[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-related-ru-liucongg-liucong-skills":3},{"items":4,"total":100,"page":101,"pageSize":102},[5,32,49,65,82],{"slug":6,"name":7,"title":7,"skillCategorySlug":8,"summary":9,"description":10,"skillCategoryName":11,"sourceUrl":12,"downloadUrl":13,"cliCommand":14,"authorName":-1,"version":-1,"license":-1,"stars":15,"trendScore":16,"qualityScore":16,"recommendedTools":17,"recommendedToolNames":17,"supportedClients":18,"clients":21,"tags":29,"installHint":14,"useCases":30,"updatedAt":31},"wechat-gggithub-chinese-ai-humanizer","wechat-gggithub\u002Fchinese-ai-humanizer","data-science-ml","用最少的提示词，识别并去除中文 AI 写作痕迹。","一份针对中文写作的极简规则清单。把它交给 Agent，让 Agent 在写作或润色时识别并删掉常见的 AI 腔。\n\n安装后，Codex 会根据 SKILL.md 中的 description 自动匹配。直接提出类似请求即可：\n\n如果安装后没有立即出现，重启 Codex。更多说明见 Codex Skill 官方文档。\n\n复制 SKILL.md 的正文内容（不含开头的 YAML frontmatter），放入对应的指令文件：\n\n- Codex：单个项目使用项目根目录下的 AGENTS.md，全局使用 ~\u002F.codex\u002FAGENTS.md。 - Claude Code：单个项目使用项目根目录下的 CLAUDE.md，全局使用 ~\u002F.claude\u002FCLAUDE.md。\n\n如果已有指令文件，追加内容即可，不要覆盖原有规则。具体加载方式可查看 Codex AGENTS.md 官方文档 和 Claude Code 官方文档。\n\n提示词也有成本。规则越短，占用的 token 越少，也越容易维护。这个项目只保留能稳定复现、能直接改写的特征，用尽可能少的文字改善中文表达。\n\n这些规则用于减少常见的中文 AI 腔。项目不提供 AI 检测功能，也不保证绕过检测工具。","Data science & ML","https:\u002F\u002Fgithub.com\u002Fwechat-gggithub\u002Fchinese-ai-humanizer","https:\u002F\u002Fgithub.com\u002Fwechat-gggithub\u002Fchinese-ai-humanizer\u002Farchive\u002FHEAD.zip","npx skillfish add wechat-gggithub\u002Fchinese-ai-humanizer",76,85,[],[19,20],"claude-desktop","cursor",[22,26],{"slug":19,"name":23,"summary":24,"count":25},"Claude Desktop","Десктопный клиент с поддержкой локальной конфигурации MCP.",0,{"slug":20,"name":27,"summary":28,"count":25},"Cursor","AI-редактор кода, часто используемый с developer MCP.",[8],[],"2026-09-14T05:06:06.50776",{"slug":33,"name":34,"title":34,"skillCategorySlug":8,"summary":35,"description":36,"skillCategoryName":11,"sourceUrl":37,"downloadUrl":38,"cliCommand":39,"authorName":-1,"version":-1,"license":-1,"stars":40,"trendScore":16,"qualityScore":16,"recommendedTools":41,"recommendedToolNames":41,"supportedClients":42,"clients":43,"tags":46,"installHint":39,"useCases":47,"updatedAt":48},"kimberlying-build-xhs-content-pack","kimberlying\u002Fbuild-xhs-content-pack","把 X 长文、书籍资料和笔记转换为小红书发布包、公众号文章与贴图的 Codex Skill","把 X 长文、文章、书籍资料和零散笔记，整理成一套可发布的小红书内容包，并同时生成公众号文章与贴图。\n\n我平时会把 X 长文、读书笔记和自己的判断丢给 Codex，让它完成选题 brief、小红书拆卡、知识卡出图、发布正文、公众号改写和发布前检查。把这套流程反复跑了几次以后，我把它封装成了 build-xhs-content-pack。\n\n当前状态：实验中。它可以稳定生成文字知识卡和公众号横版贴图，但资料、观点、风险提示和最终发布内容仍然需要人工确认。\n\n- 一篇 X 长文或网页 - 一本书或多本书的资料 - PDF、视频文字稿或本地文件 - 自己的零散笔记 - 只有一个选题和一些个人判断\n\n- 选题 brief - 资料和来源整理 - 8—12 张小红书图文卡 - 1080 × 1800 PNG 知识卡和总预览图 - 小红书标题、正文、标签和图片顺序 - 公众号长文 - 1200 × 675 公众号横版贴图 - 4 套同一视觉体系下的可切换 UI - 先看 4 个封面预览，再选择整套风格 - 发布前检查清单 - 发布后数据复盘模板\n\n这个 Skill 会先整理选题，再把内容拆成一条解释链，然后生成图片、发布材料和检查清单。\n\n- 教程型内容拆卡 - 第一次使用 Codex 的流程 - \u002Fside 和 \u002Ffork 对比卡 - AGENTS.md 写法 - 可复制 Prompt 卡 - 公众号横版流程图和对比图\n\n当前提供 4 套可切换的视觉系统。它们共用字体层级、信息结构、页码、留白逻辑和核心强调色，因此换风格后仍然像同一个账号：","https:\u002F\u002Fgithub.com\u002Fkimberlying\u002Fbuild-xhs-content-pack","https:\u002F\u002Fgithub.com\u002Fkimberlying\u002Fbuild-xhs-content-pack\u002Farchive\u002FHEAD.zip","npx skillfish add kimberlying\u002Fbuild-xhs-content-pack",63,[],[19,20],[44,45],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-09-19T08:43:35.650378",{"slug":50,"name":51,"title":51,"skillCategorySlug":8,"summary":52,"description":52,"skillCategoryName":11,"sourceUrl":53,"downloadUrl":54,"cliCommand":55,"authorName":-1,"version":-1,"license":-1,"stars":56,"trendScore":16,"qualityScore":16,"recommendedTools":57,"recommendedToolNames":57,"supportedClients":58,"clients":59,"tags":62,"installHint":55,"useCases":63,"updatedAt":64},"astroautomata-pysr","astroautomata\u002Fpysr","PySR searches for symbolic expressions which optimize a particular objective.","https:\u002F\u002Fgithub.com\u002Fastroautomata\u002Fpysr","https:\u002F\u002Fgithub.com\u002Fastroautomata\u002Fpysr\u002Farchive\u002FHEAD.zip","npx skillfish add astroautomata\u002Fpysr",3645,[],[19,20],[60,61],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-07-25T02:58:30.068082",{"slug":66,"name":67,"title":67,"skillCategorySlug":8,"summary":68,"description":69,"skillCategoryName":11,"sourceUrl":70,"downloadUrl":71,"cliCommand":72,"authorName":-1,"version":-1,"license":-1,"stars":73,"trendScore":16,"qualityScore":16,"recommendedTools":74,"recommendedToolNames":74,"supportedClients":75,"clients":76,"tags":79,"installHint":72,"useCases":80,"updatedAt":81},"zzzlc0405-photo-abstract-editorial","zzzlc0405\u002Fphoto-abstract-editorial","Commercial use is not allowed. If you build something with these Skills, attribution and are greatly appreciated.","Commercial use is not allowed. If you build something with these Skills, attribution and are greatly appreciated.\n\n在这里吐槽一下，真的很无语这几天，被人抄袭，甚至有人拿这个东西去卖，我真的无语！\n\n这是一个 ，它能将一张照片转化为「原始摄影区域 + 抽象记忆面板 + 诗意英文标题」的竖向编辑作品。\n\n- ✅ 保留照片的** - ✅ 仅从照片本身提炼** - ❌ 不是滤镜、照片重画或风格迁移\n\n📝 The skill includes the complete prompt in both and .\n\n1. 将整个 photo-abstract-editorial 文件夹复制到你的 Codex skills 目录，例如 ~\u002F.codex\u002Fskills\u002F 2. 开启新的 Codex 对话，上传一张希望处理的照片 3. 直接提出需求，例如：\n\n使用 photo-abstract-editorial 将这张照片制作成摄影与抽象面板组合的编辑作品。\n\n4. Skill 会将原图保留在成品的上方或主要区域，并在下方创建由原图关系推导出的极简抽象面板。成品中只保留一个原创英文标题（可选副标题）。","https:\u002F\u002Fgithub.com\u002Fzzzlc0405\u002Fphoto-abstract-editorial","https:\u002F\u002Fgithub.com\u002Fzzzlc0405\u002Fphoto-abstract-editorial\u002Farchive\u002FHEAD.zip","npx skillfish add zzzlc0405\u002Fphoto-abstract-editorial",5110,[],[19,20],[77,78],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-31T02:20:40.851168",{"slug":83,"name":84,"title":84,"skillCategorySlug":8,"summary":85,"description":86,"skillCategoryName":11,"sourceUrl":87,"downloadUrl":88,"cliCommand":89,"authorName":-1,"version":-1,"license":-1,"stars":90,"trendScore":91,"qualityScore":91,"recommendedTools":92,"recommendedToolNames":92,"supportedClients":93,"clients":94,"tags":97,"installHint":89,"useCases":98,"updatedAt":99},"thananon-9arm-skills","thananon\u002F9arm-skills","Skills live under skills\u002F, grouped into buckets:","Skills live under skills\u002F, grouped into buckets:\n\n- engineering\u002F — daily code work - productivity\u002F — daily non-code workflow tools - misc\u002F — kept around but rarely used - personal\u002F — tied to my own setup, not promoted - in-progress\u002F — drafts not yet ready to ship - deprecated\u002F — no longer used\n\nEach skill is its own directory containing a SKILL.md (with YAML frontmatter — name and description) and any bundled scripts or reference files.\n\nFor my own dev loop — symlink every shippable skill into ~\u002F.claude\u002Fskills\u002F:\n\n- — Four-mantra debugging discipline: reproduce → trace the fail path → falsify the hypothesis → cross-reference every breadcrumb. Recites verbatim at session start, then applies in order before any fix. - — Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, how it slipped through. Engineer-audience; refuses to draft without a reliable repro, known cause, and validated fix.","https:\u002F\u002Fgithub.com\u002Fthananon\u002F9arm-skills","https:\u002F\u002Fgithub.com\u002Fthananon\u002F9arm-skills\u002Farchive\u002FHEAD.zip","npx skillfish add thananon\u002F9arm-skills",2946,84,[],[19,20],[95,96],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:29:06.179008",111,1,5]