[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6M41QDJTHQTHPCR2YPE8WBG":3,"skill-same:01M6M41QDJTHQTHPCR2YPE8WBG":125},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":13,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M6M41QDJTHQTHPCR2YPE8WBG","sepia",null,"Make AI-generated writing read as human-written, in fiction and in professional prose. Repairs the narrative architecture of fiction and stories (based on StoryScope, arXiv:2604.03136); routes professional text through domain rules for release notes, announcements, PR and issue replies, code-review comments, incident postmortems, tickets, work orders, technical articles, and blog posts. Four operations - write, review (diagnose AI tells without editing), refactor (minimal in-place edits), recreate (full rewrite). Use when asked to humanize, de-AI, unslop, or strip AI flavor from any text; when writing or revising any of these document types; or whenever output must not read as machine-written.","endman100\u002Fskill-router-nexus","endman100","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F31997019?v=4","01M6KPDX17BYDWW4RRB0TNGGMX","01M6KPDX64Y2QBEWVFG5W5PWPF",0,"MIT","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[5,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"generated","when","posts","types","narrative","professional","de","human","incident","humanize","writing","work","text","unslop","code-review","code","release notes","notes","architecture","review","2026-11-10 10:12:30",false,"---\nname: sepia\ndescription: Make AI-generated writing read as human-written, in fiction and in professional prose. Repairs the narrative architecture of fiction and stories (based on StoryScope, arXiv:2604.03136); routes professional text through domain rules for release notes, announcements, PR and issue replies, code-review comments, incident postmortems, tickets, work orders, technical articles, and blog posts. Four operations - write, review (diagnose AI tells without editing), refactor (minimal in-place edits), recreate (full rewrite). Use when asked to humanize, de-AI, unslop, or strip AI flavor from any text; when writing or revising any of these document types; or whenever output must not read as machine-written.\nlicense: MIT\nmetadata:\n  version: \"0.2.0\"\n---\n\n# Sepia — de-AI writing\n\nEvery rule here is backed by a measured human-vs-AI gap. The load-bearing facts: in fiction, a classifier using only **narrative-structure features** detects AI at 93.2% macro-F1 and style editing barely moves it — so structure is fixed before style, always. In professional prose, the measured tells are different — filler density, missing stance, chatbot residue, register mismatch, format uniformity — and the fix is domain-specific. Route first, then operate.\n\n## Routing\n\n| Text type | Load, in order |\n|---|---|\n| Fiction \u002F stories \u002F narrative essays | `references\u002Fnarrative-pass.md` → `references\u002Fdiscourse-pass.md` → `references\u002Fstyle-pass.md`; diagnose with `references\u002Frubric.md` |\n| Release notes, changelogs, announcements | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Frelease-notes.md` |\n| PR replies, issue replies, review comments | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Fdev-replies.md` |\n| Incident postmortems \u002F RCA | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Fpostmortems.md` |\n| Tickets, work orders, bug reports | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Ftickets.md` |\n| Technical articles, blog posts, tutorials | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Ftech-articles.md` + `references\u002Fdiscourse-pass.md` §1–3 |\n| Any other prose | `references\u002Fprofessional-pass.md` + `references\u002Fstyle-pass.md` |\n\nEvery non-fiction route ends with the vocabulary\u002Fsyntax scan in `references\u002Fstyle-pass.md` §2–3, and long professional pieces take the whole style pass — in both cases skipping its fiction-slop table. If the text was produced by a known model, add `references\u002Fmodel-fingerprints.md` (fiction-centric; use as priors).\n\n## Operations\n\nAny request maps to one of four operations:\n\n| Operation | Contract |\n|---|---|\n| **write** | New content. Read the domain file *before* drafting — architecture and register decisions come first, they cannot be retrofitted cheaply. For fiction, follow Workflow A below. |\n| **review** | Diagnose only — no edits. Produce the defect list (fiction: rubric report; professional: checklist findings with quoted evidence) and stop. Report findings; apply nothing until asked. |\n| **refactor** | Minimal in-place revision preserving structure, voice, and intent. Two-stage: full defect list first, then fix item by item, deepest layer first. Skew replace\u002Fdelete over insert (measured editor ratio 74\u002F18\u002F8). |\n| **recreate** | Full rewrite. Extract the facts, claims, and intent from the original into a bare list; verify nothing invented; write fresh under the domain rules. Use when defects are structural and the text is short enough that surgery costs more than rebuilding. |\n\nThe two-stage protocol is not optional for refactor\u002Frecreate: paraphrasing without a defect list makes AI fingerprints *more* visible, not less (measured on expert detectors).\n\n## Fiction workflows\n\n**A — writing new fiction:** (1) premise, genre, length — genre sets calibration targets; (2) fill the architecture sheet in `references\u002Fnarrative-pass.md`; (3) select 3–5 human-leaning moves + one rarity move; (4) outline, run the outline\u002FQUD checks in `references\u002Fdiscourse-pass.md` and the echo test in `references\u002Fnarrative-pass.md` §2; (5) draft; (6) self-diagnose with `references\u002Frubric.md`, one group at a time; (7) style pass last.\n\n**B — revising existing fiction:** (1) diagnose completely first (rubric → discourse → style), no edits; (2) triage — architecture defects need scene-level surgery, tell the user how deep before cutting; (3) fix deepest first; (4) verify: re-run changed rubric groups, read key passages aloud, echo-test any added twist.\n\n## Calibration — the rule that governs all rules\n\n| Principle | Meaning |\n|---|---|\n| Aim at the band, not the opposite pole | Human values are moderate (chronological discontinuity 2.4\u002F5, not 5). Inverting every AI tell creates a new fingerprint. In professional prose the equivalent: match the venue's register, don't overshoot into forced casualness — informality alone fools no trained reader. |\n| Select, don't accumulate | Human writing is diverse. Fiction: 3–5 moves per story, chosen for the premise, varied across works. Professional: fix what the checklist actually flags, nothing more. |\n| Leave slack | Ordinary sentences, an underdeveloped thought, a plain paragraph. Do not sand every surface. |\n\n## Hard guardrails\n\n- **Never invent specifics.** Fiction: intertextual references, brands, places must be real and correct. Professional: versions, numbers, timestamps, benchmarks, quotes come from the actual change\u002Fincident\u002Fdata — missing info means ask the user or leave an explicit TODO, never fill. Confident wrong facts are themselves a top-tier tell.\n- **Deletion beats addition** (74% replace \u002F 18% delete \u002F 8% insert). The only additive fix is real specificity.\n- **Respect the author's voice and the venue's corpus.** Extract habits from the user's samples or the venue's recent artifacts before editing; edit toward *that* profile. Do not remove a mannerism they actually use.\n- **Dialogue quotes and quoted material are load-bearing** — do not regularize them.\n- **Check the whitelists** (`references\u002Fstyle-pass.md` §7, `references\u002Fprofessional-pass.md` last section) before flagging: clean grammar, formal tone in formal venues, and conventional templates are not evidence of AI.\n","# Sepia — de-AI writing\n\nEvery rule here is backed by a measured human-vs-AI gap. The load-bearing facts: in fiction, a classifier using only **narrative-structure features** detects AI at 93.2% macro-F1 and style editing barely moves it — so structure is fixed before style, always. In professional prose, the measured tells are different — filler density, missing stance, chatbot residue, register mismatch, format uniformity — and the fix is domain-specific. Route first, then operate.\n\n## Routing\n\n| Text type | Load, in order |\n|---|---|\n| Fiction \u002F stories \u002F narrative essays | `references\u002Fnarrative-pass.md` → `references\u002Fdiscourse-pass.md` → `references\u002Fstyle-pass.md`; diagnose with `references\u002Frubric.md` |\n| Release notes, changelogs, announcements | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Frelease-notes.md` |\n| PR replies, issue replies, review comments | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Fdev-replies.md` |\n| Incident postmortems \u002F RCA | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Fpostmortems.md` |\n| Tickets, work orders, bug reports | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Ftickets.md` |\n| Technical articles, blog posts, tutorials | `references\u002Fprofessional-pass.md` + `references\u002Fdomains\u002Ftech-articles.md` + `references\u002Fdiscourse-pass.md` §1–3 |\n| Any other prose | `references\u002Fprofessional-pass.md` + `references\u002Fstyle-pass.md` |\n\nEvery non-fiction route ends with the vocabulary\u002Fsyntax scan in `references\u002Fstyle-pass.md` §2–3, and long professional pieces take the whole style pass — in both cases skipping its fiction-slop table. If the text was produced by a known model, add `references\u002Fmodel-fingerprints.md` (fiction-centric; use as priors).\n\n## Operations\n\nAny request maps to one of four operations:\n\n| Operation | Contract |\n|---|---|\n| **write** | New content. Read the domain file *before* drafting — architecture and register decisions come first, they cannot be retrofitted cheaply. For fiction, follow Workflow A below. |\n| **review** | Diagnose only — no edits. Produce the defect list (fiction: rubric report; professional: checklist findings with quoted evidence) and stop. Report findings; apply nothing until asked. |\n| **refactor** | Minimal in-place revision preserving structure, voice, and intent. Two-stage: full defect list first, then fix item by item, deepest layer first. Skew replace\u002Fdelete over insert (measured editor ratio 74\u002F18\u002F8). |\n| **recreate** | Full rewrite. Extract the facts, claims, and intent from the original into a bare list; verify nothing invented; write fresh under the domain rules. Use when defects are structural and the text is short enough that surgery costs more than rebuilding. |\n\nThe two-stage protocol is not optional for refactor\u002Frecreate: paraphrasing without a defect list makes AI fingerprints *more* visible, not less (measured on expert detectors).\n\n## Fiction workflows\n\n**A — writing new fiction:** (1) premise, genre, length — genre sets calibration targets; (2) fill the architecture sheet in `references\u002Fnarrative-pass.md`; (3) select 3–5 human-leaning moves + one rarity move; (4) outline, run the outline\u002FQUD checks in `references\u002Fdiscourse-pass.md` and the echo test in `references\u002Fnarrative-pass.md` §2; (5) draft; (6) self-diagnose with `references\u002Frubric.md`, one group at a time; (7) style pass last.\n\n**B — revising existing fiction:** (1) diagnose completely first (rubric → discourse → style), no edits; (2) triage — architecture defects need scene-level surgery, tell the user how deep before cutting; (3) fix deepest first; (4) verify: re-run changed rubric groups, read key passages aloud, echo-test any added twist.\n\n## Calibration — the rule that governs all rules\n\n| Principle | Meaning |\n|---|---|\n| Aim at the band, not the opposite pole | Human values are moderate (chronological discontinuity 2.4\u002F5, not 5). Inverting every AI tell creates a new fingerprint. In professional prose the equivalent: match the venue's register, don't overshoot into forced casualness — informality alone fools no trained reader. |\n| Select, don't accumulate | Human writing is diverse. Fiction: 3–5 moves per story, chosen for the premise, varied across works. Professional: fix what the checklist actually flags, nothing more. |\n| Leave slack | Ordinary sentences, an underdeveloped thought, a plain paragraph. Do not sand every surface. |\n\n## Hard guardrails\n\n- **Never invent specifics.** Fiction: intertextual references, brands, places must be real and correct. Professional: versions, numbers, timestamps, benchmarks, quotes come from the actual change\u002Fincident\u002Fdata — missing info means ask the user or leave an explicit TODO, never fill. Confident wrong facts are themselves a top-tier tell.\n- **Deletion beats addition** (74% replace \u002F 18% delete \u002F 8% insert). The only additive fix is real specificity.\n- **Respect the author's voice and the venue's corpus.** Extract habits from the user's samples or the venue's recent artifacts before editing; edit toward *that* profile. Do not remove a mannerism they actually use.\n- **Dialogue quotes and quoted material are load-bearing** — do not regularize them.\n- **Check the whitelists** (`references\u002Fstyle-pass.md` §7, `references\u002Fprofessional-pass.md` last section) before flagging: clean grammar, formal tone in formal venues, and conventional templates are not evidence of AI.\n",{"name":5,"license":14,"metadata":53,"description":7},{"version":54},"0.2.0","main","f19b254e8975d0bfddb394686706106930d7964d","Writing-and-Content\u002Fsepia","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus","https:\u002F\u002Fgithub.com\u002Fendman100","2026-11-12 18:13:37",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add endman100\u002Fskill-router-nexus --skill sepia",{"tool":67,"command":68},"bunx","bunx skills add endman100\u002Fskill-router-nexus --skill sepia",{"tool":70,"command":71},"pnpm","pnpm dlx skills add endman100\u002Fskill-router-nexus --skill sepia","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002FSKILL.md",true,[75,81,85,89,93,97,101,105,109,113,117,121],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"agents\u002Fopenai.yaml","REFERENCE","参考文档",191,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Fagents\u002Fopenai.yaml",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fdiscourse-pass.md",4786,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fdiscourse-pass.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fdomains\u002Fdev-replies.md",2537,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fdomains\u002Fdev-replies.md",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fdomains\u002Fpostmortems.md",2564,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fdomains\u002Fpostmortems.md",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fdomains\u002Frelease-notes.md",2005,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fdomains\u002Frelease-notes.md",{"path":98,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fdomains\u002Ftech-articles.md",2987,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fdomains\u002Ftech-articles.md",{"path":102,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fdomains\u002Ftickets.md",1725,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fdomains\u002Ftickets.md",{"path":106,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fmodel-fingerprints.md",4192,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fmodel-fingerprints.md",{"path":110,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fnarrative-pass.md",11382,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fnarrative-pass.md",{"path":114,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Fprofessional-pass.md",5476,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fprofessional-pass.md",{"path":118,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Frubric.md",7889,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Frubric.md",{"path":122,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":123,"sourceHtmlUrl":124},"references\u002Fstyle-pass.md",6910,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fsepia\u002Freferences\u002Fstyle-pass.md",[126,148,179,200,209,233],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":130,"sourceHtmlUrl":131,"categories":132,"keywords":136,"publishedAt":48},"01M6MPCT5BXVER8HQZTW3QE9AS","create-master","基于佛教经典文献，生成特定高僧大德的 AI 教学角色","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FMetaphysics-and-Spirituality\u002FMaster-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FMetaphysics-and-Spirituality\u002FMaster-skill\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000039","教师与教育",[137,138,139,140,141,142,143,144,145,146,147],"create master","master","create","生成","true","webfetch","edit","write","read","grep","Bash",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":152,"sourceHtmlUrl":153,"categories":154,"keywords":160,"publishedAt":48},"01M6M43AKE95Y64E1JRXEF5QQ3","writing-dna-skill","从至少 20 篇完整文章中蒸馏可复用的写作 DNA，分析语言、文章结构、选题逻辑、素材策略、认知框架和视觉风格，并生成 Writing-DNA.md；按该 DNA 写作时会读取全部蒸馏产物和 5 篇相关原文。用于中英文作者、账号、品牌或出版物的风格分析与一致性写作。 Distill reusable Writing DNA from at least 20 complete articles for Chinese or English authors, publications, brands, and accounts; use for language, structure, topic logic, source strategy, cognitive-frame, and visual-style analysis.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fwriting-dna-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fwriting-dna-skill\u002FSKILL.md",[155,156,159],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":157,"categoryName":158,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},[161,162,38,163,164,165,166,167,168,169,170,171,172,140,173,174,175,176,177,178],"writing dna skill","DNA","strategy","english","logic","visual","structure","chinese","reusable","use","style","distill","analysis","frame","source","for","at","complete",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":183,"sourceHtmlUrl":184,"categories":185,"keywords":188,"publishedAt":48},"01M6M428TTCGQ4ME3KY99VN037","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fstop-slop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fstop-slop\u002FSKILL.md",[186,187],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},[189,190,191,192,29,193,194,195,196,170,197,198,40,176,199,38],"slop","stop slop","stop","drafting","drafts","https","patterns","prose","remove","editing","content",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":204,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":48},"01M6M41X0B7EBX42TK435DMGGR","shuorenhua","检查和清理中英文文本里的 AI 套路，适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求；按场景控制力度，同时保留事实、术语、语域和责任主体。","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fshuorenhua\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fshuorenhua\u002FSKILL.md",[],[202,208],"文本",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":213,"sourceHtmlUrl":214,"categories":215,"keywords":216,"publishedAt":48},"01M6M3ZD12WBEW5KXKDM4N6DFG","naming","Name products, SaaS, brands, open source projects, bots, and apps. Use when the user needs to name something, find a brand name, or pick a product name. Metaphor-driven process that produces memorable, meaningful names and avoids AI slop.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fnaming-main\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fnaming-main\u002FSKILL.md",[],[211,217,218,219,220,221,170,222,145,175,223,224,225,226,147,227,228,229,230,29,231,232,189],"repo","websearch","product name","apps","bots","view","brand","pick","gh","projects","open","saas","open source","product","describe","ai slop",{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":237,"sourceHtmlUrl":238,"categories":239,"keywords":241,"publishedAt":48},"01M6M3YVXAFAAWJ7F6JMPFREYE","humanizer-zh","去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。\n基于维基百科的\"AI 写作特征\"综合指南。检测并修复以下模式：夸大的象征意义、\n宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、\nAI 词汇、否定式排比、过多的连接性短语。","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fhumanizer-zh\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fhumanizer-zh\u002FSKILL.md",[240],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[242,243,244,145,144,143,38,140,208,245,189,191],"humanizer","zh","humanizer zh","翻译"]