[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXWW25ZP05PBWK5MZ8MSQ0":3,"skill-same:01M6BXWW25ZP05PBWK5MZ8MSQ0":66},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":42,"ownerHtmlUrl":43,"ownerBlogUrl":12,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M6BXWW25ZP05PBWK5MZ8MSQ0","sandbox-tokens",null,"Count, encode, and decode LLM tokens in a Code node or CodeAct action, with js-tiktoken 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-tokens\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"sandbox","sandbox tokens","tokens","code","js","node","host","with","action","tiktoken","count","decode","running","2026-11-10 10:12:30",false,"---\nname: sandbox-tokens\ndescription: Count, encode, and decode LLM tokens in a Code node or CodeAct action, with js-tiktoken running on the host\n---\n\n# Token counting in the sandbox\n\nSpecifier: `@nodetool-ai\u002Fsandbox-tokens`. Import it at the top of the body.\n\nOne encoding's BPE ranks are several megabytes, well past the 1 MB cap on a\ncompiled guest module, so this pack is a **host module**: the import resolves to\na generated facade over NodeTool's own implementation. The ranks load once per\nprocess per encoding.\n\nThis is what the removed `nodetool.text.CountTokens` node did.\n\n## count — how many tokens a text costs\n\n```js\nimport { count } from \"@nodetool-ai\u002Fsandbox-tokens\";\n\nconst tokens = await count(inputs.text, \"cl100k_base\");\nreturn { tokens, fitsContext: tokens \u003C 8000 };\n```\n\nEncodings: `cl100k_base` (default — GPT-4, GPT-3.5), `o200k_base` (GPT-4o),\n`p50k_base`, `r50k_base`. Empty text is 0 without loading anything.\n\n## encode \u002F decode — the token ids themselves\n\n```js\nimport { encode, decode } from \"@nodetool-ai\u002Fsandbox-tokens\";\n\nconst ids = await encode(inputs.text);\n\u002F\u002F Truncate on a token boundary rather than a character one.\nreturn { head: await decode(ids.slice(0, 500)) };\n```\n\n## Gotchas\n\n- **All three are async.**\n- **5 MB per call**, the shared host-module text cap.\n- **tiktoken is OpenAI's tokenizer.** Anthropic, Gemini, and local models count\n  differently — treat the number as an estimate for anything else.\n- **Round-tripping is not free.** `decode(encode(t))` allocates the ranks and\n  two passes; use `count` when you only need the number.\n","# Token counting in the sandbox\n\nSpecifier: `@nodetool-ai\u002Fsandbox-tokens`. Import it at the top of the body.\n\nOne encoding's BPE ranks are several megabytes, well past the 1 MB cap on a\ncompiled guest module, so this pack is a **host module**: the import resolves to\na generated facade over NodeTool's own implementation. The ranks load once per\nprocess per encoding.\n\nThis is what the removed `nodetool.text.CountTokens` node did.\n\n## count — how many tokens a text costs\n\n```js\nimport { count } from \"@nodetool-ai\u002Fsandbox-tokens\";\n\nconst tokens = await count(inputs.text, \"cl100k_base\");\nreturn { tokens, fitsContext: tokens \u003C 8000 };\n```\n\nEncodings: `cl100k_base` (default — GPT-4, GPT-3.5), `o200k_base` (GPT-4o),\n`p50k_base`, `r50k_base`. Empty text is 0 without loading anything.\n\n## encode \u002F decode — the token ids themselves\n\n```js\nimport { encode, decode } from \"@nodetool-ai\u002Fsandbox-tokens\";\n\nconst ids = await encode(inputs.text);\n\u002F\u002F Truncate on a token boundary rather than a character one.\nreturn { head: await decode(ids.slice(0, 500)) };\n```\n\n## Gotchas\n\n- **All three are async.**\n- **5 MB per call**, the shared host-module text cap.\n- **tiktoken is OpenAI's tokenizer.** Anthropic, Gemini, and local models count\n  differently — treat the number as an estimate for anything else.\n- **Round-tripping is not free.** `decode(encode(t))` allocates the ranks and\n  two passes; use `count` when you only need the number.\n",{"name":5,"description":7},"main","c7226baa82daca42a19a5855c116544f97aa8bac","packages\u002Fsandbox-packs\u002Fsandbox-tokens",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":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add nodetool-ai\u002Fnodetool --skill sandbox-tokens",{"tool":52,"command":53},"bunx","bunx skills add nodetool-ai\u002Fnodetool --skill sandbox-tokens",{"tool":55,"command":56},"pnpm","pnpm dlx skills add nodetool-ai\u002Fnodetool --skill sandbox-tokens","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tokens\u002FSKILL.md",true,[60],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"package.json","REFERENCE","参考文档",850,"https:\u002F\u002Fgithub.com\u002Fnodetool-ai\u002Fnodetool\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tokens\u002Fpackage.json",[67,76,112,142,157,173],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":75},"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":92,"publishedAt":32},"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",[82,87],{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[78,93,94,95,96,97,98,26,99,100,101,102,24,103,104,105,106,107,108,109,110,111],"MCP","Media","workflows","when","generation","media generation","visual","use","collections","for","work","debug","graph","validate","assets","run","server","mcp server","workflow",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":121,"publishedAt":32},"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",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000016","图像与多媒体",[122,123,124,125,126,127,128,24,129,130,131,132,133,134,135,136,137,138,139,140,141],"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":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":150,"publishedAt":32},"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",[148,149],{"categoryNo":119,"categoryName":120,"taxonomyType":85,"taxonomyTypeDesc":86},{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},[111,151,141,152,153,154,155,100,156,78,102],"video workflow","reusable","storyboard","build","batches","single",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":32},"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",[163],{"categoryNo":119,"categoryName":120,"taxonomyType":85,"taxonomyTypeDesc":86},[165,166,141,26,167,168,78,169,170,171,172],"clone","video clone","cast","new","analyze","product","structure","reference",{"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":180,"publishedAt":32},"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",[179],{"categoryNo":119,"categoryName":120,"taxonomyType":85,"taxonomyTypeDesc":86},[181,141,140,182,183,184,185,186,187,188,189,190,191,96,192,193,139,194,195,196,197],"video audio continuity","continuity","write","why","back","veo 3","at","cut","later","across","filter","generated","how to","mix","design","boundary","how"]