sandbox-csv
Parse and write CSV in a Code node or CodeAct action, with papaparse running on the host behind a generated facade
- License 许可
- AGPL-3.0
- 最近更新
- 2026-11-15
- Stars
- ★ 635
- Forks
- 91
01 前言 Front Matter
- name
- sandbox-csv
- description
- Parse and write CSV in a Code node or CodeAct action, with papaparse running on the host behind a generated facade
02 资源文件 2
- 参考文档package.json821 B
- 参考文档references/details.md4.4 KB
03 SKILL.md 正文
CSV in the sandbox
Specifier: @nodetool-ai/sandbox-csv. Import it at the top of the body.
papaparse imports node:stream, so it cannot be compiled into the guest. This
pack is a host module: the import resolves to a generated facade whose two
exports call NodeTool's own implementation. Both are async — a host call is a
round trip.
parse — CSV text to records
import { parse } from "@nodetool-ai/sandbox-csv";
const rows = await parse(inputs.csv); // records keyed by the header row
const raw = await parse(inputs.csv, { header: false }); // string[][]
return { count: rows.length, first: rows[0] ?? null };
Options: header (default true), delimiter (one character; omit to
auto-detect).
Values stay strings. There is no dynamicTyping, so a column never changes
shape between runs — convert what you need with Number() or new Date().
stringify — records back to CSV
import { stringify } from "@nodetool-ai/sandbox-csv";
const csv = await stringify(inputs.rows, { delimiter: ";" });
return { csv };
Takes records or row arrays. Options: header (default true), delimiter
(exactly one character).
Gotchas
- Every export is async.
parse(...)withoutawaitgives you a Promise. - 5 MB of text per call. Input over that is refused by name. Split a bigger
file, or read it in slices with
workspace.read. - Bounded concurrency still helps. Host calls start when invoked, so
Promise.allover severalparsecalls runs them together;parallelMapis the bounded form.
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.