[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AE57C5APRDF96NB3G0WQMW":3,"skill-same:01M7AE57C5APRDF96NB3G0WQMW":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AE57C5APRDF96NB3G0WQMW","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","hanchenhao\u002Fai-canvas","hanchenhao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F15713703?v=4","01M7ADWCF5AE30N3MG7MDF3RV2","01M7ADWCFVJS4V8VD9KWJG22WR",1,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tfjs\u002FSKILL.md",[],[],"2026-11-15 14:19:17",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`. Declare it in the node's `packages`\nproperty and 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`. Declare it in the node's `packages`\nproperty and 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","4ef72a828b24c99c49109033c7ec504c34f3bd17","packages\u002Fsandbox-packs\u002Fsandbox-tfjs",0,"https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas","https:\u002F\u002Fgithub.com\u002Fhanchenhao","2026-08-18 16:41:12",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add hanchenhao\u002Fai-canvas --skill sandbox-tfjs",{"tool":36,"command":37},"bunx","bunx skills add hanchenhao\u002Fai-canvas --skill sandbox-tfjs",{"tool":39,"command":40},"pnpm","pnpm dlx skills add hanchenhao\u002Fai-canvas --skill sandbox-tfjs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tfjs\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"package.json","REFERENCE","参考文档",949,"https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tfjs\u002Fpackage.json",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7AE5NP5AWGV47WS3F37VPZ1","sandbox-zip","Read and write zip archives in a Code node or CodeAct action, with fflate running on the host under a 50 MB inflation cap","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-zip\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7AE5JP0CG2S114Q246RC6MH","sandbox-yaml","Read and write YAML inside a Code node or CodeAct action, with js-yaml running in the guest","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-yaml\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7AE5GJ9AV36WM1DPW1878VM","sandbox-xml","Parse XML feeds and sitemaps in a Code node or CodeAct action, with fast-xml-parser running on the host","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-xml\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7AE5DMYDAGJW27G8KKTZ2BN","sandbox-xlsx","Read and write Excel workbooks in a Code node or CodeAct action, with exceljs running on the host","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-xlsx\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7AE5BARJSFCT296SEMYDSJQ","sandbox-twilio","Send SMS and WhatsApp messages and look up numbers from a Code node or CodeAct action, with NodeTool's Twilio request builder running on the host","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-twilio\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7AE559S35AWH50FJBZ7JNYR","sandbox-supabase","Read and write Supabase tables from a Code node or CodeAct action, with NodeTool's PostgREST request builder running on the host","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-supabase\u002FSKILL.md",[],[]]