[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DCWZD3CXZ8JHM2KZKRC0AZ":3,"skill-same:01M6DCWZD3CXZ8JHM2KZKRC0AZ":43},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M6DCWZD3CXZ8JHM2KZKRC0AZ","reframe",null,"Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Freframe\u002FSKILL.md",[],[5],"2026-11-10 10:12:30",false,"---\nname: reframe\ndescription: Reframe horizontal 16:9 video into vertical 9:16 (1080x1920) with automatic subject tracking — for Shorts, Reels, and TikTok. Use when the user wants to convert, reframe, or crop a landscape video to vertical, follow a moving subject in a vertical crop, or turn long horizontal footage into a portrait clip. GPU-accelerated via WSL2.\nlicense: MIT (skill). Engines: verthor + claude-shorts are MIT (vendored under D:\\tools\\reframe).\n---\n\n# reframe — horizontal to vertical 9:16\n\nTurns 16:9 footage into subject-tracked 1080x1920 vertical video. Runs in WSL2 Ubuntu (GPU: RTX 4050).\n\n## Engine 2 — verthor (primary, verified)\n\nScene-aware reframe: PySceneDetect → YOLOv11-seg + ByteTrack → MediaPipe face\u002Fpose + saliency →\nsmoothed virtual-camera pan\u002Fzoom → ffmpeg encode. Emits 1080x1920 H.264 with audio intact.\n\n**Run (from a FILE — never pipe the script in):**\n```\nwsl -- bash \u002Fmnt\u002Fc\u002FUsers\u002Fagentuser\u002Fsource\u002Fagent-skills-toolchain\u002Fskills\u002Freframe\u002Fscripts\u002Freframe.sh IN.mp4 OUT.mp4 preset\n```\n- Run the script from a file, NOT `... | bash`: verthor\u002Fmediapipe read stdin, so a piped script gets\n  consumed and corrupts after the verthor line. If you see a `\\r` parse error, normalize once:\n  `wsl -- bash -lc \"sed -i 's\u002F\\r\u002F\u002Fg' \u003Cscript>\"`.\n- Paths are WSL paths: Windows `D:\\x.mp4` → `\u002Fmnt\u002Fd\u002Fx.mp4`.\n- `\u003Cpreset>`: `talking_head` (default) | `sports` | `pets` | `cars`.\n- Or invoke verthor directly:\n  `wsl -- bash -lc \"source ~\u002F.local\u002Fshare\u002Freframe\u002Fverthor\u002Fbin\u002Factivate && cd \u002Fmnt\u002Fd\u002Ftools\u002Freframe\u002Fverthor && python -m verthor \u003CIN> \u003COUT> --preset talking_head --saliency-model handcrafted --video-encoder libx264\"`\n\n**Safety \u002F pinned choices (do not change):**\n- `--saliency-model handcrafted` ALWAYS. NEVER `deepgazemr` (loads remote model via torch.hub = RCE risk).\n- `--video-encoder libx264` (deterministic; NVENC auto-degrades on stock ffmpeg).\n- verthor pinned `33ac38d`; venv at `~\u002F.local\u002Fshare\u002Freframe\u002Fverthor` (WSL).\n\n## Engine 1 — claude-shorts (comparison, see references\u002Fengines.md)\n\n### Acceptance\n### Setup (one-time, already done on this machine)\n","# reframe — horizontal to vertical 9:16\n\nTurns 16:9 footage into subject-tracked 1080x1920 vertical video. Runs in WSL2 Ubuntu (GPU: RTX 4050).\n\n## Engine 2 — verthor (primary, verified)\n\nScene-aware reframe: PySceneDetect → YOLOv11-seg + ByteTrack → MediaPipe face\u002Fpose + saliency →\nsmoothed virtual-camera pan\u002Fzoom → ffmpeg encode. Emits 1080x1920 H.264 with audio intact.\n\n**Run (from a FILE — never pipe the script in):**\n```\nwsl -- bash \u002Fmnt\u002Fc\u002FUsers\u002Fagentuser\u002Fsource\u002Fagent-skills-toolchain\u002Fskills\u002Freframe\u002Fscripts\u002Freframe.sh IN.mp4 OUT.mp4 preset\n```\n- Run the script from a file, NOT `... | bash`: verthor\u002Fmediapipe read stdin, so a piped script gets\n  consumed and corrupts after the verthor line. If you see a `\\r` parse error, normalize once:\n  `wsl -- bash -lc \"sed -i 's\u002F\\r\u002F\u002Fg' \u003Cscript>\"`.\n- Paths are WSL paths: Windows `D:\\x.mp4` → `\u002Fmnt\u002Fd\u002Fx.mp4`.\n- `\u003Cpreset>`: `talking_head` (default) | `sports` | `pets` | `cars`.\n- Or invoke verthor directly:\n  `wsl -- bash -lc \"source ~\u002F.local\u002Fshare\u002Freframe\u002Fverthor\u002Fbin\u002Factivate && cd \u002Fmnt\u002Fd\u002Ftools\u002Freframe\u002Fverthor && python -m verthor \u003CIN> \u003COUT> --preset talking_head --saliency-model handcrafted --video-encoder libx264\"`\n\n**Safety \u002F pinned choices (do not change):**\n- `--saliency-model handcrafted` ALWAYS. NEVER `deepgazemr` (loads remote model via torch.hub = RCE risk).\n- `--video-encoder libx264` (deterministic; NVENC auto-degrades on stock ffmpeg).\n- verthor pinned `33ac38d`; venv at `~\u002F.local\u002Fshare\u002Freframe\u002Fverthor` (WSL).\n\n## Engine 1 — claude-shorts (comparison, see references\u002Fengines.md)\n\n### Acceptance\n### Setup (one-time, already done on this machine)\n",{},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","platform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Freframe","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":7,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill reframe",{"tool":35,"command":36},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill reframe",{"tool":38,"command":39},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill reframe","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Freframe\u002FSKILL.md",true,[],[44,66,97,124,138,154],{"skillNo":45,"name":46,"nameZh":6,"description":47,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":48,"categories":49,"keywords":50,"publishedAt":18},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[51,52,53,54,55,56,57,58,59,60,61,62,63,64,65],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":77,"publishedAt":18},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[72],{"categoryNo":73,"categoryName":74,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[78,79,80,81,82,83,84,85,86,87,88,89,90,91,60,92,93,94,95,96],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":109,"publishedAt":18},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[103,106],{"categoryNo":104,"categoryName":105,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":107,"categoryName":108,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000008","测试与质量",[110,111,112,113,114,115,116,117,118,119,79,120,121,122,123],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":18},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[126,131,132,133,134,135,136,137],"setup","report","project","installation","project setup","issues","state",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":145,"publishedAt":18},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[144],{"categoryNo":73,"categoryName":74,"taxonomyType":75,"taxonomyTypeDesc":76},[140,146,56,147,148,149,60,150,151,152,153],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":155,"name":131,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":18},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[131,133,94,160,135,161],"files","interactive"]