sandbox-docx
Build a Word document in a Code node or CodeAct action, with docx running on the host
- License 许可
- AGPL-3.0
- 最近更新
- 2026-11-15
- Stars
- ★ 635
- Forks
- 91
01 前言 Front Matter
- name
- sandbox-docx
- description
- Build a Word document in a Code node or CodeAct action, with docx running on the host
02 资源文件 8
- 资产文件assets/README.md361 B
- 参考文档package.json836 B
- 参考文档references/README.md751 B
- 脚本scripts/audit_log_analyzer.py4.7 KB
- 脚本scripts/audit_log_generator.py4.7 KB
- 脚本scripts/audit_table_creator.sh4.8 KB
- 脚本scripts/audit-archival.sh820 B
- 脚本scripts/README.md477 B
03 SKILL.md 正文
Word documents in the sandbox
Specifier: @nodetool-ai/sandbox-docx. Import it at the top of the body.
docx builds a document out of class instances (Paragraph, TextRun,
Table, …) that cannot cross the guest boundary as plain data. This pack is a
host module: you describe the document as a JSON element list and the host
builds the real .docx bytes.
build — element list to .docx bytes
import { build } from "@nodetool-ai/sandbox-docx";
const bytes = await build({
properties: { title: "Q3 Report", author: "NodeTool" },
elements: [
{ type: "heading", text: "Q3 Report", level: 1 },
{ type: "paragraph", text: "Revenue grew 12% quarter over quarter.", bold: true },
{ type: "table", rows: [["Month", "Revenue"], ["Jul", "120k"], ["Aug", "134k"]] },
{ type: "pageBreak" },
{ type: "paragraph", text: "See appendix for methodology.", alignment: "CENTER" }
]
});
await workspace.writeBytes("report.docx", bytes);
Element types:
heading—text,level(1–6, default 1)paragraph—text,alignment(LEFT/CENTER/RIGHT/JUSTIFY, defaultLEFT),bold,italic,fontSize(points, default 12)table—rows, a 2D array; every cell is stringifiedimage—data(aUint8Array),width/heightin inchespageBreak— no fields
properties.title/author/subject/keywords set the document's metadata.
Gotchas
buildis async and returns aUint8Array.- Writing only. To read an existing
.docx, use@nodetool-ai/sandbox-mammothinstead — these are two different libraries on two different sides of the format. - Images are inches, not pixels.
width/heightfollow docx's own convention; omit them and the image renders at a fixed placeholder size. - 10 MB per image. The shared host-module input cap applies to each
datafield.
04 同仓库更多 Skills
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler.
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.
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/wan-2.6/text-to-video, alibaba/wan-2.6/image-to-video, wan-video/wan-2.6-t2v, wan-video/wan-2.6-i2v, wan-video/wan2.6-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.
video-workflow
Build a reusable NodeTool video workflow for batches or repeated inputs. For a single finished piece, use a storyboard skill.
video-clone
Analyze a reference video and recreate its shot structure with a new product or cast in NodeTool.
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.