[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79GVTKM2QWEG8R6VTKDSD0V":3,"skill-same:01M79GVTKM2QWEG8R6VTKDSD0V":71},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M79GVTKM2QWEG8R6VTKDSD0V","tweet-composer",null,"Score and optimize tweets based on X's real open-source ranking algorithm. Analyzes draft tweets against the actual ranking code — not generic tips. Use when: composing tweets, optimizing drafts for reach, planning threads, analyzing why a tweet performed well\u002Fpoorly, or asking for posting strategy advice.","gyc567\u002Fgreat-skill-center","gyc567","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F265098?v=4","01M79FNR01T00G18Z13PVXWWVK","eric","01M79FNR0PB4VEDVF0VK18FX9M",0,"MIT","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Ftweet-composer\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Ftweet-composer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tweet-composer\ndescription: >\n  Score and optimize tweets based on X's real open-source ranking algorithm.\n  Analyzes draft tweets against the actual ranking code — not generic tips.\n  Use when: composing tweets, optimizing drafts for reach, planning threads,\n  analyzing why a tweet performed well\u002Fpoorly, or asking for posting strategy advice.\nauthor: ERIC\nauthor_email: gyc567@gmail.com\nauthor_twitter: https:\u002F\u002Ftwitter.com\u002FEricBlock2100\nauthor_blog: https:\u002F\u002Ftopdigg.com\n\n---\n\n# Tweet Composer\n\nScore and optimize tweets using rules derived from X's open-source ranking algorithm.\n\n## How It Works\n\nX's \"For You\" feed is ranked by a Grok-based transformer (Phoenix) that predicts 19 engagement\nactions for every candidate tweet. The final score is a weighted sum of these predictions.\nThis skill encodes the structural rules from that pipeline into a scoring system.\n\nFor the full algorithm breakdown, read `references\u002Falgorithm-rules.md`.\n\n## Scoring a Draft Tweet\n\nWhen a user asks to score or optimize a tweet draft:\n\n1. Read `references\u002Falgorithm-rules.md` for the complete rules engine\n2. Analyze the draft against all rules\n3. Output the score card in this format:\n\n```\n🐦 Tweet Composer — Score: XX\u002F100\n\n[Category scores with ✅ ⚠️ ❌ indicators]\n\n📊 Predicted Action Boost:\n├─ P(reply): [assessment]\n├─ P(favorite): [assessment]  \n├─ P(share): [assessment]\n├─ P(dwell): [assessment]\n└─ P(not_interested): [assessment]\n\n💡 Suggestions:\n→ [actionable improvements]\n\n✏️ Optimized version:\n\"[rewritten tweet]\"\n```\n\n## Scoring Rubric (Quick Reference)\n\nScore 0-100 based on weighted categories:\n\n| Category | Weight | What to check |\n|----------|--------|---------------|\n| Reply potential | 25 | Questions, opinions, CTAs that drive replies |\n| Media | 20 | Native image\u002Fvideo attached (not link previews) |\n| Shareability | 15 | Would someone DM this or copy the link? |\n| Dwell time | 15 | Length that makes people stop scrolling |\n| Content quality | 10 | Clear, original, not generic |\n| Format | 10 | No links in body, no hashtags, good length |\n| Negative signals | 5 | Risk of not_interested\u002Fmute\u002Fblock |\n\n## Thread Optimization\n\nWhen composing threads:\n- First tweet = strongest hook (DedupConversationFilter keeps only the best per conversation)\n- 3-6 tweets max (short threads > mega-threads)\n- Each tweet self-contained (many see only the first)\n- Media on tweet 1 or 2 for photo_expand boost\n- CTA in last tweet\n\n## Quick Rules (No Reference File Needed)\n\n- **Links:** Always in reply, never in body (learned penalty from lower engagement)\n- **Hashtags:** Zero. The model learns they reduce engagement\n- **Length:** 100-200 chars sweet spot for single tweets\n- **Media:** Native image\u002Fvideo = separate P(photo_expand) and P(video_quality_view) predictions\n- **Video:** Must exceed minimum duration threshold for VQV weight to apply\n- **Timing:** Post when your audience is active — engagement velocity in first 30 min is critical\n- **Frequency:** AuthorDiversityScorer penalizes exponentially: 2nd post ~55% score, 3rd ~33%. Max 3-4 strong tweets\u002Fday\n- **Quote tweets:** P(quote) has dedicated weight — QTs with added value outperform plain retweets\n- **Engagement bait:** Questions\u002Fpolls drive P(reply). \"What would you add?\" > \"Like if you agree\"\n\n\u003C!-- ERIC-AUTHOR-INFO:START -->\n---\n\n## 📬 作者信息\n\n**ERIC** — AI技术专家，专注于人工智能和自动化工具的研究与应用\n\n| 渠道 | 链接 |\n|------|------|\n| 📧 邮箱 | gyc567@gmail.com |\n| 🐦 Twitter | [@EricBlock2100](https:\u002F\u002Ftwitter.com\u002FEricBlock2100) |\n| 💬 微信 | 360369487 |\n| ✈️ Telegram | [@fatoshi_block](https:\u002F\u002Ft.me\u002Ffatoshi_block) |\n| 📢 Telegram 频道 | [@cryptochanneleric](https:\u002F\u002Ft.me\u002Fcryptochanneleric) |\n| 🔐 加密情报 TG 群 | [@btcgogopen](https:\u002F\u002Ft.me\u002Fbtcgogopen) |\n| ▶️ YouTube | [@0XBitFinance](https:\u002F\u002Fwww.youtube.com\u002F@0XBitFinance) |\n| 🌐 个人技术博客 | [topdigg.com](https:\u002F\u002Ftopdigg.com) |\n\n> 本 Skill 由 ERIC 免费提供。想深入交流或获取更多同类 Skill，欢迎通过上表任一渠道联系。\n\n\u003C!-- ERIC-AUTHOR-INFO:END -->\n","# Tweet Composer\n\nScore and optimize tweets using rules derived from X's open-source ranking algorithm.\n\n## How It Works\n\nX's \"For You\" feed is ranked by a Grok-based transformer (Phoenix) that predicts 19 engagement\nactions for every candidate tweet. The final score is a weighted sum of these predictions.\nThis skill encodes the structural rules from that pipeline into a scoring system.\n\nFor the full algorithm breakdown, read `references\u002Falgorithm-rules.md`.\n\n## Scoring a Draft Tweet\n\nWhen a user asks to score or optimize a tweet draft:\n\n1. Read `references\u002Falgorithm-rules.md` for the complete rules engine\n2. Analyze the draft against all rules\n3. Output the score card in this format:\n\n```\n🐦 Tweet Composer — Score: XX\u002F100\n\n[Category scores with ✅ ⚠️ ❌ indicators]\n\n📊 Predicted Action Boost:\n├─ P(reply): [assessment]\n├─ P(favorite): [assessment]  \n├─ P(share): [assessment]\n├─ P(dwell): [assessment]\n└─ P(not_interested): [assessment]\n\n💡 Suggestions:\n→ [actionable improvements]\n\n✏️ Optimized version:\n\"[rewritten tweet]\"\n```\n\n## Scoring Rubric (Quick Reference)\n\nScore 0-100 based on weighted categories:\n\n| Category | Weight | What to check |\n|----------|--------|---------------|\n| Reply potential | 25 | Questions, opinions, CTAs that drive replies |\n| Media | 20 | Native image\u002Fvideo attached (not link previews) |\n| Shareability | 15 | Would someone DM this or copy the link? |\n| Dwell time | 15 | Length that makes people stop scrolling |\n| Content quality | 10 | Clear, original, not generic |\n| Format | 10 | No links in body, no hashtags, good length |\n| Negative signals | 5 | Risk of not_interested\u002Fmute\u002Fblock |\n\n## Thread Optimization\n\nWhen composing threads:\n- First tweet = strongest hook (DedupConversationFilter keeps only the best per conversation)\n- 3-6 tweets max (short threads > mega-threads)\n- Each tweet self-contained (many see only the first)\n- Media on tweet 1 or 2 for photo_expand boost\n- CTA in last tweet\n\n## Quick Rules (No Reference File Needed)\n\n- **Links:** Always in reply, never in body (learned penalty from lower engagement)\n- **Hashtags:** Zero. The model learns they reduce engagement\n- **Length:** 100-200 chars sweet spot for single tweets\n- **Media:** Native image\u002Fvideo = separate P(photo_expand) and P(video_quality_view) predictions\n- **Video:** Must exceed minimum duration threshold for VQV weight to apply\n- **Timing:** Post when your audience is active — engagement velocity in first 30 min is critical\n- **Frequency:** AuthorDiversityScorer penalizes exponentially: 2nd post ~55% score, 3rd ~33%. Max 3-4 strong tweets\u002Fday\n- **Quote tweets:** P(quote) has dedicated weight — QTs with added value outperform plain retweets\n- **Engagement bait:** Questions\u002Fpolls drive P(reply). \"What would you add?\" > \"Like if you agree\"\n\n\u003C!-- ERIC-AUTHOR-INFO:START -->\n---\n\n## 📬 作者信息\n\n**ERIC** — AI技术专家，专注于人工智能和自动化工具的研究与应用\n\n| 渠道 | 链接 |\n|------|------|\n| 📧 邮箱 | gyc567@gmail.com |\n| 🐦 Twitter | [@EricBlock2100](https:\u002F\u002Ftwitter.com\u002FEricBlock2100) |\n| 💬 微信 | 360369487 |\n| ✈️ Telegram | [@fatoshi_block](https:\u002F\u002Ft.me\u002Ffatoshi_block) |\n| 📢 Telegram 频道 | [@cryptochanneleric](https:\u002F\u002Ft.me\u002Fcryptochanneleric) |\n| 🔐 加密情报 TG 群 | [@btcgogopen](https:\u002F\u002Ft.me\u002Fbtcgogopen) |\n| ▶️ YouTube | [@0XBitFinance](https:\u002F\u002Fwww.youtube.com\u002F@0XBitFinance) |\n| 🌐 个人技术博客 | [topdigg.com](https:\u002F\u002Ftopdigg.com) |\n\n> 本 Skill 由 ERIC 免费提供。想深入交流或获取更多同类 Skill，欢迎通过上表任一渠道联系。\n\n\u003C!-- ERIC-AUTHOR-INFO:END -->\n",{"name":5,"author":25,"author_blog":26,"description":27,"author_email":28,"author_twitter":29},"ERIC","https:\u002F\u002Ftopdigg.com","Score and optimize tweets based on X's real open-source ranking algorithm. Analyzes draft tweets against the actual ranking code — not generic tips. Use when: composing tweets, optimizing drafts for reach, planning threads, analyzing why a tweet performed well\u002Fpoorly, or asking for posting strategy advice.\n","gyc567@gmail.com","https:\u002F\u002Ftwitter.com\u002FEricBlock2100","main","6612bed4902342e57e7f68416c67ee822f3816f3","skills\u002Ftweet-composer","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center","https:\u002F\u002Fgithub.com\u002Fgyc567","love hacking and hiking! \r\n技术博客：https:\u002F\u002Fwww.cnblogs.com\u002Fgyc567","2026-11-10 15:55:55",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add gyc567\u002Fgreat-skill-center --skill tweet-composer",{"tool":43,"command":44},"bunx","bunx skills add gyc567\u002Fgreat-skill-center --skill tweet-composer",{"tool":46,"command":47},"pnpm","pnpm dlx skills add gyc567\u002Fgreat-skill-center --skill tweet-composer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Ftweet-composer\u002FSKILL.md",true,[51,57,61,67],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"assets\u002Fbanner.svg","ASSET","资产文件",789,"https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Ftweet-composer\u002Fassets\u002Fbanner.svg",{"path":58,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":16},"LICENSE","许可证",1075,{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"README.md","REFERENCE","参考文档",6439,"https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Ftweet-composer\u002FREADME.md",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Falgorithm-rules.md",8511,"https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Ftweet-composer\u002Freferences\u002Falgorithm-rules.md",[72,80,88,96,104,111],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":20},"01M79GXESPRPQND3ZW1FKKWCF5","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\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-dna-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-dna-skill\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":20},"01M79GW2HHGV5RE1YWP7ANQ9JA","ub-quality-gates","Uncle Bob 编程纪律与确定性质量门工具链。写代码或改代码时使用：先让它能跑，再让它正确，最后守纪律。 当用户要求 \u002Fub-mode、需要代码质量门禁、CRAP 评分、重复代码检测、变异测试、 或抱怨代码难懂\u002F难测\u002F有重复时触发。覆盖 Clojure\u002FJava\u002FGo\u002FTypeScript\u002FRust\u002FPython。","0BSD","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fub-quality-gates\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":20},"01M79GR8RYEV0YXBS536MF99JN","short-video-scripter","Use when the user asks to \"script this short video\", \"write a TikTok \u002F Reels \u002F Shorts script\", \"给这条抖音或视频号视频写脚本\", or \"fix the hook — viewers drop off in the first seconds\"; produces timestamped beat-sheet scripts on the retention-gate model (0-2s hook \u002F 2-5s confirmation \u002F 5-15s payoff \u002F loop-or-CTA) with per-scene script lines, on-screen text for muted viewing, asset keywords, and 9:16 format-param rows per platform norm card for TikTok, Reels, Shorts, 抖音, and 视频号 — plus 2-3 hook options from named hook families and an AI-content disclosure line by default on realistic synthetic media. Spec-only: rendering, TTS, and publishing stay with the user's own tools — no pipelines, no upload automation. Not for creator video briefs — use brief-generator; long-form video SEO belongs to content-writer. 短视频脚本\u002F抖音分镜\u002F开头钩子\u002F竖屏9:16","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fshort-video-scripter\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":20},"01M79GQ5XG8TY96C8HMG5W9FA5","remotion-video-master","Remotion 视频编程大师 — 用 React 组件以编程方式创建 MP4 视频。支持动画、字幕、音乐可视化、 AI 配音（TTS）与场景自动配时。触发词：用代码做视频、编程视频、React 视频、Remotion、 \u002Fremotion-video。适用场景：程序化视频（批量生成、数据驱动如年度总结、音乐可视化、自动字幕）、 教程讲解视频（技术概念可视化如 CNN 与算法、分层递进讲解、AI 配音教程）、 3D 视频（产品展示与模型动画、卡通角色讲解、3D 数据可视化、Logo 动画）。","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fremotion-video-master\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fremotion-video-master\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":20},"01M79GP9M82V134E82MWFGVJ27","short-videos","Produce 90-second universal short-video scripts (HeyGen \u002F Instagram Reels \u002F LinkedIn Video \u002F YouTube Shorts) and standalone LinkedIn posts using native Hermes tools. No Claude Code dependency.","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity-pack\u002Fshort-videos\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":20},"01M79GP11FPAVGESW5VE3NGXR1","medium-story","Full Medium article pipeline using native Hermes tools. Research → write → 4 parallel output agents → HTML conversion → git commit\u002Fpush. Includes pre-flight infrastructure verification step, revisor-methodology fact-checking, and an anti-AI-slop writing pass (banned vocabulary, structural variety, accuracy rules).","https:\u002F\u002Fgithub.com\u002Fgyc567\u002Fgreat-skill-center\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity-pack\u002Fmedium-story\u002FSKILL.md",[],[]]