Agent skill

Sandbox HTML

by nodetool-ai in nodetool-ai/nodetool

Select elements out of HTML and convert a page to markdown in a Code node or CodeAct action, with cheerio and turndown running on the host

AGPL-3.0Auto-check passedDocuments & Office

Install Sandbox HTML

skills CLI
$ npx skills add nodetool-ai/nodetool --skill sandbox-html -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nodetool-ai/nodetool sandbox-html --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/sandbox-packs/sandbox-html .claude/skills/sandbox-html && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sandbox-html
GitHub stars
560
Token cost
~839 tokens
SKILL.md length
268 words
Files
2
Skills in repo
127
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Select elements out of HTML and convert a page to markdown in a Code node or CodeAct action, with cheerio and turndown running on the host

  • Documents & Office work in your project
  • SKILL.md covers select — CSS selection, toMarkdown — a whole page, toText — a whole page as plain… and extractLinks / extractImages /…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sandbox HTML is an agent skill from nodetool-ai/nodetool. Select elements out of HTML and convert a page to markdown in a Code node or CodeAct action, with cheerio and turndown running on the host

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `package.json`).

It sits in Documents & Office. The repository describes itself as: Agent-first Creative Workspace. The licence is AGPL-3.0.

When your agent uses it

  • Documents & Office work in your project

Example prompts

  • “/sandbox-html”

What it can do on your machine

Read from SKILL.md and the folder at commit 58765d3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sandbox HTML loads about 839 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 268 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~839

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nodetool-ai/nodetool at commit 58765d3, republished under its AGPL-3.0 licence (© nodetool-ai). 268 words, ~839 tokens.

Download SKILL.mdSave it as .claude/skills/sandbox-html/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sandbox-html
description
Select elements out of HTML and convert a page to markdown in a Code node or CodeAct action, with cheerio and turndown running on the host

HTML in the sandbox

Specifier: @nodetool-ai/sandbox-html. Import it at the top of the body.

cheerio imports 25 Node builtins and turndown wants a DOM, so neither compiles into the guest. This pack is a host module: the import resolves to a generated facade over NodeTool's own implementation. Both exports are async.

select — CSS selection

js
import { select } from "@nodetool-ai/sandbox-html";

const hrefs = await select(inputs.html, "a[href]", { attr: "href", limit: 500 });
const titles = await select(inputs.html, "h2");   // trimmed text of each match
return { hrefs, titles };

Returns trimmed text per match, or the named attribute when attr is set. limit defaults to 100 and is clamped to 1000 — the cap is in the host implementation, so raising it in the call does nothing.

toMarkdown — a whole page

js
import { toMarkdown } from "@nodetool-ai/sandbox-html";

const markdown = await toMarkdown(inputs.html);
return { markdown };

The usual first step before summarizing or indexing a fetched page. Pass { turndown: {...} } to override turndown's own options.

toText — a whole page as plain text

js
import { toText } from "@nodetool-ai/sandbox-html";

const text = await toText(inputs.html);
return { text };

Strips <script>/<style> and every tag, then collapses whitespace.

js
import {
  extractLinks,
  extractImages,
  extractAudio,
  extractVideos
} from "@nodetool-ai/sandbox-html";

const links = await extractLinks(inputs.html, inputs.baseUrl);
// [{ href, text, type: "internal" | "external" }, ...]

const images = await extractImages(inputs.html, inputs.baseUrl); // string[] of resolved URLs
const audio = await extractAudio(inputs.html, inputs.baseUrl);
const videos = await extractVideos(inputs.html, inputs.baseUrl);

baseUrl is optional. When set, relative src/href values resolve against it and extractLinks classifies same-origin links as internal. Each extractor returns at most 1000 items.

extractMetadata — title, description, keywords

js
import { extractMetadata } from "@nodetool-ai/sandbox-html";

const { title, description, keywords } = await extractMetadata(inputs.html);

Any field the page doesn't set comes back null.

extractReadableText — strip chrome, keep the article

js
import { extractReadableText } from "@nodetool-ai/sandbox-html";

const article = await extractReadableText(inputs.html);

Removes script/style/nav/aside/footer/header, then returns the text of the first match among article, main, [id*=content], [class*=content], or body. A page with none of those returns "No main content found".

Getting a page's base URL

No import needed — new URL(pageUrl).origin gives the base URL to pass into the extractors above.

Gotchas

  • Every export is async.
  • 5 MB of HTML per call. Larger input is refused by name.
  • A selector that matches nothing returns [], never null. An invalid selector throws with cheerio's own message.
  • Extractors cap at 1000 items. Anything past that is silently dropped.

© nodetool-ai, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in packages/sandbox-packs/sandbox-html of nodetool-ai/nodetool.

  • SKILL.md
  • package.json

Open the folder on GitHubat commit 58765d3

Compare with similar skills

Sandbox HTML next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sandbox HTML compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sandbox HTML this skillnodetool-ai/nodetool560—~839Automated safety check: PassAGPL-3.0
Markdown Article FormatterJimLiu/baoyu-skills26k6 repos~3.5kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78214 repos~3.2kAutomated safety check: NotesMIT
Obsidian MarkdownAtmosphere/atmosphere3.8k20 repos~1.3kAutomated safety check: PassApache-2.0
DOCXrvdbreemen/OTGW-firmware20733 repos~4.3kAutomated safety check: PassProprietary
Gzh Designisjiamu/gzh-design-skill3.9k1 repos~2.2kAutomated safety check: PassAGPL-3.0

Similar skills

  • Markdown Article Formatter

    JimLiu/baoyu-skills

    Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.

    26k GitHub starsUsed in 6 repos~3.5k tokens
    Documents & OfficeAuto-check passed
  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    782 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Obsidian Markdown

    Atmosphere/atmosphere

    Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.

    3.8k GitHub starsUsed in 20 repos~1.3k tokens
    Documents & OfficeAuto-check passed
  • DOCX

    rvdbreemen/OTGW-firmware

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).

    207 GitHub starsUsed in 33 repos~4.3k tokens
    Documents & OfficeAuto-check passed
  • Gzh Design

    isjiamu/gzh-design-skill

    微信公众号文章排版引擎,将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取,自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入(非 Markdown…

    3.9k GitHub starsUsed in 1 repo~2.2k tokens
    Documents & OfficeAuto-check passed
  • Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.

    41k GitHub stars~2.5k tokensUpdated yesterday
    Documents & OfficeAuto-check passed

More from nodetool-ai/nodetool

All 127 skills in this repo
  • Beat Sync Editing

    nodetool-ai/nodetool

    Cut a NodeTool timeline to music and shape its pacing — detect the beat grid, place cuts on phrases, pick a cut type, build speed ramps with time remap, and give the piece an arc.

    560 GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Caption Titles

    nodetool-ai/nodetool

    Add and animate a consistent text layer on an existing NodeTool timeline.

    560 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Color Motion

    nodetool-ai/nodetool

    Choose and animate colour on a NodeTool timeline, including shape and text gradients, colour grades, 3D LUTs, and dither.

    560 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Commercial Beat Sheet

    nodetool-ai/nodetool

    Write a shootable, precisely timed commercial beat sheet and store it as a NodeTool storyboard, with a consistent entity roster behind every shot.

    560 GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • Elevenlabs Audio Prompting

    nodetool-ai/nodetool

    Direct ElevenLabs speech, dialogue, sound effects and music — the bracketed audio tags v3 acts on and why the voice decides whether a tag lands, stability as the delivery dial, punctuation instead…

    560 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Frame Composition

    nodetool-ai/nodetool

    Stage the frame on a NodeTool timeline — grids, focal placement, safe areas per aspect ratio, depth layers and parallax, camera moves, and where elements enter and leave.

    560 GitHub stars~3.5k tokensUpdated today
    Auto-check passed

Questions about Sandbox HTML

What does Sandbox HTML do?

Select elements out of HTML and convert a page to markdown in a Code node or CodeAct action, with cheerio and turndown running on the host. Sandbox HTML is an agent skill from nodetool-ai/nodetool.

When should I use Sandbox HTML?

Sandbox HTML fits situations like: documents & Office work in your project.

How do I install Sandbox HTML in Claude Code?

Run `npx skills add nodetool-ai/nodetool --skill sandbox-html -a claude-code`. Or copy the skill folder (packages/sandbox-packs/sandbox-html in nodetool-ai/nodetool) into .claude/skills/sandbox-html in your project. Claude Code loads it when a task matches its description.

How do I install Sandbox HTML in Codex?

Run `npx skills add nodetool-ai/nodetool --skill sandbox-html -a codex`. Or copy the skill folder (packages/sandbox-packs/sandbox-html in nodetool-ai/nodetool) into .agents/skills/sandbox-html in your project. Codex loads it when a task matches its description.

Can I use Sandbox HTML in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nodetool-ai/nodetool --skill sandbox-html -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sandbox-html, .gemini/skills/sandbox-html, .github/skills/sandbox-html and .opencode/skills/sandbox-html in your project.

What does Sandbox HTML need to run?

SKILL.md names no scripts, command-line tools or credentials: Sandbox HTML is instructions for the agent only.

Does Sandbox HTML access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sandbox HTML safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sandbox HTML use?

Sandbox HTML is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sandbox HTML use?

About 839 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sandbox HTML?

Skills that share tags, products or a category with Sandbox HTML: Markdown Article Formatter (JimLiu/baoyu-skills, 26k stars), Markitdown (ImCa0/just-laws, 782 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and DOCX (rvdbreemen/OTGW-firmware, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sandbox HTML?

nodetool-ai (a GitHub organization) maintains it in nodetool-ai/nodetool, which has 560 GitHub stars. The repository holds 127 skills in this directory. The repository was last updated on October 9, 2026.

Source: nodetool-ai/nodetool on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.