Agent skill

Export PDF

by bluzir in bluzir/claude-code-design

Export an HTML artifact to PDF via headless Chromium (puppeteer Page.pdf).

No licenceAuto-check passedDocuments & Office

Install Export PDF

skills CLI
$ npx skills add bluzir/claude-code-design --skill export-pdf -a claude-code

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

GitHub CLI
$ gh skill install bluzir/claude-code-design export-pdf --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/bluzir/claude-code-design.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/export-pdf .claude/skills/export-pdf && 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
export-pdf
GitHub stars
106
Token cost
~811 tokens
SKILL.md length
176 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
None found

At a glance

Export an HTML artifact to PDF via headless Chromium (puppeteer Page.pdf).

  • Works in 2 steps: Bash(which node) — required → Bash(test -d node_modules/puppeteer &&…
  • Tasks that involve PDF
  • SKILL.md covers Preflight, Steps, Script template… and Notes
  • Calls npm

What it does

Export PDF is an agent skill from bluzir/claude-code-design. Export an HTML artifact to PDF via headless Chromium (puppeteer Page.pdf). For multi-slide decks one page per <section.

Its SKILL.md is about 810 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 Documents & Office, covering PDF, HTML artifacts and Slides and decks. It works with Puppeteer and Bash. The repository describes itself as: Claude Design reproduced for Claude Code — HTML decks, prototypes, design systems, animated videos via skills + starters + Chrome DevTools MCP.

When your agent uses it

  • Tasks that involve PDF
  • Tasks that involve HTML artifacts
  • Tasks that involve Slides and decks

Example prompts

  • “/export-pdf”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Read, Write, Bash(node:*), Bash(realpath:*), Bash(mkdir:*), Bash(which:*), Bash(stat:*), Bash(ls:*)

Workflow steps

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

  1. Bash(which node) — required
  2. Bash(test -d node_modules/puppeteer && echo yes || echo no) — if no, tell user /doctor or run npm i -D puppeteer

What it can do on your machine

Read from SKILL.md and the folder at commit ce68c84. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Bash(node:*)
    • Bash(realpath:*)
    • Bash(mkdir:*)
    • Bash(which:*)
    • Bash(stat:*)
    • Bash(ls:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    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

Export PDF loads about 811 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 176 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~811

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 176 words (~811 tokens).

“Produce a PDF from an HTML artifact. Uses puppeteer's Page.pdf() which is lossless vector when the source is HTML/CSS/SVG.”

— opening of SKILL.md by bluzir
name
export-pdf
allowed-tools
Read, Write, Bash(node:*), Bash(realpath:*), Bash(mkdir:*), Bash(which:*), Bash(stat:*), Bash(ls:*)
argument-hint
<html-path> [output.pdf]

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/export-pdf of bluzir/claude-code-design.

Open the folder on GitHubat commit ce68c84

Compare with similar skills

Export PDF 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.

Export PDF compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Export PDF this skillbluzir/claude-code-design106—~811Automated safety check: PassNone
Ky Markdown RebuilderKyrieCheungYep/ky-markdown-rebuilder117—~5.7kAutomated safety check: PassNone
Sci HTMLShZhao27208/Aut_Sci_Write208—~1.4kAutomated safety check: NotesMIT
Paper2htmlQuZhan51496/paper2anything468—~3.3kAutomated safety check: NotesApache-2.0
Documentszhongkaifu/TensorSharp557—~4.2kAutomated safety check: PassBSD-3-Clause
Md2pdf Exportwentorai/Research-Claw858—~2.1kAutomated safety check: NotesCustom licence

Similar skills

  • Ky Markdown Rebuilder

    KyrieCheungYep/ky-markdown-rebuilder

    Rebuild visual documents into reliable Markdown by combining text extraction with page or screenshot alignment.

    117 GitHub stars~5.7k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed
  • Sci HTML

    ShZhao27208/Aut_Sci_Write

    Generate academic presentation-style HTML slide decks and browser reports from PDFs, structured text, Markdown, paper summaries, outlines, or research notes.

    208 GitHub stars~1.4k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check: notes
  • Paper2html

    QuZhan51496/paper2anything

    Convert an academic paper PDF into a publish-ready, self-contained single-page project homepage (a self-contained index.html) — the kind of paper landing page researchers host on GitHub Pages.

    468 GitHub stars~3.3k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check: notes
  • Documents

    zhongkaifu/TensorSharp

    Read and write real documents on the device - PDF, XLSX, DOCX, PPTX and CSV.

    557 GitHub stars~4.2k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Md2pdf Export

    wentorai/Research-Claw

    Convert Markdown files to PDF, PNG, or JPEG using headless Chrome (Puppeteer), following the same methodology as VS Code's Markdown Preview Enhanced extension.

    858 GitHub stars~2.1k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check: notes
  • Markdown Exporter

    bowenliang123/markdown-exporter

    Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.

    271 GitHub starsUsed in 1 repo~5.3k tokens
    Documents & OfficeAuto-check passed

More from bluzir/claude-code-design

All 18 skills in this repo
  • Apply Tweaks

    bluzir/claude-code-design

    Apply buffered tweaks from pending.yaml to the source HTML file.

    106 GitHub stars~726 tokensUpdated 5 mo ago
    Auto-check passed
  • Copy Example

    bluzir/claude-code-design

    Generate a working demo artifact on dummy content so the user can see a reference implementation.

    106 GitHub stars~782 tokensUpdated 5 mo ago
    Auto-check passed
  • Create Design System

    bluzir/claude-code-design

    Extract or build a design system (tokens, components, style guide).

    106 GitHub stars~1.1k tokensUpdated 5 mo ago
    Auto-check passed
  • Ingest GitHub

    bluzir/claude-code-design

    Clone a GitHub repo and extract design tokens (colors, fonts, spacing) from its codebase.

    106 GitHub stars~796 tokensUpdated 5 mo ago
    Auto-check passed
  • Ingest Screenshot

    bluzir/claude-code-design

    Analyze an uploaded image (screenshot of a design, website, app) and extract design tokens to use as a starting point.

    106 GitHub stars~676 tokensUpdated 5 mo ago
    Auto-check passed
  • Inspect

    bluzir/claude-code-design

    Resolve a natural-language element description ("the red button in the hero", "the third card from the top") to a concrete DOM element in the current preview + source-code location.

    106 GitHub stars~1.1k tokensUpdated 5 mo ago
    Auto-check passed

Works with

Questions about Export PDF

What does Export PDF do?

Export an HTML artifact to PDF via headless Chromium (puppeteer Page.pdf). Export PDF is an agent skill from bluzir/claude-code-design.pdf).

When should I use Export PDF?

Export PDF fits situations like: tasks that involve PDF; tasks that involve HTML artifacts; tasks that involve Slides and decks.

How do I install Export PDF in Claude Code?

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

How do I install Export PDF in Codex?

Run `npx skills add bluzir/claude-code-design --skill export-pdf -a codex`. Or copy the skill folder (.claude/skills/export-pdf in bluzir/claude-code-design) into .agents/skills/export-pdf in your project. Codex loads it when a task matches its description.

Can I use Export PDF 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 bluzir/claude-code-design --skill export-pdf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/export-pdf, .gemini/skills/export-pdf, .github/skills/export-pdf and .opencode/skills/export-pdf in your project.

What does Export PDF need to run?

Going by SKILL.md and its folder, Export PDF needs the command-line tools its instructions call (npm). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Write, Bash(node:*), Bash(realpath:*), Bash(mkdir:*), Bash(which:*), Bash(stat:*), Bash(ls:*).

Does Export PDF access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Export PDF 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 Export PDF use?

No licence was found for Export PDF or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Export PDF use?

About 811 tokens (SKILL.md is roughly 3.2k 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 Export PDF?

Skills that share tags, products or a category with Export PDF: Ky Markdown Rebuilder (KyrieCheungYep/ky-markdown-rebuilder, 117 stars), Sci HTML (ShZhao27208/Aut_Sci_Write, 208 stars), Paper2html (QuZhan51496/paper2anything, 468 stars) and Documents (zhongkaifu/TensorSharp, 557 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Export PDF?

bluzir (a GitHub user) maintains it in bluzir/claude-code-design, which has 106 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on April 20, 2026.

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