[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXWNMG9E72DG09338W15DS":3,"skill-same:01M6BXWNMG9E72DG09338W15DS":101},{"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":23,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":12,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6BXWNMG9E72DG09338W15DS","sandbox-tfjs",null,"Classify and embed images, detect objects, and answer from a passage in a Code node or CodeAct action, with TensorFlow.js running on the host","nodetool-ai\u002Fnodetool","nodetool-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F164873569?v=4","01M6BXPFDW36K9K1MR8ZH63HG2","nodetool.ai","01M6BXPFJ893XM219GQN60B0WK",635,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tfjs\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"sandbox","sandbox tfjs","tensorflow","code","js","node","images","objects","classify","host","detect","embed","with","answer","action","running","2026-11-10 10:12:30",false,"---\nname: sandbox-tfjs\ndescription: Classify and embed images, detect objects, and answer from a passage in a Code node or CodeAct action, with TensorFlow.js running on the host\n---\n\n# TensorFlow.js models in the sandbox\n\nSpecifier: `@nodetool-ai\u002Fsandbox-tfjs`. Import it at the top of the body.\n\nThe models are tens of megabytes of weights, fetched over the network and kept\nbetween calls. The guest has neither the heap for them nor a way to keep\nanything alive past a run, so this pack is a **host module**: the import\nresolves to a generated facade over NodeTool's own implementation, and each\nmodel loads once per process.\n\nThese models are small, local, and free — that is the whole reason to reach for\nthem. For anything a description or a caption would answer better, use a vision\nmodel through `nodetool.media` instead.\n\n## classify — ImageNet labels\n\n```js\nimport { classify } from \"@nodetool-ai\u002Fsandbox-tfjs\";\n\nconst labels = await classify(await workspace.readBytes(\"photo.jpg\"), { topK: 3 });\nreturn { best: labels[0].className, probability: labels[0].probability };\n```\n\nMobileNet v2 over the 1000 ImageNet classes, most likely first. `topK` defaults\nto 5.\n\n## embed — a feature vector for an image\n\n```js\nimport { embed } from \"@nodetool-ai\u002Fsandbox-tfjs\";\n\nconst vector = await embed(bytes);   \u002F\u002F 1280 numbers\n```\n\nThe MobileNet penultimate layer. Compare two vectors by cosine similarity for\nnear-duplicate detection or nearest-neighbour search.\n\n## detect — objects with boxes\n\n```js\nimport { detect } from \"@nodetool-ai\u002Fsandbox-tfjs\";\n\nconst objects = await detect(bytes, { maxBoxes: 10, minScore: 0.6 });\n\u002F\u002F [{ className: \"person\", score: 0.91, bbox: { x, y, width, height } }, …]\n```\n\nCOCO-SSD over the 80 COCO classes. The box is in image pixels. `maxBoxes`\ndefaults to 20 and `minScore` to 0.5.\n\n## answer — extractive question answering\n\n```js\nimport { answer } from \"@nodetool-ai\u002Fsandbox-tfjs\";\n\nconst spans = await answer(\"When was it founded?\", inputs.article);\nreturn { answer: spans[0]?.text ?? null };\n```\n\nBERT QnA quotes the passage — it never writes prose. Each span carries a\n`score` and its `startIndex`\u002F`endIndex` in the passage.\n\n## Gotchas\n\n- **Every export is async**, and the first call to each model waits for its\n  weights to download.\n- **Images go in as encoded bytes** (PNG\u002FJPEG\u002FWebP), decoded through the\n  sandbox's own `image` backend — so the same pixel caps `image.decode`\n  enforces apply, and 10 MB is the input limit.\n- **The models see pixels, nothing else.** `classify` on a screenshot of text\n  answers with an ImageNet class, not with the text; that is\n  `@nodetool-ai\u002Fsandbox-ocr`.\n","# TensorFlow.js models in the sandbox\n\nSpecifier: `@nodetool-ai\u002Fsandbox-tfjs`. Import it at the top of the body.\n\nThe models are tens of megabytes of weights, fetched over the network and kept\nbetween calls. The guest has neither the heap for them nor a way to keep\nanything alive past a run, so this pack is a **host module**: the import\nresolves to a generated facade over NodeTool's own implementation, and each\nmodel loads once per process.\n\nThese models are small, local, and free — that is the whole reason to reach for\nthem. For anything a description or a caption would answer better, use a vision\nmodel through `nodetool.media` instead.\n\n## classify — ImageNet labels\n\n```js\nimport { classify } from \"@nodetool-ai\u002Fsandbox-tfjs\";\n\nconst labels = await classify(await workspace.readBytes(\"photo.jpg\"), { topK: 3 });\nreturn { best: labels[0].className, probability: labels[0].probability };\n```\n\nMobileNet v2 over the 1000 ImageNet classes, most likely first. `topK` defaults\nto 5.\n\n## embed — a feature vector for an image\n\n```js\nimport { embed } from \"@nodetool-ai\u002Fsandbox-tfjs\";\n\nconst vector = await embed(bytes);   \u002F\u002F 1280 numbers\n```\n\nThe MobileNet penultimate layer. Compare two vectors by cosine similarity for\nnear-duplicate detection or nearest-neighbour search.\n\n## detect — objects with boxes\n\n```js\nimport { detect } from \"@nodetool-ai\u002Fsandbox-tfjs\";\n\nconst objects = await detect(bytes, { maxBoxes: 10, minScore: 0.6 });\n\u002F\u002F [{ className: \"person\", score: 0.91, bbox: { x, y, width, height } }, …]\n```\n\nCOCO-SSD over the 80 COCO classes. The box is in image pixels. `maxBoxes`\ndefaults to 20 and `minScore` to 0.5.\n\n## answer — extractive question answering\n\n```js\nimport { answer } from \"@nodetool-ai\u002Fsandbox-tfjs\";\n\nconst spans = await answer(\"When was it founded?\", inputs.article);\nreturn { answer: spans[0]?.text ?? null };\n```\n\nBERT QnA quotes the passage — it never writes prose. Each span carries a\n`score` and its `startIndex`\u002F`endIndex` in the passage.\n\n## Gotchas\n\n- **Every export is async**, and the first call to each model waits for its\n  weights to download.\n- **Images go in as encoded bytes** (PNG\u002FJPEG\u002FWebP), decoded through the\n  sandbox's own `image` backend — so the same pixel caps `image.decode`\n  enforces apply, and 10 MB is the input limit.\n- **The models see pixels, nothing else.** `classify` on a screenshot of text\n  answers with an ImageNet class, not with the text; that is\n  `@nodetool-ai\u002Fsandbox-ocr`.\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsandbox-packs\u002Fsandbox-tfjs",91,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool","https:\u002F\u002Fnodetool.ai\u002F","https:\u002F\u002Fgithub.com\u002Fnodetool-ai","No-code AI development","2026-11-15 03:27:49",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add nodetool-ai\u002Fnodetool --skill sandbox-tfjs",{"tool":60,"command":61},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill sandbox-tfjs",{"tool":63,"command":64},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill sandbox-tfjs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tfjs\u002FSKILL.md",true,[68,74,80,84,90,94,98],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"assets\u002FREADME.md","ASSET","资产文件",355,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdatabase\u002Fdatabase-schema-designer\u002Fskills\u002Fdesigning-database-schemas\u002Fassets\u002FREADME.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"package.json","REFERENCE","参考文档",943,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tfjs\u002Fpackage.json",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002FREADME.md",472,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdatabase\u002Fdatabase-schema-designer\u002Fskills\u002Fdesigning-database-schemas\u002Freferences\u002FREADME.md",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Ferd_generator.py","SCRIPT","脚本",2883,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdatabase\u002Fdatabase-schema-designer\u002Fskills\u002Fdesigning-database-schemas\u002Fscripts\u002Ferd_generator.py",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002FREADME.md",412,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdatabase\u002Fdatabase-schema-designer\u002Fskills\u002Fdesigning-database-schemas\u002Fscripts\u002FREADME.md",{"path":95,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fschema_validation.py",2909,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdatabase\u002Fdatabase-schema-designer\u002Fskills\u002Fdesigning-database-schemas\u002Fscripts\u002Fschema_validation.py",{"path":99,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":100},"scripts\u002Fsql_generator.py","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fdatabase\u002Fdatabase-schema-designer\u002Fskills\u002Fdesigning-database-schemas\u002Fscripts\u002Fsql_generator.py",[102,111,145,173,188,204],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":106,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":110},"01M742MX3Y2ZYK884ZXTRFKB9P","humanizer","Rewrite AI-sounding text so it reads like the writer without changing what it says.\nUse when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line\nclosers, staged openers, forced triads, dashes everywhere, inflated claims, sales\nlanguage, stock AI words, bold labels, or filler.","MIT","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhumanizer\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"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":125,"publishedAt":40},"01M6BY4D93R0Q9400ZHJ04DXP1","nodetool","Use the NodeTool MCP server to build, validate, run, and debug visual AI workflows, and to work with assets, collections, and jobs. Use when the user mentions NodeTool or asks for a workflow graph, a node, or a media generation run on their NodeTool server.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fplugins\u002Fchatgpt\u002Fnodetool\u002Fskills\u002Fnodetool\u002FSKILL.md",[117,120],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[113,126,127,128,129,130,131,36,132,133,134,135,29,136,137,138,139,140,141,142,143,144],"MCP","Media","workflows","when","generation","media generation","visual","use","collections","for","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":152,"publishedAt":40},"01M6BY4AEB05ZPBRVD078ATR2H","wan-2-6-prompting","Prompt Alibaba's Wan 2.6 video — text-to-video with a global style line plus timing-bracketed shots, and image-to-video that describes only what changes over time. Covers the shot-mode switch per provider, the prompt budget, negative prompts, motion intensity wording, audio input and prompt expansion. Use whenever the model id names a Wan 2.6 video route (alibaba\u002Fwan-2.6\u002Ftext-to-video, alibaba\u002Fwan-2.6\u002Fimage-to-video, wan-video\u002Fwan-2.6-t2v, wan-video\u002Fwan-2.6-i2v, wan-video\u002Fwan2.6-i2v-flash) on generate_video, animate_image or a TextToVideo node. Not for Wan 2.5 or 2.7, or the Wan 2.6 image routes.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fwan-2-6-prompting\u002FSKILL.md",[151],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[153,154,155,156,157,158,159,29,160,161,162,163,164,165,166,167,168,169,170,171,172],"prompting","wan 2 6 prompting","line","expansion","input","image-to-video","text-to-video","route","only","mode","time","flash","Budget","generate","text","image","animate","model","Audio","Video",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":181,"publishedAt":40},"01M6BY47T4748ZG5ZMTAR97ZWZ","video-workflow","Build a reusable NodeTool video workflow for batches or repeated inputs. For a single finished piece, use a storyboard skill.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-workflow\u002FSKILL.md",[179,180],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},[144,182,172,183,184,185,186,133,187,113,135],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":195,"publishedAt":40},"01M6BY4587N2SYN315SXGEMZC3","video-clone","Analyze a reference video and recreate its shot structure with a new product or cast in NodeTool.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-clone\u002FSKILL.md",[194],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[196,197,172,36,198,199,113,200,201,202,203],"clone","video clone","cast","new","analyze","product","structure","reference",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":211,"publishedAt":40},"01M6BY4257C2KQYYMD9EK6DK8E","video-audio-continuity","Keep sound continuous across a multi-scene piece cut from generated video — why one clip per scene hard-cuts the audio at every boundary, when to write all the scenes into a single generation instead, the sound-design vocabulary that survives a provider's copyright filter, and how to check the length, the aspect ratio and the mix of what came back. Use when a piece has more than one scene and the video model writes its own audio (Seedance 2, Veo 3, MiniMax H3, Kling 2.6 and later), or when a cut's sound drops out at the shot changes.","https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsystem-skills\u002Fvideo-audio-continuity\u002FSKILL.md",[210],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[212,172,171,213,214,215,216,217,218,219,220,221,222,129,223,224,170,225,226,227,228],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]