Agent skill

Ray

by Railly in Railly/tinte

Generate code screenshots via ray.tinte.dev API. An agent skill from Railly/tinte.

MITAuto-check passedFrontend & Design

Install Ray

skills CLI
$ npx skills add Railly/tinte --skill ray -a claude-code

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

GitHub CLI
$ gh skill install Railly/tinte ray --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/Railly/tinte.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ray .claude/skills/ray && 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
ray
GitHub stars
624
Token cost
~712 tokens
SKILL.md length
281 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Generate code screenshots via ray.tinte.dev API. An agent skill from Railly/tinte.

  • Works in 4 steps: Identify the code to screenshot (from… → Detect language from file extension or… → Call the API via curl → …
  • User asks for code screenshots
  • SKILL.md covers API, Parameters, Notes and Workflow, plus 3 more sections
  • Calls curl and magick; reaches ray.tinte.dev

What it does

Ray is an agent skill from Railly/tinte. Generate code screenshots via ray.tinte.dev API. Use when user asks for code screenshots, code images, code snippets as images, or says "ray". Calls POST https://ray.tinte.dev/api/v1/screenshot and saves the PNG result.

Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering Design systems and Hooks and plugins. It works with shadcn/ui, Visual Studio Code, Next.js and Bash. The repository describes itself as: Compile your design system into an Agent Plugin. Extract an identity from any reference, emit SKILL.md + tokens.css, lint what bypasses your tokens. The licence is MIT.

When your agent uses it

  • User asks for code screenshots
  • Code snippets as images

Example prompts

  • “/ray”

Requirements

  • Python 3

Workflow steps

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

  1. Identify the code to screenshot (from file, clipboard, or user input)
  2. Detect language from file extension or content
  3. Call the API via curl
  4. Save the PNG and open it

What it can do on your machine

Read from SKILL.md and the folder at commit 7905be3. 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

    Shell commands in SKILL.md call:

    • curl
    • magick

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • ray.tinte.dev

    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

Ray loads about 712 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 281 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~712

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 Railly/tinte at commit 7905be3, republished under its MIT licence (© Railly). 281 words, ~712 tokens.

Download SKILL.mdSave it as .claude/skills/ray/SKILL.md (or your agent's skills folder).
name
ray
description
Generate code screenshots via ray.tinte.dev API. Use when user asks for code screenshots, code images, code snippets as images, or says "ray". Calls POST https://ray.tinte.dev/api/v1/screenshot and saves the PNG result.

Ray - Code Screenshots

Generate code screenshots by calling the ray.tinte.dev API.

API

POST https://ray.tinte.dev/api/v1/screenshot
Content-Type: application/json

Parameters

ParamTypeDefaultNotes
codestringrequired1-10,000 chars
languagestring"typescript"typescript, javascript, python, rust, go, java, cpp, c, html, css, json, bash, sql, markdown, toml
themestring or TinteBlock"one-hunter"Slug from tinte.dev or inline object
mode"dark" | "light""dark"
paddingnumber320-256
fontSizenumber148-32
lineNumbersbooleantrue
titlestring""Window chrome title (max 100)
backgroundstring"midnight"One of: midnight, sunset, ocean, forest, ember, steel, aurora, none. Hex colors are not accepted.
format"png""png"PNG only
scalenumber21-4 (retina)

Notes

  • background: "none" returns a transparent RGBA PNG. Useful when you want to composite the screenshot onto a custom background.
  • Returned PNGs always include some transparent margin around the window for the drop shadow, even with padding: 0. If you're compositing the result, trim that halo first (e.g. magick input.png -trim +repage output.png).
  • Long snippets can take 30-60+ seconds to render. Use a per-request timeout when calling from scripts or agents.

Workflow

  1. Identify the code to screenshot (from file, clipboard, or user input)
  2. Detect language from file extension or content
  3. Call the API via curl
  4. Save the PNG and open it

Example

bash
curl -s -X POST https://ray.tinte.dev/api/v1/screenshot \
  -H 'Content-Type: application/json' \
  -d '{
    "code": "const greeting = \"Hello, world!\";",
    "language": "typescript",
    "theme": "one-hunter",
    "title": "hello.ts"
  }' -o screenshot.png && open screenshot.png

Language Detection

ExtensionLanguage
.ts, .tsxtypescript
.js, .jsxjavascript
.pypython
.rsrust
.gogo
.javajava
.cpp, .cc, .cxxcpp
.c, .hc
.htmlhtml
.csscss
.jsonjson
.sh, .bashbash
.sqlsql
.mdmarkdown
.tomltoml

Themes

  • Default: "one-hunter" (Vercel-inspired dark theme)
  • Any slug from tinte.dev: "github-dark", "dracula", "catppuccin", etc.
  • Inline TinteBlock object with 13 semantic colors (bg, tx, tx_2, tx_3, ui, ui_2, ui_3, ac_1, ac_2, ac_3, pr, sc, nt)

© Railly, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/ray of Railly/tinte.

Open the folder on GitHubat commit 7905be3

Compare with similar skills

Ray 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.

Ray compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ray this skillRailly/tinte624—~712Automated safety check: PassMIT
Creative Tim UI Blockscreativetimofficial/ui12k—~2.1kAutomated safety check: NotesMIT
Cosscrafter-station/petdex4.2k—~1.4kAutomated safety check: PassMIT
Ss Learnbitjaru/styleseed970—~1.3kAutomated safety check: PassMIT
Nextjs Nextra Starter Distillpdsuwwz/nextjs-nextra-starter318—~596Automated safety check: PassMIT
8sl Consume Registry8starlabs/ui140—~781Automated safety check: PassMIT

Similar skills

  • Creative Tim UI Blocks

    creativetimofficial/ui

    Helps install, generate and review Creative Tim UI blocks: shadcn/ui-based React and Tailwind sections that follow a restrained, production-minded design philosophy.

    12k GitHub stars~2.1k tokensUpdated 6 mo ago
    Frontend & DesignAuto-check: notes
  • Coss

    crafter-station/petdex

    Helps implement coss UI components correctly. An agent skill from crafter-station/petdex.

    4.2k GitHub stars~1.4k tokensUpdated 8 days ago
    Frontend & DesignAuto-check passed
  • Ss Learn

    bitjaru/styleseed

    Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or…

    970 GitHub stars~1.3k tokensUpdated 6 days ago
    Frontend & DesignAuto-check passed
  • Nextjs Nextra Starter Distill

    pdsuwwz/nextjs-nextra-starter

    Distill and apply this repository's Next.js Nextra starter architecture, implemented features, extension points, and migration patterns.

    318 GitHub stars~596 tokensUpdated 20 days ago
    Frontend & DesignAuto-check passed
  • A skill your agent uses when users want to install, integrate, or adapt 8StarLabs UI components in a Next.js plus shadcn project.

    140 GitHub stars~781 tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Styleseed

    bitjaru/styleseed

    Build, improve, or inspect UI with StyleSeed. An agent skill from bitjaru/styleseed.

    970 GitHub stars~1.1k tokensUpdated 6 days ago
    Frontend & DesignAuto-check passed

More from Railly/tinte

  • Tinte

    Railly/tinte

    Agent-native design system infrastructure. An agent skill from Railly/tinte.

    624 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Tinte Landing

    Railly/tinte

    Design or substantially improve a landing page for tinte. An agent skill from Railly/tinte.

    624 GitHub stars~3.9k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Ray

What does Ray do?

Generate code screenshots via ray.tinte.dev API. An agent skill from Railly/tinte. Ray is an agent skill from Railly/tinte.dev API.

When should I use Ray?

Ray fits situations like: user asks for code screenshots; code snippets as images.

How do I install Ray in Claude Code?

Run `npx skills add Railly/tinte --skill ray -a claude-code`. Or copy the skill folder (skills/ray in Railly/tinte) into .claude/skills/ray in your project. Claude Code loads it when a task matches its description.

How do I install Ray in Codex?

Run `npx skills add Railly/tinte --skill ray -a codex`. Or copy the skill folder (skills/ray in Railly/tinte) into .agents/skills/ray in your project. Codex loads it when a task matches its description.

Can I use Ray 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 Railly/tinte --skill ray -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ray, .gemini/skills/ray, .github/skills/ray and .opencode/skills/ray in your project.

What does Ray need to run?

Going by SKILL.md and its folder, Ray needs the command-line tools its instructions call (curl and magick). Our summary lists: Python 3.

Does Ray access the network?

SKILL.md names 1 domain. In commands or code: ray.tinte.dev; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Ray 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 Ray use?

Ray is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ray use?

About 712 tokens (SKILL.md is roughly 2.8k 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 Ray?

Skills that share tags, products or a category with Ray: Creative Tim UI Blocks (creativetimofficial/ui, 12k stars), Coss (crafter-station/petdex, 4.2k stars), Ss Learn (bitjaru/styleseed, 970 stars) and Nextjs Nextra Starter Distill (pdsuwwz/nextjs-nextra-starter, 318 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ray?

Railly (a GitHub user) maintains it in Railly/tinte, which has 624 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 8, 2026.

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