Agent skill

Gradient Text

by nexu-io in nexu-io/motion-anything

Give one short headline quiet premium emphasis: a slow on-brand gradient drifts through the type.

Apache-2.0Auto-check passedMedia & Creative

Install Gradient Text

skills CLI
$ npx skills add nexu-io/motion-anything --skill gradient-text -a claude-code

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

GitHub CLI
$ gh skill install nexu-io/motion-anything gradient-text --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/nexu-io/motion-anything.git skills-src && mkdir -p .claude/skills && cp -r skills-src/recipes/web/gradient-text .claude/skills/gradient-text && 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
gradient-text
GitHub stars
844
Token cost
~476 tokens
SKILL.md length
136 words
Files
4
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

Give one short headline quiet premium emphasis: a slow on-brand gradient drifts through the type.

  • Works in 3 steps: Copy gradient-text.css into the project… → Wrap the phrase → Set brand colors via --g1/--g2/--g3;…
  • Tasks that involve Plain language and style rules
  • SKILL.md covers When to use it, When NOT to use it (restraint), How to apply and Accessibility & performance, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gradient Text is an agent skill from nexu-io/motion-anything. Give one short headline quiet premium emphasis: a slow on-brand gradient drifts through the type. One phrase per view; never body copy (readability). Pure CSS; falls back to a solid brand color under prefers-reduced-motion.

Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `recipe.motion.yaml`).

It sits in Media & Creative, covering Plain language and style rules and Logo and visual identity. The repository describes itself as: ✨ The agentic motion layer — an open-source, chat-native motion engine. Describe the feeling; your AI ships the animation. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Plain language and style rules
  • Tasks that involve Logo and visual identity

Example prompts

  • “/gradient-text”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Copy gradient-text.css into the project and link it.
  2. Wrap the phrase
  3. Set brand colors via --g1/--g2/--g3; tune the duration (default 6s).

What it can do on your machine

Read from SKILL.md and the folder at commit b016900. 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 html).

    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

Gradient Text loads about 476 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 136 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~476

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 nexu-io/motion-anything at commit b016900, republished under its Apache-2.0 licence (© nexu-io). 136 words, ~476 tokens.

Download SKILL.mdSave it as .claude/skills/gradient-text/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
gradient-text
description
Give one short headline quiet premium emphasis: a slow on-brand gradient drifts through the type. One phrase per view; never body copy (readability). Pure CSS; falls back to a solid brand color under prefers-reduced-motion.
triggers
gradient text, animated headline, shimmering title, premium heading color, 渐变文字, 流光标题
od.mode
prototype
od.surface
web
od.platform
desktop
od.category
animation-motion
od.upstream
https://magicui.design/docs/components/animated-gradient-text
od.example_prompt
Use gradient-text on the hero word only: a slow on-brand gradient drifts through it. Keep the rest of the type solid; solid color under reduced-motion.

gradient-text

A gradient that drifts through a headline. Part of motion-anything; obeys MOTION-SPEC.md. Technique popularized by Magic UI, reimplemented dependency-free (pure CSS).

When to use it

  • One hero word / short headline / brand name / key metric you want to feel premium.

When NOT to use it (restraint)

  • Body copy or long text — it hurts readability and contrast. One short phrase per view.
  • When guaranteed color contrast is required for accessibility.

How to apply

  1. Copy gradient-text.css into the project and link it.
  2. Wrap the phrase:
    html
    <h1><span class="gradient-text">motion, anything</span></h1>
  3. Set brand colors via --g1/--g2/--g3; tune the duration (default 6s).

Accessibility & performance

  • Under prefers-reduced-motion the drift stops and the text renders in a solid --g1 color.
  • Animates background-position of a text-clipped gradient — GPU-safe.

Framework notes

  • Pure CSS; works in any framework. Keep the base --g1 readable as the reduced-motion fallback.

© nexu-io, Apache-2.0. 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 3 other files in recipes/web/gradient-text of nexu-io/motion-anything.

  • SKILL.md
  • gradient-text.css
  • preview.html
  • recipe.motion.yaml

Open the folder on GitHubat commit b016900

Compare with similar skills

Gradient Text 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.

Gradient Text compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gradient Text this skillnexu-io/motion-anything844—~476Automated safety check: PassApache-2.0
Brand and Design Toolkitnextlevelbuilder/ui-ux-pro-max-skill134k1 repos~3.5kAutomated safety check: PassMIT
Image Prompt ReverseLunarXuan/image-prompt-reverse465—~678Automated safety check: PassGPL-3.0
Opentraces MarketingJayFarei/opentraces100—~2.3kAutomated safety check: PassCustom licence
Brand Style Guiderampstackco/claude-skills940—~2.1kAutomated safety check: PassMIT
Anima Composition DirectorShiroEirin/comfyui-good-anima478—~2.9kAutomated safety check: PassGPL-3.0

Similar skills

  • Brand and Design Toolkit

    nextlevelbuilder/ui-ux-pro-max-skill

    Bundles design tasks behind one skill: brand identity, tokens, UI styling, logos, corporate identity mockups, slides, banners, icons and social images.

    134k GitHub starsUsed in 1 repo~3.5k tokens
    Media & CreativeAuto-check passed
  • Image Prompt Reverse

    LunarXuan/image-prompt-reverse

    Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts.

    465 GitHub stars~678 tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Opentraces Marketing

    JayFarei/opentraces

    Generate branded marketing screenshots of opentraces CLI commands — wordmark + CLI card + caption + wallpaper, filename-stamped and auto-copied to the clipboard.

    100 GitHub stars~2.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Brand Style Guide

    rampstackco/claude-skills

    Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts.

    940 GitHub stars~2.1k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Anima Composition Director

    ShiroEirin/comfyui-good-anima

    Convert Anima image-generation intent, tags, references, or rough prompts into concrete composition decisions.

    478 GitHub stars~2.9k tokensUpdated 3 mo ago
    Media & CreativeAuto-check passed
  • Canva Design Feedback

    canva-sdks/canva-skills

    Read a Canva design and return structured, actionable design feedback — visual hierarchy, copy/messaging, layout & spacing, consistency, readability, and accessibility.

    115 GitHub stars~1.2k tokensUpdated 3 mo ago
    Media & CreativeAuto-check passed

More from nexu-io/motion-anything

All 12 skills in this repo
  • Like Burst

    nexu-io/motion-anything

    Add a celebratory particle burst to a like / favorite / reaction button.

    844 GitHub stars~612 tokensUpdated 3 mo ago
    Auto-check passed
  • Border Beam

    nexu-io/motion-anything

    Give one card or CTA a lively accent: a small bright comet of light travels around its border.

    844 GitHub stars~461 tokensUpdated 3 mo ago
    Auto-check passed
  • Magnetic Button

    nexu-io/motion-anything

    Make a primary button feel alive by gently pulling it toward the cursor as it approaches, then springing back.

    844 GitHub stars~476 tokensUpdated 3 mo ago
    Auto-check passed
  • Scroll Reveal

    nexu-io/motion-anything

    Reveal content as it scrolls into view — a gentle rise + fade, once per element.

    844 GitHub stars~483 tokensUpdated 3 mo ago
    Auto-check passed
  • Web Shader Extractor

    nexu-io/motion-anything

    Extract a real WebGL / WebGPU / Canvas / shader effect from a live webpage (e.g.

    844 GitHub stars~541 tokensUpdated 3 mo ago
    Auto-check passed
  • Web To Design Md

    nexu-io/motion-anything

    Extract a real website's design tokens — colors, typography, spacing, CSS, and motion — into a structured design.md an AI can consume.

    844 GitHub stars~447 tokensUpdated 3 mo ago
    Auto-check passed

Questions about Gradient Text

What does Gradient Text do?

Give one short headline quiet premium emphasis: a slow on-brand gradient drifts through the type. Gradient Text is an agent skill from nexu-io/motion-anything. Give one short headline quiet premium emphasis: a slow on-brand gradient drifts through the type.

When should I use Gradient Text?

Gradient Text fits situations like: tasks that involve Plain language and style rules; tasks that involve Logo and visual identity.

How do I install Gradient Text in Claude Code?

Run `npx skills add nexu-io/motion-anything --skill gradient-text -a claude-code`. Or copy the skill folder (recipes/web/gradient-text in nexu-io/motion-anything) into .claude/skills/gradient-text in your project. Claude Code loads it when a task matches its description.

How do I install Gradient Text in Codex?

Run `npx skills add nexu-io/motion-anything --skill gradient-text -a codex`. Or copy the skill folder (recipes/web/gradient-text in nexu-io/motion-anything) into .agents/skills/gradient-text in your project. Codex loads it when a task matches its description.

Can I use Gradient Text 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 nexu-io/motion-anything --skill gradient-text -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gradient-text, .gemini/skills/gradient-text, .github/skills/gradient-text and .opencode/skills/gradient-text in your project.

What does Gradient Text need to run?

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

Does Gradient Text 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 Gradient Text 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 Gradient Text use?

Gradient Text is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gradient Text use?

About 476 tokens (SKILL.md is roughly 1.9k 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 Gradient Text?

Skills that share tags, products or a category with Gradient Text: Brand and Design Toolkit (nextlevelbuilder/ui-ux-pro-max-skill, 134k stars), Image Prompt Reverse (LunarXuan/image-prompt-reverse, 465 stars), Opentraces Marketing (JayFarei/opentraces, 100 stars) and Brand Style Guide (rampstackco/claude-skills, 940 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gradient Text?

nexu-io (a GitHub organization) maintains it in nexu-io/motion-anything, which has 844 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on July 7, 2026.

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