[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EW2SY9EYC9DHMNT2DZNMBB":3,"skill-same:01M7EW2SY9EYC9DHMNT2DZNMBB":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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EW2SY9EYC9DHMNT2DZNMBB","youtube-powers",null,"Route a YouTube channel task to the skill that owns it - cutting raw takes into videos, burning annotations, writing and checking descriptions, fixing end screens - and know which step cannot be done from here at all. Use at the start of any work on a channel, before reaching for a specific skill.","tdupu\u002Fagent-skills-public","tdupu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3440403?v=4","01M7EV32X9J0EFE5T4P8TKQTCQ","Taylor Dupuy","01M7EV32XZ1Z4MDBYAFRCJD3BP",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-powers\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: youtube-powers\ndescription: >-\n  Route a YouTube channel task to the skill that owns it - cutting raw takes\n  into videos, burning annotations, writing and checking descriptions, fixing\n  end screens - and know which step cannot be done from here at all. Use at the\n  start of any work on a channel, before reaching for a specific skill.\n---\n\n# YouTube powers\n\nA channel task is usually a chain: raw takes become a video, the video gets\nannotations, the annotations get a description, the description gets checked,\nand then somebody uploads. Each link has an owner. This routes to it.\n\n## One link is not yours\n\n**Uploading cannot be done from this machine**, and finding that out late has\ncost real time. Two independent blocks, neither of which is a policy you can\nask to have lifted:\n\n- **The Data API.** Google restricts `videos.insert` from unverified API\n  projects created after 28 July 2020 to *permanently private*. Not unlisted,\n  and not fixable by changing the setting afterwards - it needs a compliance\n  audit. Pushing a finished video through the API puts it in the one state\n  nobody can get it out of.\n- **Browser automation.** A file input cannot be clicked (the native picker is\n  invisible to the extension), and the upload tool takes at most 10 MB per\n  call from paths already shared with the session. Lecture renders run 100 MB\n  to 1 GB.\n\nLoad [[youtube-upload]] before doing anything about getting a video onto the\nchannel - including before reaching for `videos.insert` or opening Studio. The\nupload itself is the human's, every time. Say so early, stage the files and\nthe metadata so it is drag-and-drop, and do everything on both sides of it.\nThe durable fix is getting the API project verified; until then this does not\nchange.\n\nNothing else on a channel is blocked. Titles, descriptions, tags, visibility\nof existing videos, playlists and comments are all reachable through the API\nonce `bin\u002Fcredentials.py` has a token.\n\n## Where the work lives\n\n| Task | Skill |\n|---|---|\n| Raw takes to one video: choosing, ordering, trimming, joining | [[assemble-recording-series]] |\n| On-screen notes burned into the frame | [[youtube-color-commentary]] |\n| Writing a description: summary, chapters, references, provenance | [[correct-youtube-description]] |\n| Checking a description against the API's limits before it ships | [[check-youtube-description]] |\n| End screens and cards pointing at the right next video | [[correct-youtube-cards]] |\n| Getting a finished render onto the channel, and the handover it needs | [[youtube-upload]] |\n\nA series is assembled before it is annotated, and annotated before its\ndescriptions are written: dead-air trimming moves every timestamp, and a title\ncard prepended afterwards moves them again. Chapters generated before either\nare wrong.\n\n## What burns, and what does not\n\nAnything composited into the picture - annotations, title cards, corrections -\nis permanent once rendered. Re-rendering costs the encode and, if the video is\nalready up, a re-upload that loses its publish date, view count and comments.\nSo the order is: show the text to whoever is accountable, run an adversarial\nreview over it, *then* render. A panel asserting the speaker made a mistake is\nchecked against the recording and the source before it ships; a false\ncorrection burned into someone's lecture is the worst outcome available.\n\nDescriptions, titles, tags and playlists are not like this. They are editable\nforever, which is why detail that will not fit in a panel belongs in one.\n\n## Before any of it\n\nRead the channel's own operating notes if it has them - the constraints that\nbit somebody already are written down there, not here. Render to new paths;\nnever overwrite a source take, an assembly, or a previous render.\n","# YouTube powers\n\nA channel task is usually a chain: raw takes become a video, the video gets\nannotations, the annotations get a description, the description gets checked,\nand then somebody uploads. Each link has an owner. This routes to it.\n\n## One link is not yours\n\n**Uploading cannot be done from this machine**, and finding that out late has\ncost real time. Two independent blocks, neither of which is a policy you can\nask to have lifted:\n\n- **The Data API.** Google restricts `videos.insert` from unverified API\n  projects created after 28 July 2020 to *permanently private*. Not unlisted,\n  and not fixable by changing the setting afterwards - it needs a compliance\n  audit. Pushing a finished video through the API puts it in the one state\n  nobody can get it out of.\n- **Browser automation.** A file input cannot be clicked (the native picker is\n  invisible to the extension), and the upload tool takes at most 10 MB per\n  call from paths already shared with the session. Lecture renders run 100 MB\n  to 1 GB.\n\nLoad [[youtube-upload]] before doing anything about getting a video onto the\nchannel - including before reaching for `videos.insert` or opening Studio. The\nupload itself is the human's, every time. Say so early, stage the files and\nthe metadata so it is drag-and-drop, and do everything on both sides of it.\nThe durable fix is getting the API project verified; until then this does not\nchange.\n\nNothing else on a channel is blocked. Titles, descriptions, tags, visibility\nof existing videos, playlists and comments are all reachable through the API\nonce `bin\u002Fcredentials.py` has a token.\n\n## Where the work lives\n\n| Task | Skill |\n|---|---|\n| Raw takes to one video: choosing, ordering, trimming, joining | [[assemble-recording-series]] |\n| On-screen notes burned into the frame | [[youtube-color-commentary]] |\n| Writing a description: summary, chapters, references, provenance | [[correct-youtube-description]] |\n| Checking a description against the API's limits before it ships | [[check-youtube-description]] |\n| End screens and cards pointing at the right next video | [[correct-youtube-cards]] |\n| Getting a finished render onto the channel, and the handover it needs | [[youtube-upload]] |\n\nA series is assembled before it is annotated, and annotated before its\ndescriptions are written: dead-air trimming moves every timestamp, and a title\ncard prepended afterwards moves them again. Chapters generated before either\nare wrong.\n\n## What burns, and what does not\n\nAnything composited into the picture - annotations, title cards, corrections -\nis permanent once rendered. Re-rendering costs the encode and, if the video is\nalready up, a re-upload that loses its publish date, view count and comments.\nSo the order is: show the text to whoever is accountable, run an adversarial\nreview over it, *then* render. A panel asserting the speaker made a mistake is\nchecked against the recording and the source before it ships; a false\ncorrection burned into someone's lecture is the worst outcome available.\n\nDescriptions, titles, tags and playlists are not like this. They are editable\nforever, which is why detail that will not fit in a panel belongs in one.\n\n## Before any of it\n\nRead the channel's own operating notes if it has them - the constraints that\nbit somebody already are written down there, not here. Render to new paths;\nnever overwrite a source take, an assembly, or a previous render.\n",{"name":5,"description":7},"main","8d13efb5e66306aeae6e3b948bc463e7e2db1b65","skills\u002Fyoutube-powers","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public","https:\u002F\u002Fgithub.com\u002Ftdupu","https:\u002F\u002Ftdupu.github.io\u002Findex.html","Associate Professor, Department of Mathematics and Statistics, University of Vermont --- last updated Fall 2019","2026-11-13 09:07:19",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add tdupu\u002Fagent-skills-public --skill youtube-powers",{"tool":38,"command":39},"bunx","bunx skills add tdupu\u002Fagent-skills-public --skill youtube-powers",{"tool":41,"command":42},"pnpm","pnpm dlx skills add tdupu\u002Fagent-skills-public --skill youtube-powers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-powers\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"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},"01M7EW4PT586KKE7VRCAD80Z9K","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7EW4HV5V74AF3PTV8N4T0PS","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7EW4DNKGP5CR1RAJP2J9PHA","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7EW4BA2QP88VBFVXDVJM7XQ","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-superpowers\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EW47F2JG5FBESDJNP3PKMV","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EW44N8556Y556NX9HJT4KP","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]