Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ai4creativitylab/index.skill/extract-pdfnpx skills add AI4CreativityLab/Index.skill --skill extract-pdfgit clone --depth 1 https://github.com/AI4CreativityLab/Index.skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ai4creativitylab/index.skill/extract-pdf)<a href="https://agentmods.dev/skills/ai4creativitylab/index.skill/extract-pdf"><img src="https://agentmods.dev/badge/skills/ai4creativitylab/index.skill/extract-pdf.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00125 | $0.03878 |
| Opus 5 | $0.00063 | $0.01939 |
| Sonnet 5 | $0.00025 | $0.00776 |
| Haiku 4.5 | $0.00013 | $0.00388 |
Grade A, and why
extract-pdf scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the PDF Extractor. Your job is to turn any PDF into a structured workspace that the calling agent (Claude) can read directly — markdown files for the textual content (with tables, headings, and lists preserved), PNG files for the visual content. There is no separate vision API in the loop: Claude itself reads the rendered page images with its built-in Read tool.
Why this skill exists
Naive PDF text extraction loses figures, tables, formulas, layout, and anything in scanned pages. The classic workaround is to send each page image to an external vision model, which adds API keys, cost, and rate limiting. Heavy ML pipelines (Marker, Nougat, MinerU, Docling) need GBs of model weights and a GPU. Claude is already multimodal, so the right move is to compose lightweight tools and let Claude handle anything that needs vision:
- Render each page to PNG locally with PyMuPDF. No system dependencies, no poppler, no ML.
- Extract structured Markdown with
pymupdf4llm— the official LLM-targeted PDF→Markdown extractor from the PyMuPDF maintainers. It detects tables, headings, lists, and code blocks and preserves them as proper Markdown so Claude can read them at a glance instead of squinting at column-aligned spaces. - Run pdfminer.six in parallel on the same page set as a complementary plain-text extractor. PyMuPDF and pdfminer use different layout-analysis algorithms, and when one mangles a page (ligatures, columns, vertical text, weird encodings) the other often nails it. Disagreement between the two is itself a useful signal.
- Hand all of it to Claude as files it can
Readon demand. For math, scanned pages, or figures where text extraction can't be exact, the agent reads the page image directly — no extra OCR step.
This makes PDF analysis a one-command operation that any future skill or task can reuse.
When to use
Trigger this skill whenever a task involves a PDF and any of:
- "summarize / read / analyze / explain this PDF"
- "extract text / tables / figures from a PDF"
- "what does the chart on page 4 show?"
- "convert this PDF to something I can work with / to markdown"
- the PDF has scanned pages, math, diagrams, or complex layout
- another skill (e.g.
index-noteforpaper/book) needs structured PDF content
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 249 lines · 125 tokens per session scan A b4fe84c1bd91
extract-pdf is a skill published in the GitHub repository AI4CreativityLab/Index.skill (77 stars, last pushed 2mo ago), licensed MIT. It adds 125 tokens to every session and 3,878 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
paddleocr-doc-parsing
Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表…
paper-reader
Use when user asks to "read paper", "analyze paper", "summarize paper", "读论文", "分析文献", "帮我看一下这篇paper", "论文笔记", or provides a PDF file that appears to be an academic paper. Specialized for CV/DL papers. Also supports Zotero integration: "读一下这篇论文 ...", "快速看一下这篇论文 ...", "批判性分析这篇论文 ...", "读一下 Zotero 里的 XXX", "批量读一下 Zotero…
citra
Skill "citra" from SylphxAI/pdf-reader-mcp, covering citra — pdf evidence for agents, install, or, tools and sdk.
graphic-ebook
Creates professionally designed B2B SaaS e-books in HTML + CSS, exported as print-ready PDF. 3–10 pages, 9 style presets, 11 page layout types. Trigger when user says "create an ebook", "design a lead magnet", "make a PDF guide", "build a gated content piece", "write a B2B ebook", "design a white paper", "create a…
pdf-fill
Fill PDF form fields from a data dict.