁止用健康养生知识变相发布相关广告。 - Review action: 健康养生内容不得在同一页面或同时出现相关经营者地址、联系方式、购物链接等。核对产品分类、广告审查文件、批准内容、有效期和发布主体。 ## CN-AD-006: 针对未成年人的互联网媒介 - Authority: law - Risk default
Github ReposUpdated 5h agoRank 70
AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
OPENCLAW
Github ReposUpdated 6mo agoRank 70
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
OPENCLAW
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/xiaoxiaochen5678-dot/skills/content-compliance-review-skill",
"sourceUrl": "https://clawhub.ai/xiaoxiaochen5678-dot/skills/content-compliance-review-skill",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-09T20:28:20.255Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-xiaoxiaochen5678-dot-content-compliance-review-skill/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-xiaoxiaochen5678-dot-content-compliance-review-skill/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-09T20:28:20.255Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "2K downloads",
"href": "https://clawhub.ai/xiaoxiaochen5678-dot/content-compliance-review-skill",
"sourceUrl": "https://clawhub.ai/xiaoxiaochen5678-dot/content-compliance-review-skill",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-09T20:28:20.255Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "0.1.0",
"href": "https://clawhub.ai/xiaoxiaochen5678-dot/content-compliance-review-skill",
"sourceUrl": "https://clawhub.ai/xiaoxiaochen5678-dot/content-compliance-review-skill",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-08-10T08:15:20.089Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-xiaoxiaochen5678-dot-content-compliance-review-skill/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-xiaoxiaochen5678-dot-content-compliance-review-skill/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 0.1.0",
"description": "Initial release of content-compliance-review skill. - Reviews planned social-media content for legal, platform-policy, account-safety, privacy, copyright, advertising, and audience-safety risks. - Supports multi-surface and multi-platform review, considering scripts, captions, images, audio, and more. - Requires detailed, evidence-based risk reporting with actionable revision suggestions and clear risk levels. - Handles missing or uncertain context transparently and does not guarantee approval or immunity from enforcement. - Establishes best practices for rule library maintenance and update workflow.",
"href": "https://clawhub.ai/xiaoxiaochen5678-dot/content-compliance-review-skill",
"sourceUrl": "https://clawhub.ai/xiaoxiaochen5678-dot/content-compliance-review-skill",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-08-10T08:15:20.089Z",
"isPublic": true
}
]
}Record generated Oct 9, 2026.