[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD55583WTM8RVRHZDGBFP7":3,"skill-same:01M7FD55583WTM8RVRHZDGBFP7":46},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7FD55583WTM8RVRHZDGBFP7","video-content",null,"Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a YouTube channel specifically — idea selection, retention teardowns, and channel-level strategy — use `youtube-producer`.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fvideo-content\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: video-content\ndescription: Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a YouTube channel specifically — idea selection, retention teardowns, and channel-level strategy — use `youtube-producer`.\n---\n\n# Video content\n\nThis covers video as a format across platforms — short-form, long-form, and the packaging that\ndecides whether either gets watched. `youtube-producer` covers one platform in depth: channel\nstrategy, idea selection against a channel's history, and retention teardowns against YouTube's\nown curves. When the question is about a channel rather than a video, it belongs there.\n\n## Packaging is most of the outcome\n\nA video nobody clicks has no retention curve. Title and thumbnail are not promotion of the video —\nthey are the promise the video must keep, and they should be designed before it is made. If you\ncannot package it compellingly, the idea is weak; find that out before filming.\n\n**Titles** — specific over clever. Curiosity that a real answer resolves, not a withheld one. Front-load\nthe distinguishing word, since titles truncate.\n\n**Thumbnails** — one subject, readable at thumbnail size on a phone. High contrast. Text under about\nfour words, or none. Thumbnail and title must not say the same thing; together they should say more\nthan either alone.\n\n## Openings\n\nThe first fifteen seconds decide the rest. Deliver the promise immediately — no channel intro, no\n\"before we get started,\" no restating the title.\n\nBest openings show the outcome, state the surprising conclusion, or drop the viewer mid-action. Then\nsay what the video will cover, briefly, so they know the shape of the commitment.\n\n## Structure by length\n\n**Short-form** — one idea, opening frame that reads as motion, and a payoff before attention decays.\nNo setup. The loop matters: end where the beginning makes sense again.\n\n**Long-form** — chapters that each work standalone, with an explicit reason to continue at every\nseam. Retention is lost at transitions, not in the middle of sections. Vary pace deliberately; a\nuniformly intense video is as tiring as a flat one.\n\n## Diagnosing underperformance\n\n- **Low click-through** — packaging problem. Title and thumbnail, not content.\n- **High click-through, early drop** — the opening did not pay the promise. Or the promise was\n  unpayable.\n- **Steady mid-video decline** — normal. Look at the slope against your own baseline, not absolutes.\n- **Sharp mid-video cliff** — find the timestamp and watch it. It is almost always a transition, a\n  tangent, or a sponsor read placed badly.\n\n## Repurposing\n\nPlan derivatives before filming, not after. Segments intended to stand alone get shot to stand\nalone. Extracting short-form from a video not built for it produces clips that need context they do\nnot have.\n\n## Tooling\n\nEditing: DaVinci Resolve, Adobe Premiere Pro, Final Cut Pro, CapCut, and similar; Descript for\ntranscript-driven editing, which is faster for talking-head and interview formats than a timeline.\n\nRecording remote: Riverside, Zoom, StreamYard, and similar — record local tracks per participant\nwhere the tool supports it, because the connection quality on the day decides the ceiling otherwise.\n\nRepurposing and captions: Opus Clip, Submagic, and similar. Burned-in captions are not optional;\nmost viewing is silent, and the caption is the packaging on every platform that autoplays.\n\n## Never\n\n- Produce before the title and thumbnail exist. Packaging decides whether anything you shot gets seen.\n- Open with a preamble. The first seconds are where an audience is lost, not where it is warmed up.\n- Diagnose a video on view count alone. Impressions, click-through, and retention fail differently and need different fixes.\n","# Video content\n\nThis covers video as a format across platforms — short-form, long-form, and the packaging that\ndecides whether either gets watched. `youtube-producer` covers one platform in depth: channel\nstrategy, idea selection against a channel's history, and retention teardowns against YouTube's\nown curves. When the question is about a channel rather than a video, it belongs there.\n\n## Packaging is most of the outcome\n\nA video nobody clicks has no retention curve. Title and thumbnail are not promotion of the video —\nthey are the promise the video must keep, and they should be designed before it is made. If you\ncannot package it compellingly, the idea is weak; find that out before filming.\n\n**Titles** — specific over clever. Curiosity that a real answer resolves, not a withheld one. Front-load\nthe distinguishing word, since titles truncate.\n\n**Thumbnails** — one subject, readable at thumbnail size on a phone. High contrast. Text under about\nfour words, or none. Thumbnail and title must not say the same thing; together they should say more\nthan either alone.\n\n## Openings\n\nThe first fifteen seconds decide the rest. Deliver the promise immediately — no channel intro, no\n\"before we get started,\" no restating the title.\n\nBest openings show the outcome, state the surprising conclusion, or drop the viewer mid-action. Then\nsay what the video will cover, briefly, so they know the shape of the commitment.\n\n## Structure by length\n\n**Short-form** — one idea, opening frame that reads as motion, and a payoff before attention decays.\nNo setup. The loop matters: end where the beginning makes sense again.\n\n**Long-form** — chapters that each work standalone, with an explicit reason to continue at every\nseam. Retention is lost at transitions, not in the middle of sections. Vary pace deliberately; a\nuniformly intense video is as tiring as a flat one.\n\n## Diagnosing underperformance\n\n- **Low click-through** — packaging problem. Title and thumbnail, not content.\n- **High click-through, early drop** — the opening did not pay the promise. Or the promise was\n  unpayable.\n- **Steady mid-video decline** — normal. Look at the slope against your own baseline, not absolutes.\n- **Sharp mid-video cliff** — find the timestamp and watch it. It is almost always a transition, a\n  tangent, or a sponsor read placed badly.\n\n## Repurposing\n\nPlan derivatives before filming, not after. Segments intended to stand alone get shot to stand\nalone. Extracting short-form from a video not built for it produces clips that need context they do\nnot have.\n\n## Tooling\n\nEditing: DaVinci Resolve, Adobe Premiere Pro, Final Cut Pro, CapCut, and similar; Descript for\ntranscript-driven editing, which is faster for talking-head and interview formats than a timeline.\n\nRecording remote: Riverside, Zoom, StreamYard, and similar — record local tracks per participant\nwhere the tool supports it, because the connection quality on the day decides the ceiling otherwise.\n\nRepurposing and captions: Opus Clip, Submagic, and similar. Burned-in captions are not optional;\nmost viewing is silent, and the caption is the packaging on every platform that autoplays.\n\n## Never\n\n- Produce before the title and thumbnail exist. Packaging decides whether anything you shot gets seen.\n- Open with a preamble. The first seconds are where an audience is lost, not where it is warmed up.\n- Diagnose a video on view count alone. Impressions, click-through, and retention fail differently and need different fixes.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fvideo-content",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill video-content",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill video-content",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill video-content","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fvideo-content\u002FSKILL.md",true,[],[47,54,59,66,73,80],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":55,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\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":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]