[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AE4QSBFF92S5ABQ0AHZ2WV":3,"skill-same:01M7AE4QSBFF92S5ABQ0AHZ2WV":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},"01M7AE4QSBFF92S5ABQ0AHZ2WV","sandbox-markdown",null,"Parse markdown into a token stream inside a Code node or CodeAct action, with marked's lexer running in the guest","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-markdown\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sandbox-markdown\ndescription: Parse markdown into a token stream inside a Code node or CodeAct action, with marked's lexer running in the guest\n---\n\n# Markdown in the sandbox\n\nSpecifier: `@nodetool-ai\u002Fsandbox-markdown`. One module, the `marked` root\nexport. Declare it in the node's `packages` property and import it at the top\nof the body.\n\n`marked` is pure JavaScript — no Node builtins, no DOM — so it compiles\nstraight into the QuickJS guest. There is no pre-built \"extract headers\"\nhelper; `marked.lexer` gives you the token stream and you read what you need\nout of it.\n\n## lexer — markdown text to tokens\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst tokens = marked.lexer(inputs.markdown);\nreturn { tokenCount: tokens.length };\n```\n\nEach token carries a `type` (`heading`, `paragraph`, `list`, `code`, `table`,\n`link` tokens nested inside `paragraph`\u002F`text` tokens, etc.) and the fields\nthat type needs.\n\n## Headers → a document outline\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst headers = marked.lexer(inputs.markdown)\n  .filter((t) => t.type === \"heading\")\n  .map((t) => ({ level: t.depth, text: t.text }));\nreturn { headers };\n```\n\n## Links → a flat list\n\n`marked` nests inline tokens (links, emphasis) inside block tokens. Walk\n`tokens.links` for a document's reference-style link definitions, or walk each\nblock's `.tokens` for inline links:\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nfunction collectLinks(tokens, out = []) {\n  for (const t of tokens) {\n    if (t.type === \"link\") out.push({ href: t.href, text: t.text });\n    if (t.tokens) collectLinks(t.tokens, out);\n    if (t.items) collectLinks(t.items, out);\n  }\n  return out;\n}\n\nconst links = collectLinks(marked.lexer(inputs.markdown));\nreturn { links };\n```\n\n## Lists → nested items\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst lists = marked.lexer(inputs.markdown)\n  .filter((t) => t.type === \"list\")\n  .map((t) => ({\n    ordered: t.ordered,\n    items: t.items.map((item) => item.text)\n  }));\nreturn { lists };\n```\n\n## Code blocks → language + source\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst codeBlocks = marked.lexer(inputs.markdown)\n  .filter((t) => t.type === \"code\")\n  .map((t) => ({ language: t.lang || \"text\", code: t.text }));\nreturn { codeBlocks };\n```\n\n## Tables → rows of records\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst tables = marked.lexer(inputs.markdown)\n  .filter((t) => t.type === \"table\")\n  .map((t) => {\n    const headers = t.header.map((cell) => cell.text);\n    return t.rows.map((row) =>\n      Object.fromEntries(row.map((cell, i) => [headers[i], cell.text]))\n    );\n  });\nreturn { tables };\n```\n\n## Markdown → HTML\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst html = marked.parse(inputs.markdown);\nreturn { html };\n```\n\n## Gotchas\n\n- **Everything runs in the guest.** The 64 MB guest heap holds your input text,\n  the token tree, and the returned value at once.\n- **`marked.lexer` is synchronous**, unlike `marked.parse` (which can be async\n  when you register an async extension — the default configuration is not).\n- **Token shapes differ by type.** A `list` token's items are themselves\n  tokens with their own `.tokens`; a `table` token has `header`\u002F`rows`, not a\n  flat `cells` array. Log a sample token when a shape is unclear.\n- **This pack is the only route to markdown parsing.** There is no\n  `data.parseMarkdown` global; every library the sandbox offers is an\n  importable module, and this is the one for markdown.\n","# Markdown in the sandbox\n\nSpecifier: `@nodetool-ai\u002Fsandbox-markdown`. One module, the `marked` root\nexport. Declare it in the node's `packages` property and import it at the top\nof the body.\n\n`marked` is pure JavaScript — no Node builtins, no DOM — so it compiles\nstraight into the QuickJS guest. There is no pre-built \"extract headers\"\nhelper; `marked.lexer` gives you the token stream and you read what you need\nout of it.\n\n## lexer — markdown text to tokens\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst tokens = marked.lexer(inputs.markdown);\nreturn { tokenCount: tokens.length };\n```\n\nEach token carries a `type` (`heading`, `paragraph`, `list`, `code`, `table`,\n`link` tokens nested inside `paragraph`\u002F`text` tokens, etc.) and the fields\nthat type needs.\n\n## Headers → a document outline\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst headers = marked.lexer(inputs.markdown)\n  .filter((t) => t.type === \"heading\")\n  .map((t) => ({ level: t.depth, text: t.text }));\nreturn { headers };\n```\n\n## Links → a flat list\n\n`marked` nests inline tokens (links, emphasis) inside block tokens. Walk\n`tokens.links` for a document's reference-style link definitions, or walk each\nblock's `.tokens` for inline links:\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nfunction collectLinks(tokens, out = []) {\n  for (const t of tokens) {\n    if (t.type === \"link\") out.push({ href: t.href, text: t.text });\n    if (t.tokens) collectLinks(t.tokens, out);\n    if (t.items) collectLinks(t.items, out);\n  }\n  return out;\n}\n\nconst links = collectLinks(marked.lexer(inputs.markdown));\nreturn { links };\n```\n\n## Lists → nested items\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst lists = marked.lexer(inputs.markdown)\n  .filter((t) => t.type === \"list\")\n  .map((t) => ({\n    ordered: t.ordered,\n    items: t.items.map((item) => item.text)\n  }));\nreturn { lists };\n```\n\n## Code blocks → language + source\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst codeBlocks = marked.lexer(inputs.markdown)\n  .filter((t) => t.type === \"code\")\n  .map((t) => ({ language: t.lang || \"text\", code: t.text }));\nreturn { codeBlocks };\n```\n\n## Tables → rows of records\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst tables = marked.lexer(inputs.markdown)\n  .filter((t) => t.type === \"table\")\n  .map((t) => {\n    const headers = t.header.map((cell) => cell.text);\n    return t.rows.map((row) =>\n      Object.fromEntries(row.map((cell, i) => [headers[i], cell.text]))\n    );\n  });\nreturn { tables };\n```\n\n## Markdown → HTML\n\n```js\nimport { marked } from \"@nodetool-ai\u002Fsandbox-markdown\";\n\nconst html = marked.parse(inputs.markdown);\nreturn { html };\n```\n\n## Gotchas\n\n- **Everything runs in the guest.** The 64 MB guest heap holds your input text,\n  the token tree, and the returned value at once.\n- **`marked.lexer` is synchronous**, unlike `marked.parse` (which can be async\n  when you register an async extension — the default configuration is not).\n- **Token shapes differ by type.** A `list` token's items are themselves\n  tokens with their own `.tokens`; a `table` token has `header`\u002F`rows`, not a\n  flat `cells` array. Log a sample token when a shape is unclear.\n- **This pack is the only route to markdown parsing.** There is no\n  `data.parseMarkdown` global; every library the sandbox offers is an\n  importable module, and this is the one for markdown.\n",{"name":5,"description":7},"main","4ef72a828b24c99c49109033c7ec504c34f3bd17","packages\u002Fsandbox-packs\u002Fsandbox-markdown",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-markdown",{"tool":36,"command":37},"bunx","bunx skills add hanchenhao\u002Fai-canvas --skill sandbox-markdown",{"tool":39,"command":40},"pnpm","pnpm dlx skills add hanchenhao\u002Fai-canvas --skill sandbox-markdown","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-markdown\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"package.json","REFERENCE","参考文档",851,"https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-markdown\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},"01M7AE57C5APRDF96NB3G0WQMW","sandbox-tfjs","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","https:\u002F\u002Fgithub.com\u002Fhanchenhao\u002Fai-canvas\u002Fblob\u002Fmain\u002Fpackages\u002Fsandbox-packs\u002Fsandbox-tfjs\u002FSKILL.md",[],[]]