Agent skill

Capture Banners

by nguyenyou in nguyenyou/scalex

Re-render Scalex banner and OG image PNGs from their HTML source files using Chrome DevTools MCP.

MITAuto-check passedTesting & QA

Install Capture Banners

skills CLI
$ npx skills add nguyenyou/scalex --skill capture-banners -a claude-code

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

GitHub CLI
$ gh skill install nguyenyou/scalex capture-banners --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/nguyenyou/scalex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/capture-banners .claude/skills/capture-banners && 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
capture-banners
GitHub stars
109
Token cost
~586 tokens
SKILL.md length
218 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Re-render Scalex banner and OG image PNGs from their HTML source files using Chrome DevTools MCP.

  • Works in 4 steps: Open or navigate to the HTML file using… → Resize the viewport to 1200x630 → Take a screenshot and save directly to… → …
  • Banner HTML files are edited (slogan changes
  • SKILL.md covers Banner inventory, Required viewport size, Capture procedure and Notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Capture Banners is an agent skill from nguyenyou/scalex. Re-render Scalex banner and OG image PNGs from their HTML source files using Chrome DevTools MCP. Use this skill whenever banner HTML files are edited (slogan changes, color tweaks, layout changes) and the corresponding PNGs need to be regenerated. Triggers on "capture banners", "update banner images", "re-render banners", "regenerate PNGs", or after any edit to files in site/-banner.html or site/og-banner.html.

Its SKILL.md is about 590 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 Testing & QA, covering Browser testing and Social media graphics. It works with Chrome DevTools and Model Context Protocol. The repository describes itself as: Scala code intelligence for coding agents. Zero Build Server. Zero Compilation. Just answers. The licence is MIT.

When your agent uses it

  • Banner HTML files are edited (slogan changes
  • Layout changes) and the corresponding PNGs need to be regenerated
  • Capture banners
  • Update banner images

Example prompts

  • “capture banners”
  • “update banner images”
  • “re-render banners”
  • “/capture-banners”

Workflow steps

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

  1. Open or navigate to the HTML file using a file:// URL
  2. Resize the viewport to 1200x630
  3. Take a screenshot and save directly to the PNG path
  4. Repeat for the remaining 3 banners. You can reuse the same tab by navigating to the next HTML file.

What it can do on your machine

Read from SKILL.md and the folder at commit 9098af8. 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.

    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

Capture Banners loads about 586 tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 218 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~586

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 nguyenyou/scalex at commit 9098af8, republished under its MIT licence (© nguyenyou). 218 words, ~586 tokens.

Download SKILL.mdSave it as .claude/skills/capture-banners/SKILL.md (or your agent's skills folder).
name
capture-banners
description
Re-render Scalex banner and OG image PNGs from their HTML source files using Chrome DevTools MCP. Use this skill whenever banner HTML files are edited (slogan changes, color tweaks, layout changes) and the corresponding PNGs need to be regenerated. Triggers on "capture banners", "update banner images", "re-render banners", "regenerate PNGs", or after any edit to files in site/*-banner*.html or site/og-banner*.html.

Capture Banners

The Scalex project has 4 banner images that are rendered from HTML source files. When the HTML is edited, the PNGs must be re-captured to stay in sync.

Banner inventory

HTML sourcePNG outputPurpose
site/readme-banner-dark.htmlsite/readme-banner-dark.pngGitHub README banner (dark mode)
site/readme-banner-light.htmlsite/readme-banner-light.pngGitHub README banner (light mode)
site/og-banner.htmlsite/og-banner.pngOpenGraph social preview (dark)
site/og-banner-light.htmlsite/og-banner-light.pngOpenGraph social preview (light)

Required viewport size

All banners are designed at 1200 x 630 pixels. The HTML <body> is hardcoded to this size. The Chrome DevTools viewport must match exactly, otherwise the screenshot will crop or include extra whitespace.

Capture procedure

Use Chrome DevTools MCP tools. For each banner:

  1. Open or navigate to the HTML file using a file:// URL:

    file:///absolute/path/to/scalex/site/readme-banner-dark.html
  2. Resize the viewport to 1200x630:

    mcp__chrome-devtools__resize_page(width=1200, height=630)
  3. Take a screenshot and save directly to the PNG path:

    mcp__chrome-devtools__take_screenshot(
      filePath="site/readme-banner-dark.png",
      format="png"
    )
  4. Repeat for the remaining 3 banners. You can reuse the same tab by navigating to the next HTML file.

Notes

  • The Kestrel mascot image (Kestrel.png) is referenced by relative path in the HTML, so the file:// URL must point to the site/ directory for it to render.
  • After capturing, the PNGs are ready to commit — no post-processing needed.
  • If the images look wrong (missing mascot, broken layout), check that the HTML references are correct relative to the site/ directory.

© nguyenyou, 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 .agents/skills/capture-banners of nguyenyou/scalex.

Open the folder on GitHubat commit 9098af8

Compare with similar skills

Capture Banners 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.

Capture Banners compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Capture Banners this skillnguyenyou/scalex109—~586Automated safety check: PassMIT
Record E2E Giflablup/backend.ai-webui133—~907Automated safety check: NotesLGPL-3.0
Browser Testing with Chrome DevToolsaddyosmani/agent-skills105k4 repos~3.5kAutomated safety check: WarnMIT
Diff-Driven Smoke TestsSkyvern-AI/skyvern23k—~5.2kAutomated safety check: PassAGPL-3.0
Mirroir Onboardjfarcand/mirroir-mcp247—~4.4kAutomated safety check: NotesApache-2.0
Octocode Chrome Devtoolsbgauryy/octocode949—~1.6kAutomated safety check: PassMIT

Similar skills

  • Record E2E Gif

    lablup/backend.ai-webui

    Record Playwright e2e tests as one GIF per test case (video → ffmpeg palette GIF) and return a markdown table for a PR description.

    133 GitHub stars~907 tokensUpdated today
    Testing & QAAuto-check: notes
  • Connects an agent to a real Chrome instance through the Chrome DevTools MCP server, so it can inspect the DOM, read console errors and profile performance directly.

    105k GitHub starsUsed in 4 repos~3.5k tokens
    Testing & QAAuto-check: warnings
  • Diff-Driven Smoke Tests

    Skyvern-AI/skyvern

    Reads your git diff, writes a handful of happy-path browser smoke tests, runs them with Skyvern or Chrome DevTools MCP and posts screenshot evidence to the PR.

    23k GitHub stars~5.2k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Mirroir Onboard

    jfarcand/mirroir-mcp

    Onboard a consumer web app to mirroir's .mirroir/ dotfile by EXPLORING the running app (chrome-devtools-mcp) — derive real selectors from the accessibility tree, exercise each surface's primary…

    247 GitHub stars~4.4k tokensUpdated 5 days ago
    Testing & QAAuto-check: notes
  • Octocode Chrome Devtools

    bgauryy/octocode

    A skill your agent uses when a live page needs Chrome DevTools/CDP evidence: network failures, console errors, performance, DOM/CSS actionability, screenshots/PDF, cookies/storage…

    949 GitHub stars~1.6k tokensUpdated 2 days ago
    Testing & QAAuto-check passed
  • System Bridge Testing Workflow

    timmo001/system-bridge

    How to test System Bridge - Go table-driven tests and commands, web-client quality checks (lint/typecheck/format, no unit tests), the Chrome DevTools MCP interactive test loop for UI and WebSocket…

    357 GitHub stars~844 tokensUpdated today
    Testing & QAAuto-check passed

More from nguyenyou/scalex

  • Scalex

    nguyenyou/scalex

    Explore and navigate Git-tracked Scala 2/3 and Java source with Scalex.

    109 GitHub stars~2k tokensUpdated 23 days ago
    Auto-check passed
  • Benchmark

    nguyenyou/scalex

    Run scalex performance benchmarks, profiling, and timing analysis.

    109 GitHub stars~3.4k tokensUpdated 23 days ago
    Auto-check passed

Questions about Capture Banners

What does Capture Banners do?

Re-render Scalex banner and OG image PNGs from their HTML source files using Chrome DevTools MCP. Capture Banners is an agent skill from nguyenyou/scalex. Re-render Scalex banner and OG image PNGs from their HTML source files using Chrome DevTools MCP.

When should I use Capture Banners?

Capture Banners fits situations like: banner HTML files are edited (slogan changes; layout changes) and the corresponding PNGs need to be regenerated; capture banners; update banner images.

How do I install Capture Banners in Claude Code?

Run `npx skills add nguyenyou/scalex --skill capture-banners -a claude-code`. Or copy the skill folder (.agents/skills/capture-banners in nguyenyou/scalex) into .claude/skills/capture-banners in your project. Claude Code loads it when a task matches its description.

How do I install Capture Banners in Codex?

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

Can I use Capture Banners 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 nguyenyou/scalex --skill capture-banners -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/capture-banners, .gemini/skills/capture-banners, .github/skills/capture-banners and .opencode/skills/capture-banners in your project.

What does Capture Banners need to run?

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

Does Capture Banners 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 Capture Banners 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 Capture Banners use?

Capture Banners 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 Capture Banners use?

About 586 tokens (SKILL.md is roughly 2.3k 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 Capture Banners?

Skills that share tags, products or a category with Capture Banners: Record E2E Gif (lablup/backend.ai-webui, 133 stars), Browser Testing with Chrome DevTools (addyosmani/agent-skills, 105k stars), Diff-Driven Smoke Tests (Skyvern-AI/skyvern, 23k stars) and Mirroir Onboard (jfarcand/mirroir-mcp, 247 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Capture Banners?

nguyenyou (a GitHub user) maintains it in nguyenyou/scalex, which has 109 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 18, 2026.

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