[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CTFWSZMWYYD7XW3AD3RRT9":3,"skill-same:01M6CTFWSZMWYYD7XW3AD3RRT9":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6CTFWSZMWYYD7XW3AD3RRT9","humanize-chinese",null,"Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.","Sam-06060\u002Fjarvis-assistant","Sam-06060","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F208600848?v=4","01M6CRKT7C7FXD21V6HXF293S0","Samson Frank Ganta","01M6CRKTBEKYFD8YX5Z1GT99EE",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fhumanize-chinese\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"humanize chinese","humanize","chinese","conversion","style-transfer","aigc","Academic","scoring","practical","community","writing","use","user","editing","text","transfer","content","workflow","safe","2026-11-10 10:12:30",false,"---\nname: humanize-chinese\ndescription: Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when the user asks to 去AI味, 降AIGC, 去除AI痕迹, 论文降重, 知网检测, 维普检测, humanize chinese, detect AI text, or make Chinese text sound more natural.\ncategory: content\nrisk: safe\nsource: community\ntags:\n  - chinese\n  - writing\n  - editing\n  - aigc\n  - academic\n  - style-transfer\ndate_added: \"2026-04-03\"\n---\n\n# Humanize Chinese\n\nUse this skill when you need to detect AI-like Chinese writing, rewrite it to feel less synthetic, reduce AIGC signals in academic prose, or convert the text into a more specific Chinese writing style.\n\n## When to Use\n\n- Use when the user says `去AI味`, `降AIGC`, `去除AI痕迹`, `让文字更自然`, `改成人话`, or `降低AI率`\n- Use when the user wants a Chinese text checked for AI-writing patterns or suspicious phrasing\n- Use when the user wants academic-paper-specific AIGC reduction for CNKI, VIP, or Wanfang-style checks\n- Use when the user wants Chinese text rewritten into a different style such as `zhihu`, `xiaohongshu`, `wechat`, `weibo`, `literary`, or `academic`\n\n## Core Workflow\n\n### 1. Detect Before Rewriting\n\nStart by identifying the most obvious AI markers instead of rewriting blindly:\n\n- rigid `first\u002Fsecond\u002Ffinally` structures\n- mechanical connectors such as `综上所述`, `值得注意的是`, `由此可见`\n- abstract grandiose wording with low information density\n- repeated sentence rhythm and paragraph length\n- academic prose that sounds too complete, too certain, or too template-driven\n\nIf the user provides a short sample, call out the suspicious phrases directly before rewriting.\n\n### 2. Rewrite in the Smallest Useful Pass\n\nPrefer targeted rewrites over total regeneration:\n\n- remove formulaic connectors rather than paraphrasing every sentence\n- vary sentence length and paragraph rhythm\n- replace repeated verbs and noun phrases\n- swap abstract summaries for concrete observations where possible\n- keep the original claims, facts, citations, and terminology intact\n\n### 3. Validate the Result\n\nAfter rewriting, verify that the text:\n\n- still says the same thing\n- sounds less templated\n- uses more natural rhythm\n- does not introduce factual drift\n- stays in the correct register for the target audience\n\nFor academic text, preserve a scholarly tone. Do not over-casualize.\n\n## Optional CLI Flow\n\nIf the user has a local clone of the source toolkit, these examples are useful:\n\n```bash\npython3 scripts\u002Fdetect_cn.py text.txt -v\npython3 scripts\u002Fcompare_cn.py text.txt -a -o clean.txt\npython3 scripts\u002Facademic_cn.py paper.txt -o clean.txt --compare\npython3 scripts\u002Fstyle_cn.py text.txt --style xiaohongshu -o out.txt\n```\n\nUse this CLI sequence when available:\n\n1. detect and inspect suspicious sentences\n2. rewrite or compare\n3. rerun detection on the cleaned file\n4. optionally convert into a target style\n\n## Manual Rewrite Playbook\n\nIf the scripts are unavailable, use this manual process.\n\n### Common AI Markers\n\n- numbered or mirrored structures that feel too symmetrical\n- filler transitions that add no meaning\n- repeated stock phrases\n- overly even sentence length\n- conclusions that sound final, polished, and risk-free\n\n### Rewrite Moves\n\n- delete weak transitions first\n- collapse repetitive phrases into one stronger sentence\n- split sentences at natural turns instead of forcing long balanced structures\n- merge choppy sentences when they feel robotic\n- replace generic abstractions with concrete wording\n- introduce light variation in cadence so the prose does not march at a constant tempo\n\n## Academic AIGC Reduction\n\nFor papers, reports, or theses:\n\n- keep discipline-specific terminology unchanged\n- replace AI-academic stock phrases with more grounded scholarly phrasing\n- reduce absolute certainty with measured hedging where appropriate\n- vary paragraph structure so each section does not read like the same template\n- add limitations or uncertainty if the conclusion feels unnaturally complete\n\nExamples of safer direction changes:\n\n- `本文旨在` -> `本文尝试` or `本研究关注`\n- `具有重要意义` -> `值得关注` or `有一定参考价值`\n- `研究表明` -> `前人研究发现` or `已有文献显示`\n\nDo not invent citations, evidence, or data.\n\n## Style Conversion\n\nUse style conversion only after the base text is readable and natural.\n\nSupported style directions from the source workflow:\n\n- `casual`\n- `zhihu`\n- `xiaohongshu`\n- `wechat`\n- `academic`\n- `literary`\n- `weibo`\n\nWhen switching style, keep the user's meaning stable and change only tone, structure, and surface wording.\n\n## Output Rules\n\n- Show the main AI-like patterns you found\n- Explain the rewrite strategy in 1-3 short bullets\n- Return the rewritten Chinese text\n- If helpful, include a short note on remaining weak spots\n\n## Source\n\nAdapted from the `voidborne-d\u002Fhumanize-chinese` project and its CLI\u002Fscript workflow for Chinese AI-text detection and rewriting.\n","# Humanize Chinese\n\nUse this skill when you need to detect AI-like Chinese writing, rewrite it to feel less synthetic, reduce AIGC signals in academic prose, or convert the text into a more specific Chinese writing style.\n\n## When to Use\n\n- Use when the user says `去AI味`, `降AIGC`, `去除AI痕迹`, `让文字更自然`, `改成人话`, or `降低AI率`\n- Use when the user wants a Chinese text checked for AI-writing patterns or suspicious phrasing\n- Use when the user wants academic-paper-specific AIGC reduction for CNKI, VIP, or Wanfang-style checks\n- Use when the user wants Chinese text rewritten into a different style such as `zhihu`, `xiaohongshu`, `wechat`, `weibo`, `literary`, or `academic`\n\n## Core Workflow\n\n### 1. Detect Before Rewriting\n\nStart by identifying the most obvious AI markers instead of rewriting blindly:\n\n- rigid `first\u002Fsecond\u002Ffinally` structures\n- mechanical connectors such as `综上所述`, `值得注意的是`, `由此可见`\n- abstract grandiose wording with low information density\n- repeated sentence rhythm and paragraph length\n- academic prose that sounds too complete, too certain, or too template-driven\n\nIf the user provides a short sample, call out the suspicious phrases directly before rewriting.\n\n### 2. Rewrite in the Smallest Useful Pass\n\nPrefer targeted rewrites over total regeneration:\n\n- remove formulaic connectors rather than paraphrasing every sentence\n- vary sentence length and paragraph rhythm\n- replace repeated verbs and noun phrases\n- swap abstract summaries for concrete observations where possible\n- keep the original claims, facts, citations, and terminology intact\n\n### 3. Validate the Result\n\nAfter rewriting, verify that the text:\n\n- still says the same thing\n- sounds less templated\n- uses more natural rhythm\n- does not introduce factual drift\n- stays in the correct register for the target audience\n\nFor academic text, preserve a scholarly tone. Do not over-casualize.\n\n## Optional CLI Flow\n\nIf the user has a local clone of the source toolkit, these examples are useful:\n\n```bash\npython3 scripts\u002Fdetect_cn.py text.txt -v\npython3 scripts\u002Fcompare_cn.py text.txt -a -o clean.txt\npython3 scripts\u002Facademic_cn.py paper.txt -o clean.txt --compare\npython3 scripts\u002Fstyle_cn.py text.txt --style xiaohongshu -o out.txt\n```\n\nUse this CLI sequence when available:\n\n1. detect and inspect suspicious sentences\n2. rewrite or compare\n3. rerun detection on the cleaned file\n4. optionally convert into a target style\n\n## Manual Rewrite Playbook\n\nIf the scripts are unavailable, use this manual process.\n\n### Common AI Markers\n\n- numbered or mirrored structures that feel too symmetrical\n- filler transitions that add no meaning\n- repeated stock phrases\n- overly even sentence length\n- conclusions that sound final, polished, and risk-free\n\n### Rewrite Moves\n\n- delete weak transitions first\n- collapse repetitive phrases into one stronger sentence\n- split sentences at natural turns instead of forcing long balanced structures\n- merge choppy sentences when they feel robotic\n- replace generic abstractions with concrete wording\n- introduce light variation in cadence so the prose does not march at a constant tempo\n\n## Academic AIGC Reduction\n\nFor papers, reports, or theses:\n\n- keep discipline-specific terminology unchanged\n- replace AI-academic stock phrases with more grounded scholarly phrasing\n- reduce absolute certainty with measured hedging where appropriate\n- vary paragraph structure so each section does not read like the same template\n- add limitations or uncertainty if the conclusion feels unnaturally complete\n\nExamples of safer direction changes:\n\n- `本文旨在` -> `本文尝试` or `本研究关注`\n- `具有重要意义` -> `值得关注` or `有一定参考价值`\n- `研究表明` -> `前人研究发现` or `已有文献显示`\n\nDo not invent citations, evidence, or data.\n\n## Style Conversion\n\nUse style conversion only after the base text is readable and natural.\n\nSupported style directions from the source workflow:\n\n- `casual`\n- `zhihu`\n- `xiaohongshu`\n- `wechat`\n- `academic`\n- `literary`\n- `weibo`\n\nWhen switching style, keep the user's meaning stable and change only tone, structure, and surface wording.\n\n## Output Rules\n\n- Show the main AI-like patterns you found\n- Explain the rewrite strategy in 1-3 short bullets\n- Return the rewritten Chinese text\n- If helpful, include a short note on remaining weak spots\n\n## Source\n\nAdapted from the `voidborne-d\u002Fhumanize-chinese` project and its CLI\u002Fscript workflow for Chinese AI-text detection and rewriting.\n",{"name":5,"risk":42,"tags":48,"source":33,"category":40,"date_added":50,"description":7},[26,34,37,29,49,28],"academic","2026-04-03","main","a50a3aa6b39fb0e1b7db88bef1bfc9c93606e126","modules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fhumanize-chinese",0,"https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant","https:\u002F\u002Fgithub.com\u002FSam-06060","Mobile Application Developer | Kotlin | Flutter, KMP, Swfit, Android,Swift UI | Building at Saar It Resources | Creator of Jarvis (AI Assistant)","2026-06-23 05:13:38",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add Sam-06060\u002Fjarvis-assistant --skill humanize-chinese",{"tool":65,"command":66},"bunx","bunx skills add Sam-06060\u002Fjarvis-assistant --skill humanize-chinese",{"tool":68,"command":69},"pnpm","pnpm dlx skills add Sam-06060\u002Fjarvis-assistant --skill humanize-chinese","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fhumanize-chinese\u002FSKILL.md",true,[73,79],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"metadata.json","REFERENCE","参考文档",632,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcopilot\u002Fangular-ui-patterns\u002Fmetadata.json",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"README.md",1666,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcopilot\u002Fangular-ui-patterns\u002FREADME.md",[84,97,113,140,159,185],{"skillNo":85,"name":86,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":94,"publishedAt":43},"01M6GDRVS6FXX3ESH0C9DW01C0","test_skill","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fscratch\u002Ftest_skill\u002FSKILL.md",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[95,96],"Test Skill","test",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":43},"01M6GDRQ40HX22MA6XWC31RHHK","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzustand-store-ts\u002FSKILL.md",[],[104,105,106,107,108,109,110,33,111,112],"zustand store ts","zustand","store","with","types","middleware","patterns","create","typescript",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":122,"publishedAt":43},"01M6GDRKEA0WE670SPFWX5GKCN","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzoom-automation\u002FSKILL.md",[119],{"categoryNo":120,"categoryName":121,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000023","Skill与智能体开发",[123,124,125,126,127,128,129,130,131,132,133,134,135,136,33,137,138,139],"automation","zoom automation","zoom","first","Tools","search","MCP","via","meeting","automate","critical","creation","webinars","composio","recordings","management","tracking",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":147,"publishedAt":43},"01M6GDRFS1452PC71JQ38S24HR","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzoho-crm-automation\u002FSKILL.md",[146],{"categoryNo":120,"categoryName":121,"taxonomyType":92,"taxonomyTypeDesc":93},[148,123,149,150,151,152,153,33,128,154,136,155,133,132,127,156,111,157,129,158],"crm automation","zoho crm","crm","zoho crm automation","zoho","leads","contacts","records","update","tasks","manage",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":168,"publishedAt":43},"01M6GDRCKQBAVTGHX5XBH26KPZ","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzod-validation-expert\u002FSKILL.md",[165],{"categoryNo":166,"categoryName":167,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000009","前端开发",[169,170,171,172,173,112,42,174,175,176,177,178,107,179,180,181,182,33,183,184],"expert","zod","zod validation expert","validation","react","parsing","errors","schema validation","react hook form","hook","trpc","form","type","next","schema","Next.js",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":43},"01M6GDR658B08K4MY0RWD4A6EH","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzeroize-audit\u002FSKILL.md",[191],{"categoryNo":120,"categoryName":121,"taxonomyType":92,"taxonomyTypeDesc":93},[193,194,195,196,197,198,199,200,33,201,202,203,204,205,206,207,208,209,210,129],"zeroize audit","audit","write","passwords","get","project","c++","activate","assembly","read","Bash","secrets","analysis","data","flow","verification","code","rust"]