{"id":"55428fed-80ee-417b-9f68-c79ab7136533","entityType":"agent","slug":"clawhub-devinchen2014-socialdatax-sensitive-check","name":"敏感词检测与违禁词检查","canonicalUrl":"https://www.xpersona.co/agent/clawhub-devinchen2014-socialdatax-sensitive-check","canonicalPath":"/agent/clawhub-devinchen2014-socialdatax-sensitive-check","generatedAt":"2026-10-11T03:54:25.963Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T00:25:25.093Z","emptyReason":null},"description":"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 Skill: 敏感词检测与违禁词检查 Owner: devinchen2014 Summary: 用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 Tags: latest:0.1.10 Version history: v0.1.10 | 2026-08-22T15:08:06.327Z | user 同步当前 SocialDataX 使用说明与参数文案。 v0.1.9 | 2026-08-05T03:23:29.989Z | user 同步 SocialDataX 多平台公开能力口径 v0.1.8 | 2026-07-20T11:46:15.784Z | user Refresh API Key guidance to the SocialDataX AI access page.","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1777wgr53fwsangwq5485w3jd85913j:socialdatax-sensitive-check","sourceUrl":"https://clawhub.ai/devinchen2014/socialdatax-sensitive-check","homepage":"https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/devinchen2014/socialdatax-sensitive-check","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":62,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 Skill: 敏感词检测与违禁词检查 Owner: devinchen2014 Summary: 用于敏感词检测、违禁词检测、"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T00:25:25.093Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T00:25:25.093Z","emptyReason":null},"stars":null,"forks":null,"downloads":1220,"packageName":null,"latestVersion":"0.1.10","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T00:25:25.081Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T00:25:25.093Z","lastCrawledAt":"2026-10-11T00:25:25.081Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T00:25:25.081Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.10","createdAt":"2026-08-22T15:08:06.327Z","changelog":"同步当前 SocialDataX 使用说明与参数文案。","fileCount":3,"zipByteSize":4556},{"version":"0.1.9","createdAt":"2026-08-05T03:23:29.989Z","changelog":"同步 SocialDataX 多平台公开能力口径","fileCount":3,"zipByteSize":4116},{"version":"0.1.8","createdAt":"2026-07-20T11:46:15.784Z","changelog":"Refresh API Key guidance to the SocialDataX AI access page.","fileCount":3,"zipByteSize":4205},{"version":"0.1.7","createdAt":"2026-07-20T11:26:51.384Z","changelog":"Refresh API Key guidance to the SocialDataX AI access page.","fileCount":3,"zipByteSize":4350},{"version":"0.1.6","createdAt":"2026-07-20T10:39:45.102Z","changelog":"Refresh API Key guidance to the SocialDataX AI access page.","fileCount":3,"zipByteSize":4269},{"version":"0.1.5","createdAt":"2026-07-20T08:45:53.147Z","changelog":"Add balance recharge guidance to generated SocialDataX Skill.","fileCount":3,"zipByteSize":4370},{"version":"0.1.4","createdAt":"2026-07-20T08:17:53.418Z","changelog":"Add balance recharge guidance to generated SocialDataX Skill.","fileCount":3,"zipByteSize":4409},{"version":"0.1.3","createdAt":"2026-07-10T10:02:00.717Z","changelog":"Optimize sensitive words check marketplace title and disclosure copy.","fileCount":3,"zipByteSize":4137}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1777wgr53fwsangwq5485w3jd85913j:socialdatax-sensitive-check","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","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":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T03:54:25.962Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-devinchen2014-socialdatax-sensitive-check/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T00:25:25.093Z","emptyReason":null},"readme":"Skill: 敏感词检测与违禁词检查\n\nOwner: devinchen2014\n\nSummary: 用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\nTags: latest:0.1.10\n\nVersion history:\n\nv0.1.10 | 2026-08-22T15:08:06.327Z | user\n\n同步当前 SocialDataX 使用说明与参数文案。\n\nv0.1.9 | 2026-08-05T03:23:29.989Z | user\n\n同步 SocialDataX 多平台公开能力口径\n\nv0.1.8 | 2026-07-20T11:46:15.784Z | user\n\nRefresh API Key guidance to the SocialDataX AI access page.\n\nv0.1.7 | 2026-07-20T11:26:51.384Z | user\n\nRefresh API Key guidance to the SocialDataX AI access page.\n\nv0.1.6 | 2026-07-20T10:39:45.102Z | user\n\nRefresh API Key guidance to the SocialDataX AI access page.\n\nv0.1.5 | 2026-07-20T08:45:53.147Z | user\n\nAdd balance recharge guidance to generated SocialDataX Skill.\n\nv0.1.4 | 2026-07-20T08:17:53.418Z | user\n\nAdd balance recharge guidance to generated SocialDataX Skill.\n\nv0.1.3 | 2026-07-10T10:02:00.717Z | user\n\nOptimize sensitive words check marketplace title and disclosure copy.\n\nv0.1.2 | 2026-07-04T14:09:12.560Z | user\n\nImprove ClawHub long-tail discovery for platform sensitive word and copy compliance searches.\n\nv0.1.1 | 2026-07-04T13:57:54.362Z | user\n\nImprove ClawHub search keywords for sensitive words and prohibited words discovery.\n\nv0.1.0 | 2026-07-02T12:07:16.270Z | user\n\nAdd SocialDataX text sensitive-check skill listing.\n\nArchive index:\n\nArchive v0.1.10: 3 files, 4556 bytes\n\nFiles: skill-card.md (2364b), SKILL.md (5781b), _meta.json (147b)\n\nFile v0.1.10:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/ai?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/ai?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 如果出现 SDK/依赖缺失、npm 网络、Node.js/npm/npx 不可用或执行权限错误：这是本地运行环境、依赖安装、网络或 AI 平台授权问题，不是 SocialDataX API Key 或业务数据返回错误；有权限时可自动安装或修复；需要网络或执行授权时提醒用户同意或完成授权；处理后继续原命令；不要改用公开网页搜索替代 SocialDataX 数据。\n- 非余额不足的网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 如果返回 `insufficient_balance` 或“积分不足”：不要重复重试；把错误里的充值链接原样展示给用户，并提醒用户充值后继续执行刚才同一条命令。\n- 如果用户已经充值但仍提示余额不足：确认当前环境变量 `SOCIALDATAX_API_KEY` 是否来自刚充值的同一个账号；必要时重新复制官网后台的 API Key。\n- 重试仍失败：说明当前调用不可用，请用户补充或更换关键词、链接、ID 等输入后再重试。\n\n## 常见问题\n\n- 没结果：确认输入对象完整，再缩小分析范围。\n- 调用失败：先确认 `SOCIALDATAX_API_KEY` 已配置；如果是 `insufficient_balance` 或“积分不足”，按错误里的充值链接充值后继续原命令，不要反复重试。\n- 担心账号安全：这是只读能力，不登录、不发帖、不点赞、不评论。\n- 想继续分析：把最相关的 1-3 条结果发回来，继续缩小范围。\n\nFile v0.1.10:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.10\",\n  \"publishedAt\": 1787411286327\n}\n\nFile v0.1.10:skill-card.md\n\n## Description:\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[devinchen2014](https://clawhub.ai/user/devinchen2014)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and content teams use this skill to check draft text for sensitive or prohibited wording before publishing. It returns violation status, risk level, hit categories, highlighted risk fragments, and safer rewrite suggestions for generic text and Xiaohongshu, Douyin, or Kuaishou contexts.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill runs a mutable third-party npm package at runtime.\n\nMitigation: Use only after trusting the SocialDataX npm publisher and prefer a pinned, reviewed package version.\n\nRisk: Checked text is sent to the SocialDataX service and may be stored for history, billing, and troubleshooting.\n\nMitigation: Avoid submitting unrelated sensitive content and limit inputs to the text that needs review.\n\nRisk: The runtime command uses SOCIALDATAX_API_KEY from the environment.\n\nMitigation: Expose only the required environment variable when running the command.\n\n## Reference(s):\n\n- [SocialDataX API key and product page](https://socialdatax.com/ai?from=clawhub)\n- [ClawHub skill page](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check)\n- [ClawHub publisher profile](https://clawhub.ai/user/devinchen2014)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell command examples and JSON service responses]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires Node.js, npm, and SOCIALDATAX_API_KEY; supports generic, xhs, douyin, and kuaishou platform context.]\n\n## Skill Version(s):\n\n0.1.10 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.1.9: 3 files, 4116 bytes\n\nFiles: skill-card.md (2222b), SKILL.md (5319b), _meta.json (146b)\n\nFile v0.1.9:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/ai?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/ai?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 非余额不足的网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 如果返回 `insufficient_balance` 或“积分不足”：不要重复重试；把错误里的充值链接原样展示给用户，并提醒用户充值后继续执行刚才同一条命令。\n- 如果用户已经充值但仍提示余额不足：确认当前环境变量 `SOCIALDATAX_API_KEY` 是否来自刚充值的同一个账号；必要时重新复制官网后台的 API Key。\n- 重试仍失败：说明当前调用不可用，给出可替代输入方式。\n\n## 常见问题\n\n- 没结果：确认输入对象完整，再缩小分析范围。\n- 调用失败：先确认 `SOCIALDATAX_API_KEY` 已配置；如果是 `insufficient_balance` 或“积分不足”，按错误里的充值链接充值后继续原命令，不要反复重试。\n- 担心账号安全：这是只读能力，不登录、不发帖、不点赞、不评论。\n- 想继续分析：把最相关的 1-3 条结果发回来，继续缩小范围。\n\nFile v0.1.9:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.9\",\n  \"publishedAt\": 1785900209989\n}\n\nFile v0.1.9:skill-card.md\n\n## Description:\n\nChecks draft text for sensitive or prohibited terms, platform-specific content risks, compliance concerns, and safer rewrite suggestions for Xiaohongshu, Douyin, Kuaishou, and general text.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[devinchen2014](https://clawhub.ai/user/devinchen2014)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users, creators, marketers, and agents use this skill to check draft copy for sensitive terms, prohibited wording, platform risk signals, and safer rewrite options before publication.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Submitted text and structured results are sent to and retained by SocialDataX for history, billing, and troubleshooting.\n\nMitigation: Avoid submitting confidential drafts unless that data handling is acceptable for the user or organization.\n\nRisk: API credentials could be exposed if supplied outside the documented environment variable flow.\n\nMitigation: Provide the API key only through SOCIALDATAX_API_KEY and do not include it in prompts, shell history examples, or skill text.\n\nRisk: The current release checks text only and does not support image sensitivity checks.\n\nMitigation: Use this skill only for text review and route image review needs to a separate supported capability.\n\n## Reference(s):\n\n- [SocialDataX AI](https://socialdatax.com/ai?from=clawhub)\n- [ClawHub skill page](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with inline shell commands and JSON service results]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires SOCIALDATAX_API_KEY and the node/npm-based socialdatax-skills package; checks only text in the current release.]\n\n## Skill Version(s):\n\n0.1.9 (source: release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.1.8: 3 files, 4205 bytes\n\nFiles: skill-card.md (2046b), SKILL.md (5352b), _meta.json (146b)\n\nFile v0.1.8:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/ai?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/ai?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 非余额不足的网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 如果返回 `insufficient_balance` 或“积分不足”：不要重复重试；把错误里的充值链接原样展示给用户，并提醒用户充值后继续执行刚才同一条命令。\n- 如果用户已经充值但仍提示余额不足：确认当前环境变量 `SOCIALDATAX_API_KEY` 是否来自刚充值的同一个账号；必要时重新复制官网后台的 API Key。\n- 重试仍失败：说明当前调用不可用，给出可替代输入方式。\n\n## 常见问题\n\n- 没结果：确认输入对象完整，再缩小分析范围。\n- 调用失败：先确认 `SOCIALDATAX_API_KEY` 已配置；如果是 `insufficient_balance` 或“积分不足”，按错误里的充值链接充值后继续原命令，不要反复重试。\n- 担心账号安全：这是只读能力，不登录、不发帖、不点赞、不评论。\n- 想继续分析：把最相关的 1-3 条结果发回来，继续缩小范围。\n\nFile v0.1.8:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.8\",\n  \"publishedAt\": 1784547975784\n}\n\nFile v0.1.8:skill-card.md\n\n## Description: <br>\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议，支持小红书、抖音、快手和通用文本场景。 <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[devinchen2014](https://clawhub.ai/user/devinchen2014) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nContent creators, marketers, and agents use this skill to check draft Chinese social content for sensitive or prohibited wording before publishing. It returns risk status, risk level, matched issue types, highlighted text, and safer rewrite suggestions for generic, Xiaohongshu, Douyin, and Kuaishou contexts. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: User-provided draft text is sent to SocialDataX and may be retained with analysis results for disclosed operational purposes. <br>\nMitigation: Avoid submitting secrets or highly confidential drafts unless the user's SocialDataX account and policies permit that use. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check) <br>\n- [SocialDataX AI access page](https://socialdatax.com/ai?from=clawhub) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, json, shell commands, guidance] <br>\n**Output Format:** [Markdown summary for agent responses; CLI and MCP calls return JSON.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires SOCIALDATAX_API_KEY; avoid echoing the full submitted draft unless the user explicitly asks.] <br>\n\n## Skill Version(s): <br>\n0.1.8 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.7: 3 files, 4350 bytes\n\nFiles: skill-card.md (2439b), SKILL.md (5352b), _meta.json (146b)\n\nFile v0.1.7:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/ai?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/ai?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 非余额不足的网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 如果返回 `insufficient_balance` 或“积分不足”：不要重复重试；把错误里的充值链接原样展示给用户，并提醒用户充值后继续执行刚才同一条命令。\n- 如果用户已经充值但仍提示余额不足：确认当前环境变量 `SOCIALDATAX_API_KEY` 是否来自刚充值的同一个账号；必要时重新复制官网后台的 API Key。\n- 重试仍失败：说明当前调用不可用，给出可替代输入方式。\n\n## 常见问题\n\n- 没结果：确认输入对象完整，再缩小分析范围。\n- 调用失败：先确认 `SOCIALDATAX_API_KEY` 已配置；如果是 `insufficient_balance` 或“积分不足”，按错误里的充值链接充值后继续原命令，不要反复重试。\n- 担心账号安全：这是只读能力，不登录、不发帖、不点赞、不评论。\n- 想继续分析：把最相关的 1-3 条结果发回来，继续缩小范围。\n\nFile v0.1.7:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.7\",\n  \"publishedAt\": 1784546811384\n}\n\nFile v0.1.7:skill-card.md\n\n## Description: <br>\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[devinchen2014](https://clawhub.ai/user/devinchen2014) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and content teams use this skill to check draft text for sensitive or prohibited wording before publishing. It supports platform-aware review for generic text, Xiaohongshu, Douyin, and Kuaishou, returning risk level, matched categories, highlighted fragments, and rewrite suggestions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Checked text is sent to SocialDataX and retained by the service for history, billing, and troubleshooting. <br>\nMitigation: Avoid submitting secrets or highly confidential drafts unless that retention is acceptable. <br>\nRisk: The skill requires SOCIALDATAX_API_KEY and network access through the SocialDataX CLI or MCP tool. <br>\nMitigation: Use the documented SocialDataX AI access page to obtain the key and keep it in the environment rather than embedding it in prompts, files, or shared logs. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check) <br>\n- [SocialDataX AI access page](https://socialdatax.com/ai?from=clawhub) <br>\n- [Publisher profile](https://clawhub.ai/user/devinchen2014) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown guidance with optional shell commands and JSON-shaped API results] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Results may include violation status, risk level, matched types, highlighted fragments, summaries, platform context, and rewrite suggestions.] <br>\n\n## Skill Version(s): <br>\n0.1.7 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.6: 3 files, 4269 bytes\n\nFiles: skill-card.md (2249b), SKILL.md (5352b), _meta.json (146b)\n\nFile v0.1.6:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/ai?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/ai?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 非余额不足的网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 如果返回 `insufficient_balance` 或“积分不足”：不要重复重试；把错误里的充值链接原样展示给用户，并提醒用户充值后继续执行刚才同一条命令。\n- 如果用户已经充值但仍提示余额不足：确认当前环境变量 `SOCIALDATAX_API_KEY` 是否来自刚充值的同一个账号；必要时重新复制官网后台的 API Key。\n- 重试仍失败：说明当前调用不可用，给出可替代输入方式。\n\n## 常见问题\n\n- 没结果：确认输入对象完整，再缩小分析范围。\n- 调用失败：先确认 `SOCIALDATAX_API_KEY` 已配置；如果是 `insufficient_balance` 或“积分不足”，按错误里的充值链接充值后继续原命令，不要反复重试。\n- 担心账号安全：这是只读能力，不登录、不发帖、不点赞、不评论。\n- 想继续分析：把最相关的 1-3 条结果发回来，继续缩小范围。\n\nFile v0.1.6:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.6\",\n  \"publishedAt\": 1784543985102\n}\n\nFile v0.1.6:skill-card.md\n\n## Description: <br>\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议，支持小红书、抖音、快手和通用文本场景。 <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[devinchen2014](https://clawhub.ai/user/devinchen2014) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and content operators use this skill to check draft social-media or general text for sensitive terms, prohibited content, platform risk, and safer rewrite options before publication. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: User-provided text is sent to the SocialDataX external API and may be stored server-side for history, billing, and troubleshooting. <br>\nMitigation: Avoid submitting secrets, private credentials, or highly sensitive unpublished material unless organizational policy approves that use. <br>\nRisk: Returned content-safety classifications and rewrite suggestions may be incomplete or unsuitable for a specific platform policy decision. <br>\nMitigation: Review the returned violation status, risk level, hit types, highlights, and suggestions before publishing or taking enforcement action. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check) <br>\n- [SocialDataX AI access page](https://socialdatax.com/ai?from=clawhub) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Shell commands, API Calls, JSON, Guidance] <br>\n**Output Format:** [JSON results with concise Markdown summary and rewrite suggestions] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires SOCIALDATAX_API_KEY; supports generic, xhs, douyin, and kuaishou platform contexts.] <br>\n\n## Skill Version(s): <br>\n0.1.6 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.5: 3 files, 4370 bytes\n\nFiles: skill-card.md (2443b), SKILL.md (5348b), _meta.json (146b)\n\nFile v0.1.5:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 非余额不足的网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 如果返回 `insufficient_balance` 或“积分不足”：不要重复重试；把错误里的充值链接原样展示给用户，并提醒用户充值后继续执行刚才同一条命令。\n- 如果用户已经充值但仍提示余额不足：确认当前环境变量 `SOCIALDATAX_API_KEY` 是否来自刚充值的同一个账号；必要时重新复制官网后台的 API Key。\n- 重试仍失败：说明当前调用不可用，给出可替代输入方式。\n\n## 常见问题\n\n- 没结果：确认输入对象完整，再缩小分析范围。\n- 调用失败：先确认 `SOCIALDATAX_API_KEY` 已配置；如果是 `insufficient_balance` 或“积分不足”，按错误里的充值链接充值后继续原命令，不要反复重试。\n- 担心账号安全：这是只读能力，不登录、不发帖、不点赞、不评论。\n- 想继续分析：把最相关的 1-3 条结果发回来，继续缩小范围。\n\nFile v0.1.5:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.5\",\n  \"publishedAt\": 1784537153147\n}\n\nFile v0.1.5:skill-card.md\n\n## Description: <br>\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[devinchen2014](https://clawhub.ai/user/devinchen2014) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and content teams use this skill to check draft text for sensitive or prohibited terms before publishing. It returns risk status, risk level, matched categories, highlighted risk fragments, and safer rewrite suggestions for generic, Xiaohongshu, Douyin, and Kuaishou text scenarios. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Draft text is sent to the hosted SocialDataX API for review. <br>\nMitigation: Avoid submitting confidential drafts unless SocialDataX server-side handling is acceptable for the use case. <br>\nRisk: The skill requires a SOCIALDATAX_API_KEY for CLI or MCP use. <br>\nMitigation: Store the API key in the environment variable only and avoid placing it in prompts, shared files, or command transcripts. <br>\nRisk: The artifact states that submitted text and structured detection results may be stored for history, billing, and troubleshooting. <br>\nMitigation: Use the skill only for content where that storage behavior is acceptable. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check) <br>\n- [SocialDataX homepage](https://socialdatax.com/?from=clawhub) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Analysis, Shell commands, Guidance] <br>\n**Output Format:** [Markdown guidance with optional JSON results from the SocialDataX CLI or MCP tool] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires SOCIALDATAX_API_KEY and node/npm; supports platform values generic, xhs, douyin, and kuaishou.] <br>\n\n## Skill Version(s): <br>\n0.1.5 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.4: 3 files, 4409 bytes\n\nFiles: skill-card.md (2597b), SKILL.md (5348b), _meta.json (146b)\n\nFile v0.1.4:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名；do not infer alternate domains。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 非余额不足的网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 如果返回 `insufficient_balance` 或“积分不足”：不要重复重试；把错误里的充值链接原样展示给用户，并提醒用户充值后继续执行刚才同一条命令。\n- 如果用户已经充值但仍提示余额不足：确认当前环境变量 `SOCIALDATAX_API_KEY` 是否来自刚充值的同一个账号；必要时重新复制官网后台的 API Key。\n- 重试仍失败：说明当前调用不可用，给出可替代输入方式。\n\n## 常见问题\n\n- 没结果：确认输入对象完整，再缩小分析范围。\n- 调用失败：先确认 `SOCIALDATAX_API_KEY` 已配置；如果是 `insufficient_balance` 或“积分不足”，按错误里的充值链接充值后继续原命令，不要反复重试。\n- 担心账号安全：这是只读能力，不登录、不发帖、不点赞、不评论。\n- 想继续分析：把最相关的 1-3 条结果发回来，继续缩小范围。\n\nFile v0.1.4:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.4\",\n  \"publishedAt\": 1784535473418\n}\n\nFile v0.1.4:skill-card.md\n\n## Description: <br>\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[devinchen2014](https://clawhub.ai/user/devinchen2014) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nContent, social media, and marketing teams use this skill to check draft text for sensitive words, platform-specific compliance risk, and safer rewrite options before publishing. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Submitted draft text is sent to SocialDataX and may be retained for history, billing, and troubleshooting. <br>\nMitigation: Use a dedicated API key and avoid submitting secrets, private drafts, or regulated content unless SocialDataX retention is acceptable for the use case. <br>\nRisk: The skill depends on SOCIALDATAX_API_KEY and a network call to the SocialDataX service. <br>\nMitigation: Store the API key in the agent environment, do not paste it into prompts or files, and confirm the key belongs to the intended account before retrying balance-related failures. <br>\nRisk: The current release supports text sensitive-word checks only. <br>\nMitigation: Use it for text review workflows and route image-sensitive checks to a separate capability when available. <br>\n\n\n## Reference(s): <br>\n- [SocialDataX](https://socialdatax.com/?from=clawhub) <br>\n- [ClawHub skill listing](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check) <br>\n- [Publisher profile](https://clawhub.ai/user/devinchen2014) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance] <br>\n**Output Format:** [Markdown guidance backed by JSON service results and optional shell command snippets] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Uses SOCIALDATAX_API_KEY, supports generic, xhs, douyin, and kuaishou platform contexts, and should avoid echoing the full submitted draft unless requested.] <br>\n\n## Skill Version(s): <br>\n0.1.4 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.3: 3 files, 4137 bytes\n\nFiles: skill-card.md (2427b), SKILL.md (4784b), _meta.json (146b)\n\nFile v0.1.3:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 重试仍失败：说明当前调用不可用，给出可替代输入方式。\n\n## 常见问题\n\n- 没结果：确认输入对象完整，再缩小分析范围。\n- 调用失败：先确认 `SOCIALDATAX_API_KEY` 已配置，再重试。\n- 担心账号安全：这是只读能力，不登录、不发帖、不点赞、不评论。\n- 想继续分析：把最相关的 1-3 条结果发回来，继续缩小范围。\n\nFile v0.1.3:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.3\",\n  \"publishedAt\": 1783677720717\n}\n\nFile v0.1.3:skill-card.md\n\n## Description: <br>\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[devinchen2014](https://clawhub.ai/user/devinchen2014) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal creators, marketers, and content reviewers use this skill to check draft text for sensitive or prohibited wording before publishing. It can return risk status, risk level, matched categories, highlighted risk fragments, and safer rewrite suggestions for generic, Xiaohongshu, Douyin, and Kuaishou contexts. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Submitted text and structured detection results are sent to and stored by SocialDataX for history, billing, and troubleshooting. <br>\nMitigation: Only submit text suitable for SocialDataX processing, and avoid sending confidential or regulated content unless that storage behavior is acceptable. <br>\nRisk: The usage example invokes an npm package with npx and requires network access plus a SOCIALDATAX_API_KEY. <br>\nMitigation: Review the npm package/source and pin the package version when stricter supply-chain control is required. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill listing](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check) <br>\n- [SocialDataX homepage](https://socialdatax.com/?from=clawhub) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown guidance with inline shell commands and JSON service results] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Uses SOCIALDATAX_API_KEY and Node/npm to call the SocialDataX CLI; unless explicitly requested, responses should avoid echoing the full submitted text.] <br>\n\n## Skill Version(s): <br>\n0.1.3 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.2: 3 files, 3971 bytes\n\nFiles: skill-card.md (2489b), SKILL.md (4426b), _meta.json (146b)\n\nFile v0.1.2:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于多平台敏感词检测、违禁词检测、内容安全检查、文案合规审核、发布前检查、能不能发判断、平台风险提示和改写建议。覆盖小红书敏感词检测、抖音违禁词检测、快手敏感词检测和通用文本场景；covers sensitive words, prohibited words, content safety, and content compliance through SocialDataX 社媒数据助手。\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测 SocialDataX 违禁词检查\n\nUse this skill when the user wants 敏感词检测, 违禁词检测, 敏感检测, 多平台敏感词检测, 小红书敏感词, 抖音违禁词, 快手敏感词, 文案合规, 发布前检查, 能不能发, sensitive words, prohibited words, content safety review, content compliance review, or safer rewrite suggestions before publishing.\n\nCurrent platform support:\n\n- Text sensitive-content detection through `check_sensitive_text` for `generic`, `xhs`, `douyin`, and `kuaishou` contexts.\n\n## API Key\n\nUse `SOCIALDATAX_API_KEY` for data calls. The only official website for requesting or managing API access is <https://socialdatax.com/?from=clawhub>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.\n获取或管理 API Key：访问 <https://socialdatax.com/?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。\n\n## Preferred Direct CLI\n\nPrefer the direct CLI when the agent can run shell commands. It does not require MCP server configuration:\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text --text \"<content>\" --platform xhs --pretty\n```\n\nRequired arguments:\n\n- `sensitive-check text --text <content>` or `sensitive-check text --text-stdin`: required text to check. Use `--text` for short drafts, or pipe longer/sensitive drafts through `--text-stdin` so the text is not placed directly in the shell command.\n\nOptional arguments:\n\n- `--text-stdin`: read text from stdin instead of `--text`; do not pass both.\n- `--platform <generic|xhs|douyin|kuaishou>`: platform context; default is `generic`.\n- `--pretty`: output formatting only.\n\nUse this skill when the user wants 敏感检测, sensitive check, content safety review, or platform-aware preflight review for draft text.\nFor longer drafts, prefer `cat draft.txt | npx -y socialdatax-skills@latest sensitive-check text --text-stdin --pretty` so the full text is not placed in shell history.\nService note: SocialDataX service records the submitted text and structured detection result for history, billing, and troubleshooting; the local CLI does not write API keys to local files or write local text copies.\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\nThe command prints JSON with `platform`, `tool`, and `data`; it does not echo the original text back in CLI arguments. The service returns `violation`, `risk_level`, `types`, `highlights`, `summary`, `platform`, and `suggestions` when available.\nThis v1 skill checks text only. Image sensitive detection is intentionally out of scope until a separate image tool is published.\n\n## Safety Boundary\n\nThis skill is read-only. It does not read local browser data, does not perform login, posting, liking, commenting, or account changes. The local CLI and installer do not write API keys to local files.\n\n## MCP Tools\n\nMCP tools matching the direct CLI commands above:\n\n- `check_sensitive_text`\n\nIf MCP tools are already available in the current agent, call `check_sensitive_text` with `text` and optional `platform`: `generic`, `xhs`, `douyin`, or `kuaishou`.\n\n## Output Guidance\n\nReport whether there is a violation, the risk level, detected types, brief highlights, and concrete rewrite suggestions.\nDo not echo the full original text back unless the user explicitly asks; prefer short highlights and safer rewrite guidance.\n\nFile v0.1.2:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.2\",\n  \"publishedAt\": 1783174152560\n}\n\nFile v0.1.2:skill-card.md\n\n## Description: <br>\n用于多平台敏感词检测、违禁词检测、内容安全检查、文案合规审核、发布前检查、能不能发判断、平台风险提示和改写建议。覆盖小红书敏感词检测、抖音违禁词检测、快手敏感词检测和通用文本场景；covers sensitive words, prohibited words, content safety, and content compliance through SocialDataX 社媒数据助手。 <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[devinchen2014](https://clawhub.ai/user/devinchen2014) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and content teams use this skill to check draft text for sensitive or prohibited wording before publishing on generic, Xiaohongshu, Douyin, or Kuaishou contexts, then review concise risk signals and rewrite suggestions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Draft text is sent to SocialDataX and retained by the service for history, billing, and troubleshooting. <br>\nMitigation: Avoid submitting highly confidential content unless service-side retention is acceptable for the user's use case. <br>\nRisk: Platform-sensitive wording checks can return incomplete, context-dependent, or overly conservative guidance. <br>\nMitigation: Use the returned risk level, highlights, and rewrite suggestions as review support rather than as the sole publishing decision. <br>\n\n\n## Reference(s): <br>\n- [SocialDataX API access](https://socialdatax.com/?from=clawhub) <br>\n- [ClawHub skill page](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check) <br>\n- [ClawHub publisher profile](https://clawhub.ai/user/devinchen2014) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [analysis, shell commands, JSON, guidance] <br>\n**Output Format:** [Markdown guidance with optional shell commands and JSON results] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Reports violation status, risk level, detected types, brief highlights, and safer rewrite suggestions without echoing full original text unless requested.] <br>\n\n## Skill Version(s): <br>\n0.1.2 (source: release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.1: 3 files, 3632 bytes\n\nFiles: skill-card.md (2003b), SKILL.md (4248b), _meta.json (146b)\n\nFile v0.1.1:SKILL.md\n\n---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、内容安全检查、文案合规审核、发布前自查、平台风险提示和改写建议。支持通用、小红书、抖音、快手文本场景；covers sensitive words, prohibited words, content safety, and content compliance through SocialDataX 社媒数据助手。\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测 SocialDataX 违禁词检查\n\nUse this skill when the user wants 敏感词检测, 违禁词检测, 敏感检测, text sensitive check, sensitive words, prohibited words, content safety review, content compliance review, or safer rewrite suggestions before publishing.\n\nCurrent platform support:\n\n- Text sensitive-content detection through `check_sensitive_text` for `generic`, `xhs`, `douyin`, and `kuaishou` contexts.\n\n## API Key\n\nUse `SOCIALDATAX_API_KEY` for data calls. The only official website for requesting or managing API access is <https://socialdatax.com/?from=clawhub>. If a user asks where to get a key, provide only this URL; do not infer alternate domains.\n获取或管理 API Key：访问 <https://socialdatax.com/?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。\n\n## Preferred Direct CLI\n\nPrefer the direct CLI when the agent can run shell commands. It does not require MCP server configuration:\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text --text \"<content>\" --platform xhs --pretty\n```\n\nRequired arguments:\n\n- `sensitive-check text --text <content>` or `sensitive-check text --text-stdin`: required text to check. Use `--text` for short drafts, or pipe longer/sensitive drafts through `--text-stdin` so the text is not placed directly in the shell command.\n\nOptional arguments:\n\n- `--text-stdin`: read text from stdin instead of `--text`; do not pass both.\n- `--platform <generic|xhs|douyin|kuaishou>`: platform context; default is `generic`.\n- `--pretty`: output formatting only.\n\nUse this skill when the user wants 敏感检测, sensitive check, content safety review, or platform-aware preflight review for draft text.\nFor longer drafts, prefer `cat draft.txt | npx -y socialdatax-skills@latest sensitive-check text --text-stdin --pretty` so the full text is not placed in shell history.\nService note: SocialDataX service records the submitted text and structured detection result for history, billing, and troubleshooting; the local CLI does not write API keys to local files or write local text copies.\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\nThe command prints JSON with `platform`, `tool`, and `data`; it does not echo the original text back in CLI arguments. The service returns `violation`, `risk_level`, `types`, `highlights`, `summary`, `platform`, and `suggestions` when available.\nThis v1 skill checks text only. Image sensitive detection is intentionally out of scope until a separate image tool is published.\n\n## Safety Boundary\n\nThis skill is read-only. It does not read local browser data, does not perform login, posting, liking, commenting, or account changes. The local CLI and installer do not write API keys to local files.\n\n## MCP Tools\n\nMCP tools matching the direct CLI commands above:\n\n- `check_sensitive_text`\n\nIf MCP tools are already available in the current agent, call `check_sensitive_text` with `text` and optional `platform`: `generic`, `xhs`, `douyin`, or `kuaishou`.\n\n## Output Guidance\n\nReport whether there is a violation, the risk level, detected types, brief highlights, and concrete rewrite suggestions.\nDo not echo the full original text back unless the user explicitly asks; prefer short highlights and safer rewrite guidance.\n\nFile v0.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.1\",\n  \"publishedAt\": 1783173474362\n}\n\nFile v0.1.1:skill-card.md\n\n## Description: <br>\nChecks draft text for sensitive or prohibited words and content-compliance risk across generic, Xiaohongshu, Douyin, and Kuaishou contexts through SocialDataX. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[devinchen2014](https://clawhub.ai/user/devinchen2014) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal creators, marketers, and developers use this skill to check draft text before publishing and receive platform-aware risk signals, brief highlights, and safer rewrite suggestions. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Submitted draft text is sent to SocialDataX and retained by that service for history, billing, troubleshooting, and related operational purposes. <br>\nMitigation: Avoid submitting secrets or highly sensitive unpublished material unless that retention is acceptable; use stdin for longer drafts so content is not placed directly in shell command history. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill listing](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check) <br>\n- [SocialDataX API access](https://socialdatax.com/?from=clawhub) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, JSON, Shell commands, Guidance] <br>\n**Output Format:** [Markdown summary with optional shell command and JSON tool output excerpts] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Reports violation status, risk level, detected types, highlights, and rewrite suggestions; avoids echoing full original text unless requested.] <br>\n\n## Skill Version(s): <br>\n0.1.1 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: 敏感词检测与违禁词检查 Owner: devinchen2014 Summary: 用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 Tags: latest:0.1.10 Version history: v0.1.10 | 2026-08-22T15:08:06.327Z | user 同步当前 SocialDataX 使用说明与参数文案。 v0.1.9 | 2026-08-05T03:23:29.989Z | user 同步 SocialDataX 多平台公开能力口径 v0.1.8 | 2026-07-20T11:46:15.784Z | user Refresh API Key guidance to the SocialDataX AI access page. ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"npx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check"},{"language":"bash","snippet":"npx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check"},{"language":"bash","snippet":"npx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check"},{"language":"bash","snippet":"npx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check"},{"language":"bash","snippet":"npx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check"},{"language":"bash","snippet":"npx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: \"socialdatax-sensitive-check\"\ndescription: \"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\"\nsource_client: \"socialdatax-skills\"\nsource_platform: \"clawhub\"\nsource_skill: \"socialdatax-sensitive-check\"\nmetadata: {\"openclaw\":{\"requires\":{\"env\":[\"SOCIALDATAX_API_KEY\"],\"bins\":[\"node\",\"npm\"]},\"primaryEnv\":\"SOCIALDATAX_API_KEY\",\"install\":[{\"kind\":\"node\",\"package\":\"socialdatax-skills\",\"bins\":[]}],\"emoji\":\"🛡️\",\"homepage\":\"https://socialdatax.com/ai?from=clawhub\"}}\n---\n<!-- AUTO-GENERATED from socialdatax-skill-source. Do not edit directly; run `node scripts/generate_socialdatax_skills.mjs`. -->\n\n# 敏感词检测与违禁词检查\n\n## 适用场景\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\n## 快速开始\n\n- 粘贴要检测的文案，并按需要指定平台：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n- 你通常会得到：是否违规、风险等级、命中类型、风险片段和改写建议。\n\n## API Key 获取\n\n获取或管理 API Key：访问 <https://socialdatax.com/ai?from=clawhub>，按官网的 API Key 申请/管理入口操作。环境变量名固定使用 `SOCIALDATAX_API_KEY`；不要引导用户使用其他域名。\n\n## 直接调用命令\n\n优先使用 direct CLI；能运行 shell 命令的 Agent 不需要额外配置 MCP server：\n\n```bash\nnpx -y socialdatax-skills@latest sensitive-check text \\\n  --text \"<content>\" --platform xhs --pretty --source-client socialdatax-skills \\\n  --source-platform clawhub --source-skill socialdatax-sensitive-check\n```\n\n## 参数说明\n\n通用：\n- 必填：`sensitive-check text --text <content>`：必填文本；使用用户要检查的文案进行分析，但不要把原文保存在 skill 文案里。\n- 可选：`--platform <generic|xhs|douyin|kuaishou>`：平台上下文，可选；默认是 `generic`。\n- 可选：`--pretty`：只影响输出格式，不改变实际请求结果。\n- 可选：`--source-client socialdatax-skills --source-platform clawhub --source-skill socialdatax-sensitive-check`：这是当前 Agent Skill 的来源标记；按本 Skill 示例执行时保持这些值不变。\n\n适用于敏感词检测、违禁词检查、文案发布前检查、content safety review、文案合规审核、能不能发判断和 safer rewrite suggestions for draft text.\n命令返回 JSON，包含 `platform`、`tool` 和 `data`，不会在 CLI 参数区回显原文。服务会在可用时返回 `violation`、`risk_level`、`types`、`highlights`、`summary`、`platform` 和 `suggestions`。\n服务端会保存提交文本和结构化检测结果，用于历史记录、计费和问题排查；本地 CLI 不会把 API Key 写入本地文件，也不会写本地文本副本。\n当前 v1 只支持文本敏感检测；图片敏感检测要等单独的图片能力发布后再支持。\n\n## 输出建议\n\n优先输出是否违规、风险等级、命中类型、关键提示和可执行改写建议。\n\n输出时说明是否违规、风险等级、命中的类型、关键提示，以及可执行的改写建议。\n除非用户明确要求，否则不要回显完整原文；优先给出简短提示和更安全的改写建议。\n\n## MCP 工具\n\n与上面 direct CLI 命令对应的 MCP 工具：\n\n- `check_sensitive_text`\n\n如果当前 Agent 已可直接调用 MCP 工具，使用 `check_sensitive_text`，传入 `text`，并可选传 `platform`：`generic`、`xhs`、`douyin` 或 `kuaishou`。\n\n## 安全边界\n\n这是只读 skill。运行时使用用户环境变量中的 `SOCIALDATAX_API_KEY`；生成的 Skill 文件不包含 API Key。不会读取本地浏览器数据，也不会执行登录、发帖、点赞、评论或账号修改。\n\n## 示例结果\n\n- 示例展示格式，不代表固定字段：风险=是否违规/风险等级/命中类型；建议=可替换表达和发布前注意点。\n\n## 异常处理\n\n- 如果出现 SDK/依赖缺失、npm 网络、Node.js/npm/npx 不可用或执行权限错误：这是本地运行环境、依赖安装、网络或 AI 平台授权问题，不是 SocialDataX API Key 或业务数据返回错误；有权限时可自动安装或修复；需要网络或执行授权时提醒用户同意或完成授权；处理后继续原命令；不要改用公开网页搜索替代 SocialDataX 数据。\n- 非余额不足的网络或 API 异常：保留错误信息，检查 `SOCIALDATAX_API_KEY`、参数和链接格式后原样重试一次。\n- 如果返回 `insufficient_balance` 或“积分不足”：不要重复重试；把错误里的充值链接原样展示给用户，并提醒用户充值后继续执行刚才同一条命令。\n- 如果用户已经充值但仍提示余额不足：确认当前环境变量 `SOCIALDATAX_API_KEY` 是否来自刚充值的同一个账号；必要时重新复制官网后台的 API Key。\n- 重试仍失败：说明当前调用不可用，请用户补充或更换关键词、链接、ID 等输入后再重试。\n\n"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn79gym47c788rbwr4amw8arfh859t3b\",\n  \"slug\": \"socialdatax-sensitive-check\",\n  \"version\": \"0.1.10\",\n  \"publishedAt\": 1787411286327\n}"},{"path":"skill-card.md","content":"## Description:\n\n用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[devinchen2014](https://clawhub.ai/user/devinchen2014)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and content teams use this skill to check draft text for sensitive or prohibited wording before publishing. It returns violation status, risk level, hit categories, highlighted risk fragments, and safer rewrite suggestions for generic text and Xiaohongshu, Douyin, or Kuaishou contexts.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill runs a mutable third-party npm package at runtime.\n\nMitigation: Use only after trusting the SocialDataX npm publisher and prefer a pinned, reviewed package version.\n\nRisk: Checked text is sent to the SocialDataX service and may be stored for history, billing, and troubleshooting.\n\nMitigation: Avoid submitting unrelated sensitive content and limit inputs to the text that needs review.\n\nRisk: The runtime command uses SOCIALDATAX_API_KEY from the environment.\n\nMitigation: Expose only the required environment variable when running the command.\n\n## Reference(s):\n\n- [SocialDataX API key and product page](https://socialdatax.com/ai?from=clawhub)\n- [ClawHub skill page](https://clawhub.ai/devinchen2014/skills/socialdatax-sensitive-check)\n- [ClawHub publisher profile](https://clawhub.ai/user/devinchen2014)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell command examples and JSON service responses]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires Node.js, npm, and SOCIALDATAX_API_KEY; supports generic, xhs, douyin, and kuaishou platform context.]\n\n## Skill Version(s):\n\n0.1.10 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 Skill: 敏感词检测与违禁词检查 Owner: devinchen2014 Summary: 用于敏感词检测、违禁词检测、文案发布前检查、内容安全检查、文案合规审核、能不能发判断、平台风险提示和改写建议。支持小红书、抖音、快手和通用文本场景，来自 SocialDataX 社媒数据助手。 Tags: latest:0.1.10 Version history: v0.1.10 | 2026-08-22T15:08:06.327Z | user 同步当前 SocialDataX 使用说明与参数文案。 v0.1.9 | 2026-08-05T03:23:29.989Z | user 同步 SocialDataX 多平台公开能力口径 v0.1.8 | 2026-07-20T11:46:15.784Z | user Refresh API Key guidance to the SocialDataX AI access page.","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":851,"uniquenessScore":52,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T00:25:25.093Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T00:25:25.093Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T03:54:25.963Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"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!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"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","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}