New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

PDF Skill

by OpenLoaf in OpenLoaf/OpenLoaf

All-in-one PDF read / write / convert / OCR. An agent skill from OpenLoaf/OpenLoaf.

AGPL-3.0Auto-check passedDocuments & Office

Install PDF Skill

skills CLI
$ npx skills add OpenLoaf/OpenLoaf --skill pdf-skill -a claude-code

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

GitHub CLI
$ gh skill install OpenLoaf/OpenLoaf pdf-skill --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/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/pdf/en .claude/skills/pdf-skill && 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
pdf-skill
GitHub stars
108
Token cost
~2k tokens
SKILL.md length
445 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
AGPL-3.0

At a glance

All-in-one PDF read / write / convert / OCR. An agent skill from OpenLoaf/OpenLoaf.

  • Works in 5 steps: Read: PdfInspect is the only entry point → Write: JsSandbox + pdf-lib / pdfkit → OCR (scanned PDFs) → …
  • Scenarios: summarize a PDF
  • SKILL.md covers Tool List, 1. Read: PdfInspect is the…, 2. Write: JsSandbox + pdf-lib… and 3. OCR (scanned PDFs), plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

PDF Skill is an agent skill from OpenLoaf/OpenLoaf. All-in-one PDF read / write / convert / OCR. Trigger scenarios: summarize a PDF, extract text or tables, fill an AcroForm, render pages as images, merge, split, add a watermark, rotate, encrypt/decrypt, create a new PDF (invoice / report / receipt), convert between PDF and docx/md/txt. Typical phrasings: "summarize this PDF", "fill out this PDF form", "merge these PDFs", "add a watermark to the PDF", "convert PDF to Word", "OCR this scan", "show me what page 3 of the PDF looks like". Load this skill whenever the…

Its SKILL.md is about 2k 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 and Forms and invoices. It works with Microsoft Word. The repository describes itself as: 🍞Open-source, local-first AI workspace with Agents, multi-model chat (GPT/Claude/Gemini/DeepSeek), Notion-like docs, AI image & video generation, email, calendar & terminal…. The licence is AGPL-3.0.

When your agent uses it

  • Scenarios: summarize a PDF
  • Fill an AcroForm
  • Render pages as images
  • Add a watermark

Example prompts

  • “summarize this PDF”
  • “fill out this PDF form”
  • “merge these PDFs”
  • “/pdf-skill”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Read: PdfInspect is the only entry point
  2. Write: JsSandbox + pdf-lib / pdfkit
  3. OCR (scanned PDFs)
  4. Format Conversion
  5. Common Error Fallbacks

What it can do on your machine

Read from SKILL.md and the folder at commit f7eccf6. 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 javascript).

    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

PDF Skill loads about 2k tokens when it runs. Until then it costs about 154 tokens; SKILL.md has 445 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~154
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 OpenLoaf/OpenLoaf at commit f7eccf6, republished under its AGPL-3.0 licence (© OpenLoaf). 445 words, ~1,999 tokens.

Download SKILL.mdSave it as .claude/skills/pdf-skill/SKILL.md (or your agent's skills folder).
name
pdf-skill
description
All-in-one PDF read / write / convert / OCR. Trigger scenarios: summarize a PDF, extract text or tables, fill an AcroForm, render pages as images, merge, split, add a watermark, rotate, encrypt/decrypt, create a new PDF (invoice / report / receipt), convert between PDF and docx/md/txt. Typical phrasings: "summarize this PDF", "fill out this PDF form", "merge these PDFs", "add a watermark to the PDF", "convert PDF to Word", "OCR this scan", "show me what page 3 of the PDF looks like". Load this skill whenever the user mentions a .pdf file, needs to produce a PDF, or wants to make any change to a PDF.

PDF Skill

Read with PdfInspect; all write / modify / create operations use JsSandbox to run Node scripts via pdf-lib / pdfkit / pdf-parse and similar pre-installed libraries; format conversion uses DocConvert; scanned PDFs go through CloudImageUnderstand.

Tool List

ToolResponsibilityRead-only
PdfInspectRead: summary / text / tables / form-fields / form-structure / images / annotations / renderYes
JsSandboxAll write operations: create new PDF, merge, watermark, rotate, fill forms, decrypt… implemented with pdf-lib / pdfkit codeNo
DocConvertFormat conversion: pdf ↔ docx / html / md / txt / xlsxNo
CloudImageUnderstandOCR entry point for scanned PDFs (cloud, consumes credits)No

Loading (two steps, both required):

  1. LoadSkill pdf-skill — only pulls this skill doc into context.
  2. ToolSearch(query: "select:PdfInspect,JsSandbox,DocConvert") — activates the tool schemas.

Read on a .pdf gives only a lightweight summary; any analysis / summarization / fill / edit / convert / OCR of a PDF must go through PdfInspect + JsSandbox.

1. Read: PdfInspect is the only entry point

When you don't know what the PDF looks like, run summary first:

PdfInspect { action: "summary", filePath: "…" }

Returns pageCount / fileSize / characterCount / hasForm / encryption / textType. Branch on textType:

textTypeNext step
extractablePdfInspect(text) — direct full-text extraction
scanned / cid-encodedPdfInspect(render, pageRange) → CloudImageUnderstand on each PNG for OCR
isEncrypted: trueDecrypt with JsSandbox + pdf-lib, or call PdfInspect(password)

Large PDFs must pass pageRange (e.g. "1-5"), otherwise output will be truncated.

AcroForm forms: call PdfInspect(form-fields) to get checkedValue / radioOptions before filling.

2. Write: JsSandbox + pdf-lib / pdfkit

Prefer pdf-lib (edit existing PDFs / merge / watermark / rotate / fill forms / decrypt); use pdfkit from scratch when you need complex layouts (vector + text + images).

2.1 Demo: Create an invoice PDF from scratch (pdfkit)
js
import PDFDocument from 'pdfkit'
import fs from 'node:fs'

const doc = new PDFDocument({ size: 'A4', margin: 48 })
doc.pipe(fs.createWriteStream('invoice.pdf'))

doc.fontSize(22).text('INVOICE', { align: 'right' })
doc.moveDown()
doc.fontSize(10).text('Acme Corp', { align: 'right' })
doc.text('Invoice #2026-042   Date: 2026-04-20', { align: 'right' })
doc.moveDown()

// Simple table
const rows = [
  ['Widget', 1, 50.00],
  ['Gadget', 2, 30.00],
]
doc.fontSize(12).text('Description     Qty     Unit     Total')
doc.moveTo(48, doc.y).lineTo(547, doc.y).stroke()
let total = 0
for (const [name, qty, unit] of rows) {
  const line = qty * unit
  total += line
  doc.text(`${name.padEnd(14)} ${qty}       $${unit.toFixed(2)}   $${line.toFixed(2)}`)
}
doc.moveDown().fontSize(14).text(`Total: $${total.toFixed(2)}`, { align: 'right' })

doc.end()
await new Promise(r => doc.on('end', r))
console.log('invoice.pdf written')

CJK note: pdfkit's default fonts have no CJK glyphs. For Chinese output, call doc.registerFont('cn', '/path/to/NotoSansCJK.ttf') first, then doc.font('cn'). System fallback fonts are not guaranteed to cover CJK.

Show full SKILL.md (167 more words)Show less
2.2 Demo: Add a CONFIDENTIAL watermark to an existing PDF (pdf-lib)
js
import { PDFDocument, rgb, degrees, StandardFonts } from 'pdf-lib'
import fs from 'node:fs/promises'

const src = await fs.readFile(process.argv[2] ?? 'input.pdf')
const pdf = await PDFDocument.load(src)
const font = await pdf.embedFont(StandardFonts.HelveticaBold)

for (const page of pdf.getPages()) {
  const { width, height } = page.getSize()
  page.drawText('CONFIDENTIAL', {
    x: width / 2 - 140,
    y: height / 2,
    size: 64,
    font,
    color: rgb(0.9, 0.1, 0.1),
    opacity: 0.25,
    rotate: degrees(-30),
  })
}

const out = await pdf.save()
await fs.writeFile('watermarked.pdf', out)
console.log(`watermarked ${pdf.getPageCount()} pages`)
2.3 Demo: Merge PDFs (pdf-lib)
js
import { PDFDocument } from 'pdf-lib'
import fs from 'node:fs/promises'

const merged = await PDFDocument.create()
for (const p of ['a.pdf', 'b.pdf', 'c.pdf']) {
  const src = await PDFDocument.load(await fs.readFile(p))
  const pages = await merged.copyPages(src, src.getPageIndices())
  pages.forEach(pg => merged.addPage(pg))
}
await fs.writeFile('merged.pdf', await merged.save())
console.log(`merged → ${merged.getPageCount()} pages`)
2.4 Demo: Fill an AcroForm (run PdfInspect(form-fields) first to get checkedValue)
js
import { PDFDocument } from 'pdf-lib'
import fs from 'node:fs/promises'

const pdf = await PDFDocument.load(await fs.readFile('form.pdf'))
const form = pdf.getForm()
form.getTextField('full_name').setText('John Smith')
form.getCheckBox('agree').check()          // use setValue('Y') if PdfInspect gives checkedValue='Y'
form.getRadioGroup('gender').select('M')
// form.flatten()  // call this to lock the form
await fs.writeFile('filled.pdf', await pdf.save())
console.log('form filled')
2.5 Demo: Decrypt / rotate / extract pages
js
// Decrypt
import { PDFDocument } from 'pdf-lib'
const pdf = await PDFDocument.load(buf, { password: 'secret', ignoreEncryption: false })
await fs.writeFile('unlocked.pdf', await pdf.save())

// Rotate page 1 by 90°
pdf.getPage(0).setRotation(degrees(90))

// Extract pages 3 and 5 into a new PDF
const out = await PDFDocument.create()
const [p3, p5] = await out.copyPages(pdf, [2, 4])
out.addPage(p3); out.addPage(p5)

3. OCR (scanned PDFs)

PdfInspect(summary)              // textType == 'scanned'
PdfInspect(render, pageRange)    // yields [<asset>/render-p1.png, ...]
CloudImageUnderstand(image=<each png>, question='Extract all text accurately')

4. Format Conversion

DocConvert(from="pdf", to="docx", sourcePath="…")   # PDF → Word for editing
DocConvert(from="docx", to="pdf", sourcePath="…")   # Word → PDF for distribution

DocConvert is faster and better at preserving layout than JsSandbox + pdf-lib; prefer it for format conversion.

5. Common Error Fallbacks

SymptomCauseFix
Garbled / square characters with pdfkitDefault font has no CJK glyphsCall registerFont('cn', '/path/to/NotoSansCJK.ttf') first
pdf-lib throws EncryptedPDFError on loadFile is encryptedPDFDocument.load(buf, { password: '…' })
Watermark uneven across pagesPages have different sizesLoop page.getSize() and compute x/y per page
Merged PDF has font rendering differencesSource PDFs have incomplete embedded fontsRewrite with pdf-lib's useObjectStreams: false
TypeError: Cannot read properties of undefined (reading 'save')pdfkit has no doc.save() / doc.restore() (those are Canvas 2D APIs)Switch colors / sizes directly via doc.fillColor() / doc.fontSize() — no save/restore stack needed. Finish the document with doc.pipe(fs.createWriteStream(...)); doc.end()

To patch a script: JsSandbox(action="edit-and-run", scriptPath=<previous path>, edits=[{find,replace}]) — only pass the diff.

© OpenLoaf, AGPL-3.0. 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 apps/server/src/ai/builtin-skills/pdf/en of OpenLoaf/OpenLoaf.

Open the folder on GitHubat commit f7eccf6

Compare with similar skills

PDF Skill 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.

PDF Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PDF Skill this skillOpenLoaf/OpenLoaf108—~2kAutomated safety check: PassAGPL-3.0
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Markitdownjimmc414/Kosmos5942 repos~1.7kAutomated safety check: PassNone
Code2mediatsingliuwin/autoclaw283—~956Automated safety check: PassMIT
Doc Cleanernotoriouslab/doc-cleaner309—~712Automated safety check: PassMIT
MineruNebutra/MinerU-Skill122—~504Automated safety check: PassMIT

Similar skills

  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes

  • Markitdown

    jimmc414/Kosmos

    Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.

    594 GitHub starsUsed in 2 repos~1.7k tokens
    Documents & OfficeAuto-check passed

  • Code2media

    tsingliuwin/autoclaw

    Universal media renderer with no fixed template — any custom layout, size or style becomes pixel-perfect images (PNG/JPEG/WebP), vector SVG, paged PDFs or animations (WebP/GIF).

    283 GitHub stars~956 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed

  • Doc Cleaner

    notoriouslab/doc-cleaner

    Convert PDF, DOCX, XLSX, and text files to clean, structured Markdown.

    309 GitHub stars~712 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed

  • Mineru

    Nebutra/MinerU-Skill

    An AI-Native skill for parsing PDF / Office / image files into Markdown with MinerU — a fast, zero-config document parser for AI agents.

    122 GitHub stars~504 tokensUpdated 14 days ago
    Documents & OfficeAuto-check passed

  • Office Documents

    ZS520L/HanakoPro

    A skill your agent uses when the user asks to open, read, inspect, understand, summarize, analyze, extract tables/text from, modify, update, repair, split, merge, rotate, or convert information from…

    102 GitHub stars~1.6k tokensUpdated 4 mo ago
    Documents & OfficeAuto-check passed

More from OpenLoaf/OpenLoaf

All 33 skills in this repo

  • Agent Orchestration Skill

    OpenLoaf/OpenLoaf

    Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed

  • Browser Ops Skill

    OpenLoaf/OpenLoaf

    Triggered when the user asks for page-level interaction with a specific webpage: login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or…

    108 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed

  • Canvas Ops Skill

    OpenLoaf/OpenLoaf

    Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership.

    108 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed

  • Word Document Read, Write and Convert

    OpenLoaf/OpenLoaf

    Reads, edits, converts and reviews Word documents through three dedicated tools, covering tracked changes, comments, tables, images and format conversion.

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed

  • Email Operations

    OpenLoaf/OpenLoaf

    Handles a real email account through query and mutate tools: check the inbox, read, search, reply, forward, compose and organize, with sending always confirmed first.

    108 GitHub stars~1.8k tokensUpdated 4 mo ago
    Auto-check passed

  • macOS Desktop Control

    OpenLoaf/OpenLoaf

    Guides an agent to operate native macOS apps by surveying an app first, acting through intents, menus or keystrokes, and verifying each step, in OpenLoaf Desktop only.

    108 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed

Works with

Categories

Questions about PDF Skill

What does PDF Skill do?

All-in-one PDF read / write / convert / OCR. An agent skill from OpenLoaf/OpenLoaf. PDF Skill is an agent skill from OpenLoaf/OpenLoaf. All-in-one PDF read / write / convert / OCR.

When should I use PDF Skill?

PDF Skill fits situations like: scenarios: summarize a PDF; fill an AcroForm; render pages as images; add a watermark.

How do I install PDF Skill in Claude Code?

Run `npx skills add OpenLoaf/OpenLoaf --skill pdf-skill -a claude-code`. Or copy the skill folder (apps/server/src/ai/builtin-skills/pdf/en in OpenLoaf/OpenLoaf) into .claude/skills/pdf-skill in your project. Claude Code loads it when a task matches its description.

How do I install PDF Skill in Codex?

Run `npx skills add OpenLoaf/OpenLoaf --skill pdf-skill -a codex`. Or copy the skill folder (apps/server/src/ai/builtin-skills/pdf/en in OpenLoaf/OpenLoaf) into .agents/skills/pdf-skill in your project. Codex loads it when a task matches its description.

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

What does PDF Skill need to run?

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

Does PDF Skill 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 PDF Skill 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 PDF Skill use?

PDF Skill is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PDF Skill use?

About 2k tokens (SKILL.md is roughly 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 PDF Skill?

Skills that share tags, products or a category with PDF Skill: Markitdown (ImCa0/just-laws, 781 stars), Markitdown (jimmc414/Kosmos, 594 stars), Code2media (tsingliuwin/autoclaw, 283 stars) and Doc Cleaner (notoriouslab/doc-cleaner, 309 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PDF Skill?

OpenLoaf (a GitHub organization) maintains it in OpenLoaf/OpenLoaf, which has 108 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on May 14, 2026.

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