{"id":"29a9afa5-84d4-4b1a-9705-5dcb33d13297","entityType":"agent","slug":"clawhub-li-jin-xuan-de-ai","name":"Humanize Text","canonicalUrl":"https://www.xpersona.co/agent/clawhub-li-jin-xuan-de-ai","canonicalPath":"/agent/clawhub-li-jin-xuan-de-ai","generatedAt":"2026-10-11T20:59:40.630Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T16:44:59.340Z","emptyReason":null},"description":"文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题， 让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。 触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人 Skill: Humanize Text Owner: li-jin-xuan Summary: 文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题， 让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。 触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人 Tags: ai-detection:1.0.0, copywriting:1.0.0, latest:1.0.0, text-optimization:1.0.0, writing:1.0.0 Version history: v1.0.0 | 2026-05-28T08:15:01.880Z | auto - **Initial release of “humanize-text” (文案去AI味优化器)** - Detects and fixes mechanical, templated, or overly","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17cfmj15rmd05fdx5yebhj11987jf7t:de-ai","sourceUrl":"https://clawhub.ai/li-jin-xuan/de-ai","homepage":"https://clawhub.ai/li-jin-xuan/skills/de-ai","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/li-jin-xuan/de-ai","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/li-jin-xuan/skills/de-ai","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题， 让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。 触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人 Skill: Humanize Text Owner: li-jin-xuan Summary: 文"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:44:59.340Z","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":"2026-10-11T16:44:59.340Z","emptyReason":null},"stars":null,"forks":null,"downloads":1025,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:44:59.328Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T16:44:59.340Z","lastCrawledAt":"2026-10-11T16:44:59.328Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T16:44:59.328Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-05-28T08:15:01.880Z","changelog":"- **Initial release of “humanize-text” (文案去AI味优化器)** - Detects and fixes mechanical, templated, or overly polite expressions in AI-generated text - Makes content sound more like it’s written by a real person; suitable for social posts, customer support, and product intros - Outlines six “AI flavor” detection points (e.g., cliché openings, long sentences, formal language) - Provides specific optimization guidelines for self-media and customer service scenarios - Includes before/after examples for practical reference","fileCount":5,"zipByteSize":5317}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17cfmj15rmd05fdx5yebhj11987jf7t:de-ai","setupComplexity":"low","setupSteps":["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":{"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-li-jin-xuan-de-ai/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T20:59:40.630Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-li-jin-xuan-de-ai/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":"2026-10-11T16:44:59.340Z","emptyReason":null},"readme":"Skill: Humanize Text\n\nOwner: li-jin-xuan\n\nSummary: 文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题， 让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。 触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人\n\nTags: ai-detection:1.0.0, copywriting:1.0.0, latest:1.0.0, text-optimization:1.0.0, writing:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-05-28T08:15:01.880Z | auto\n\n- **Initial release of “humanize-text” (文案去AI味优化器)**\n- Detects and fixes mechanical, templated, or overly polite expressions in AI-generated text\n- Makes content sound more like it’s written by a real person; suitable for social posts, customer support, and product intros\n- Outlines six “AI flavor” detection points (e.g., cliché openings, long sentences, formal language)\n- Provides specific optimization guidelines for self-media and customer service scenarios\n- Includes before/after examples for practical reference\n\nArchive index:\n\nArchive v1.0.0: 5 files, 5317 bytes\n\nFiles: references/examples.md (1828b), scripts/detect-ai-flavor.sh (1846b), skill-card.md (2195b), SKILL.md (2349b), _meta.json (124b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: humanize-text\ndescription: >\n  文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题，\n  让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。\n  触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人\n---\n\n# 文案去AI味优化器\n\n> AI味越少，转化越高。这个skill帮你把机器生成的内容改得像人写的。\n\n## 六大AI味检测点\n\n### 1. 开头太套路\n- ❌ \"在当今数字化时代，...\"\n- ❌ \"随着科技的不断发展，...\"\n- ✅ 直接说事，用\"昨天\"、\"上周\"、\"刚发现\"开头\n\n### 2. 爱用长句和连接词\n- ❌ \"此外，值得注意的是，...\"\n- ❌ \"综上所述，我们可以得出结论...\"\n- ✅ 短句。一句说完就说下一句。不用过渡词。\n\n### 3. 过度礼貌/委婉\n- ❌ \"如果您方便的话，建议您可以考虑...\"\n- ❌ \"我们诚挚地建议您...\"\n- ✅ \"试一下这个方法\" / \"别这么做\"\n\n### 4. 模板化结尾\n- ❌ \"希望以上建议对您有所帮助\"\n- ❌ \"如果您有任何问题，请随时与我们联系\"\n- ✅ 自然收尾或不收尾\n\n### 5. 缺少个人痕迹\n- ❌ 完美的逻辑结构、每段等长、完美排版\n- ✅ 偶尔的口语、括号吐槽、个人经历\n\n### 6. 用词太书面\n- ❌ \"获取\"、\"进行\"、\"共计\"、\"鉴于\"\n- ✅ \"拿到\"、\"搞\"、\"一共\"、\"因为\"\n\n## 优化规则\n\n### 小红书/自媒体风格\n```markdown\n1. 每段不超过3行\n2. 用表情符号但不要堆砌\n3. 可以有括号碎碎念（就像这样）\n4. 用\"！\"表示兴奋，\"？\"装疑惑\n5. 适当留白，不用填满每个空格\n6. 第一人称：\"我\"、\"我们\"\n7. 不要总结，不要升华\n```\n\n### 客服/回复风格\n```markdown\n1. 先共情再给方案\n2. 少用\"您好\"，用\"嗨\"或直接说事\n3. 可以适当用语气词：\"哈\"、\"嘛\"、\"吧\"\n4. 不要\"很高兴为您服务\"\n5. 不懂直接说\"这个我查一下\"\n```\n\n## 修改示例\n\n| 原文（AI味） | 修改后（人味） |\n|-------------|---------------|\n| 如果您遇到数据丢失问题，建议您立即停止使用该设备 | 数据丢了？先别往里头写东西 |\n| 我们的产品具有卓越的性能表现 | 用起来很快，不卡 |\n| 综上所述，我们推荐您选择方案A | 选A就对了 |\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7fc34rycpwvg7703ka9f4ven87je1f\",\n  \"slug\": \"de-ai\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1779956101880\n}\n\nFile v1.0.0:references/examples.md\n\n# 去AI味修改示例库\n\n## 小红书/自媒体类\n\n❌ 原文（AI味）：\n\"在当今快节奏的生活中，我们往往忽视了数据备份的重要性。本文将为您详细介绍如何有效保护您的数据安全。\"\n\n✅ 改后（人味）：\n\"上周帮客户恢复了一块硬盘，回来我自己也吓了一跳。\n赶紧把备份搞上了。\n不多说，直接分享几个血的教训👇\"\n\n❌ 原文：\n\"这款产品具有卓越的性能表现，能够有效提升您的工作效率。此外，其简洁的设计也深受用户喜爱。\"\n\n✅ 改后：\n\"速度真的快，用了回不去。\n界面也干净，看着不烦。\"\n\n## 客服/回复类\n\n❌ 原文：\n\"您好，感谢您的咨询。关于您提到的数据丢失问题，我们建议您先停止使用该设备，以免数据被覆盖。\"\n\n✅ 改后：\n\"先别往里头写东西了哈 🙏\n你一存新文件，旧数据可能就被盖掉了。\"\n\n❌ 原文：\n\"如果您对我们的服务有任何不满意之处，请随时与我们联系，我们将竭诚为您解决问题。\"\n\n✅ 改后：\n\"哪里不满意你说，我帮你调。\"\n\n## 产品介绍类\n\n❌ 原文：\n\"本产品采用先进的算法技术，能够高效地完成数据恢复任务，支持多种文件系统和存储介质。\"\n\n✅ 改后：\n\"丢了的照片、文档、视频，只要没被盖掉，基本都能拉回来。\n硬盘、U盘、内存卡都行。\"\n\n## 常见AI味词替换表\n\n| 别用 | 改用 |\n|------|------|\n| 获取 | 拿到/搞到 |\n| 进行 | 做/搞 |\n| 共计 | 一共 |\n| 鉴于 | 因为 |\n| 予以 | 给 |\n| 事宜 | 的事/的问题 |\n| 该方案 | 这个方案 |\n| 上述 | 上面说的 |\n| 如下 | 下面这些 |\n| 是否 | 是不是 |\n| 较为 | 比较 |\n| 极其 | 特别/超级 |\n| 诸多 | 很多 |\n| 以及 | 和/还有 |\n| 均为 | 都是 |\n\nFile v1.0.0:skill-card.md\n\n## Description:\n\nHumanize Text helps detect and rewrite Chinese AI-generated copy that sounds mechanical, templated, overly formal, or too polite so it reads more like natural human writing.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[li-jin-xuan](https://clawhub.ai/user/li-jin-xuan)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users, creators, support teams, and product writers use this skill to make Chinese social posts, customer replies, and product descriptions sound more natural, direct, and less AI-generated.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill is tailored to Chinese phrasing and style conventions, so output may be less appropriate for other languages or formal brand voices.\n\nMitigation: Review the rewritten text against the intended language, audience, and brand tone before publishing.\n\nRisk: The skill may activate on broad requests to make text sound more natural and could change tone, directness, or politeness more than intended.\n\nMitigation: Ask for targeted edits and compare the result with the original before using it in customer-facing content.\n\nRisk: The included shell detector uses heuristic pattern checks and scores, not a definitive AI-content classifier.\n\nMitigation: Treat script output as an editing cue and rely on human review for final quality decisions.\n\n## Reference(s):\n\n- [Examples](references/examples.md)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Natural-language guidance, Markdown examples, rewritten text, and optional shell-script detection reports]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Primarily tailored to Chinese copy-editing; no sensitive access or system changes are requested according to the security evidence.]\n\n## Skill Version(s):\n\n1.0.0 (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.","readmeExcerpt":"Skill: Humanize Text Owner: li-jin-xuan Summary: 文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题， 让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。 触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人 Tags: ai-detection:1.0.0, copywriting:1.0.0, latest:1.0.0, text-optimization:1.0.0, writing:1.0.0 Version history: v1.0.0 | 2026-05-28T08:15:01.880Z | auto - **Initial release of “humanize-text” (文案去AI味优化器)** - Detects and fixes mechanical, templated, or overly","codeSnippets":[],"executableExamples":[{"language":"markdown","snippet":"1. 每段不超过3行\n2. 用表情符号但不要堆砌\n3. 可以有括号碎碎念（就像这样）\n4. 用\"！\"表示兴奋，\"？\"装疑惑\n5. 适当留白，不用填满每个空格\n6. 第一人称：\"我\"、\"我们\"\n7. 不要总结，不要升华"},{"language":"markdown","snippet":"1. 先共情再给方案\n2. 少用\"您好\"，用\"嗨\"或直接说事\n3. 可以适当用语气词：\"哈\"、\"嘛\"、\"吧\"\n4. 不要\"很高兴为您服务\"\n5. 不懂直接说\"这个我查一下\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: humanize-text\ndescription: >\n  文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题，\n  让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。\n  触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人\n---\n\n# 文案去AI味优化器\n\n> AI味越少，转化越高。这个skill帮你把机器生成的内容改得像人写的。\n\n## 六大AI味检测点\n\n### 1. 开头太套路\n- ❌ \"在当今数字化时代，...\"\n- ❌ \"随着科技的不断发展，...\"\n- ✅ 直接说事，用\"昨天\"、\"上周\"、\"刚发现\"开头\n\n### 2. 爱用长句和连接词\n- ❌ \"此外，值得注意的是，...\"\n- ❌ \"综上所述，我们可以得出结论...\"\n- ✅ 短句。一句说完就说下一句。不用过渡词。\n\n### 3. 过度礼貌/委婉\n- ❌ \"如果您方便的话，建议您可以考虑...\"\n- ❌ \"我们诚挚地建议您...\"\n- ✅ \"试一下这个方法\" / \"别这么做\"\n\n### 4. 模板化结尾\n- ❌ \"希望以上建议对您有所帮助\"\n- ❌ \"如果您有任何问题，请随时与我们联系\"\n- ✅ 自然收尾或不收尾\n\n### 5. 缺少个人痕迹\n- ❌ 完美的逻辑结构、每段等长、完美排版\n- ✅ 偶尔的口语、括号吐槽、个人经历\n\n### 6. 用词太书面\n- ❌ \"获取\"、\"进行\"、\"共计\"、\"鉴于\"\n- ✅ \"拿到\"、\"搞\"、\"一共\"、\"因为\"\n\n## 优化规则\n\n### 小红书/自媒体风格\n```markdown\n1. 每段不超过3行\n2. 用表情符号但不要堆砌\n3. 可以有括号碎碎念（就像这样）\n4. 用\"！\"表示兴奋，\"？\"装疑惑\n5. 适当留白，不用填满每个空格\n6. 第一人称：\"我\"、\"我们\"\n7. 不要总结，不要升华\n```\n\n### 客服/回复风格\n```markdown\n1. 先共情再给方案\n2. 少用\"您好\"，用\"嗨\"或直接说事\n3. 可以适当用语气词：\"哈\"、\"嘛\"、\"吧\"\n4. 不要\"很高兴为您服务\"\n5. 不懂直接说\"这个我查一下\"\n```\n\n## 修改示例\n\n| 原文（AI味） | 修改后（人味） |\n|-------------|---------------|\n| 如果您遇到数据丢失问题，建议您立即停止使用该设备 | 数据丢了？先别往里头写东西 |\n| 我们的产品具有卓越的性能表现 | 用起来很快，不卡 |\n| 综上所述，我们推荐您选择方案A | 选A就对了 |"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7fc34rycpwvg7703ka9f4ven87je1f\",\n  \"slug\": \"de-ai\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1779956101880\n}"},{"path":"references/examples.md","content":"# 去AI味修改示例库\n\n## 小红书/自媒体类\n\n❌ 原文（AI味）：\n\"在当今快节奏的生活中，我们往往忽视了数据备份的重要性。本文将为您详细介绍如何有效保护您的数据安全。\"\n\n✅ 改后（人味）：\n\"上周帮客户恢复了一块硬盘，回来我自己也吓了一跳。\n赶紧把备份搞上了。\n不多说，直接分享几个血的教训👇\"\n\n❌ 原文：\n\"这款产品具有卓越的性能表现，能够有效提升您的工作效率。此外，其简洁的设计也深受用户喜爱。\"\n\n✅ 改后：\n\"速度真的快，用了回不去。\n界面也干净，看着不烦。\"\n\n## 客服/回复类\n\n❌ 原文：\n\"您好，感谢您的咨询。关于您提到的数据丢失问题，我们建议您先停止使用该设备，以免数据被覆盖。\"\n\n✅ 改后：\n\"先别往里头写东西了哈 🙏\n你一存新文件，旧数据可能就被盖掉了。\"\n\n❌ 原文：\n\"如果您对我们的服务有任何不满意之处，请随时与我们联系，我们将竭诚为您解决问题。\"\n\n✅ 改后：\n\"哪里不满意你说，我帮你调。\"\n\n## 产品介绍类\n\n❌ 原文：\n\"本产品采用先进的算法技术，能够高效地完成数据恢复任务，支持多种文件系统和存储介质。\"\n\n✅ 改后：\n\"丢了的照片、文档、视频，只要没被盖掉，基本都能拉回来。\n硬盘、U盘、内存卡都行。\"\n\n## 常见AI味词替换表\n\n| 别用 | 改用 |\n|------|------|\n| 获取 | 拿到/搞到 |\n| 进行 | 做/搞 |\n| 共计 | 一共 |\n| 鉴于 | 因为 |\n| 予以 | 给 |\n| 事宜 | 的事/的问题 |\n| 该方案 | 这个方案 |\n| 上述 | 上面说的 |\n| 如下 | 下面这些 |\n| 是否 | 是不是 |\n| 较为 | 比较 |\n| 极其 | 特别/超级 |\n| 诸多 | 很多 |\n| 以及 | 和/还有 |\n| 均为 | 都是 |"},{"path":"skill-card.md","content":"## Description:\n\nHumanize Text helps detect and rewrite Chinese AI-generated copy that sounds mechanical, templated, overly formal, or too polite so it reads more like natural human writing.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[li-jin-xuan](https://clawhub.ai/user/li-jin-xuan)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users, creators, support teams, and product writers use this skill to make Chinese social posts, customer replies, and product descriptions sound more natural, direct, and less AI-generated.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill is tailored to Chinese phrasing and style conventions, so output may be less appropriate for other languages or formal brand voices.\n\nMitigation: Review the rewritten text against the intended language, audience, and brand tone before publishing.\n\nRisk: The skill may activate on broad requests to make text sound more natural and could change tone, directness, or politeness more than intended.\n\nMitigation: Ask for targeted edits and compare the result with the original before using it in customer-facing content.\n\nRisk: The included shell detector uses heuristic pattern checks and scores, not a definitive AI-content classifier.\n\nMitigation: Treat script output as an editing cue and rely on human review for final quality decisions.\n\n## Reference(s):\n\n- [Examples](references/examples.md)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Natural-language guidance, Markdown examples, rewritten text, and optional shell-script detection reports]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Primarily tailored to Chinese copy-editing; no sensitive access or system changes are requested according to the security evidence.]\n\n## Skill Version(s):\n\n1.0.0 (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":"文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题， 让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。 触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人 Skill: Humanize Text Owner: li-jin-xuan Summary: 文案去AI味优化器。检测和修复AI生成文本中常见的机械感、模板化表达、过度礼貌等问题， 让文本更像人写的。适用于小红书文案、客服回复、产品介绍等场景。 触发词：去AI味、优化文案、自然一点、别像AI写的、口语化、更像人 Tags: ai-detection:1.0.0, copywriting:1.0.0, latest:1.0.0, text-optimization:1.0.0, writing:1.0.0 Version history: v1.0.0 | 2026-05-28T08:15:01.880Z | auto - **Initial release of “humanize-text” (文案去AI味优化器)** - Detects and fixes mechanical, templated, or overly","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":737,"uniquenessScore":60,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T16:44:59.340Z","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":"2026-10-11T16:44:59.340Z","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":"2026-10-11T20:59:40.630Z","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"}]}}}