Convert, mix, and measure colors inside a Code node or CodeAct action, with culori running in the guest
Scanned 9/1/2026
Install to Claude Code
npx -y skills add nodetool-ai/nodetool --skill sandbox-color --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Sandbox Color?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nodetool-ai-sandbox-color)More formats (shields.io, HTML) on the badges page.
---
name: sandbox-color
description: Convert, mix, and measure colors inside a Code node or CodeAct action, with culori running in the guest
---
# Color in the sandbox
Specifier: `@nodetool-ai/sandbox-color`. One module, culori's root export.
Import it at the top of the body.
## Parse and convert
```js
import { parse, formatHex, converter } from "@nodetool-ai/sandbox-color";
const color = parse(inputs.hex);
const rgb = converter("rgb")(color);
return { hex: formatHex(color), rgb };
```
## Mix and difference
```js
import { interpolate, formatHex, differenceCiede2000 } from "@nodetool-ai/sandbox-color";
const mix = interpolate(["#2563eb", "#f97316"]);
const mid = formatHex(mix(0.5));
const delta = differenceCiede2000()("#2563eb", "#f97316");
return { mid, delta };
```
## Gotchas
- **Objects, not CSS strings, after parse.** A parsed color is `{ mode, ...channels }`.
- **Named imports.** There is no useful default export.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...