sandbox-yaml
Read and write YAML inside a Code node or CodeAct action, with js-yaml running in the guest
- License 许可
- AGPL-3.0
- 最近更新
- 2026-11-12
- Stars
- ★ 628
- Forks
- 90
01 前言 Front Matter
- name
- sandbox-yaml
- description
- Read and write YAML inside a Code node or CodeAct action, with js-yaml running in the guest
02 资源文件 1
- 参考文档package.json844 B
03 SKILL.md 正文
YAML in the sandbox
Specifier: @nodetool-ai/sandbox-yaml. One module, the js-yaml root export.
Import it at the top of the body.
load — YAML text to a value
import yaml from "@nodetool-ai/sandbox-yaml";
const config = yaml.load(inputs.text);
return { name: config.name, replicas: config.replicas };
load reads one document and throws a YAMLException with a line and column
on malformed input. Multi-document files go through loadAll, which returns an
array.
dump — a value to YAML text
import yaml from "@nodetool-ai/sandbox-yaml";
return { text: yaml.dump({ name: inputs.name, tags: inputs.tags }, { indent: 2 }) };
dump throws on a cyclic structure unless you pass { noRefs: false }, and on
a value it cannot represent (a function, a symbol).
Gotchas
- Everything runs in the guest. The 64 MB guest heap holds your input text, the parse tree, and the returned value at once. A file of a few megabytes is fine; a hundred megabytes is not.
- No timers, no I/O. The guest has no
setTimeout, no filesystem, and no Node builtins. js-yaml needs none of them — that is why it is admitted — but code you write around it must not reach for them either. - The safe schema is not the default.
yaml.loadusesDEFAULT_SCHEMA, which resolves tags such as!!timestamp. For input from a stranger, pass{ schema: yaml.FAILSAFE_SCHEMA }and get strings, arrays, and objects only. - This pack is the only route to YAML. There is no
data.parseYamlglobal any more; every library the sandbox offers is an importable module, and this is the one for YAML. A node that needs it declares it.
04 同仓库更多 Skills
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.
veo-3-prompting
Prompt Google's Veo 3 video line — the five-element shot/setting/subject/action/dialogue structure, the cinematography vocabulary it reads directly, duration and aspect-ratio tradeoffs, the audio and auto-fix switches per provider, and the fixes for visual drift, temporal inconsistency and audio mismatch. Use whenever the model id contains veo3 or veo-3 (fal-ai/veo3.1 and its fast, lite, image-to-video, first-last-frame and reference-to-video routes, fal-ai/veo3/image-to-video, google/veo3.1 on atlascloud, google/veo-3 and google/veo-3.1 on replicate, kie's veo-3-1, and Gemini's own veo-3.1-generate-preview) on generate_video, animate_image, generate_video_from_references or a TextToVideo node.