sandbox-mammoth
Read a Word document as text or HTML in a Code node or CodeAct action, with mammoth 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-mammoth
- description
- Read a Word document as text or HTML in a Code node or CodeAct action, with mammoth running on the host
02 资源文件 4
- 资产文件assets/README.md339 B
- 参考文档package.json862 B
- 参考文档references/README.md475 B
- 脚本scripts/README.md536 B
03 SKILL.md 正文
Word documents in the sandbox (reading)
Specifier: @nodetool-ai/sandbox-mammoth. Import it at the top of the body.
mammoth reads a .docx buffer through Node's own zip/XML stack; it will never
be a guest module. This pack is a host module: the import resolves to a
generated facade over NodeTool's own implementation.
extractRawText — docx bytes to plain text
import { extractRawText } from "@nodetool-ai/sandbox-mammoth";
const bytes = await workspace.readBytes("report.docx");
const text = await extractRawText(bytes);
Formatting is discarded — this is the fast path when you only need the words.
convertToHtml — docx bytes to HTML
import { convertToHtml } from "@nodetool-ai/sandbox-mammoth";
const html = await convertToHtml(bytes);
Headings, lists, tables, bold/italic runs, and embedded images (as base64 data URIs) survive the conversion. Track changes, headers/footers, footnotes, and exact visual layout do not — mammoth targets semantic HTML, not a pixel-exact render.
Get the bytes from workspace.readBytes, or from a fetched body with
await response.bytes().
Gotchas
- Both exports are async.
- 10 MB per document. Larger input is refused by name.
- Reading only. To build a
.docx, use@nodetool-ai/sandbox-docxinstead.
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.