Borrowing it
Nothing to install: this file belongs to u9401066/med-paper-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/u9401066/med-paper-assistant/master/.claude/skills/pdf-asset-extractor/SKILL.mdgit clone --depth 1 https://github.com/u9401066/med-paper-assistantWrote 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/u9401066/med-paper-assistant/pdf-asset-extractor)<a href="https://agentmods.dev/skills/u9401066/med-paper-assistant/pdf-asset-extractor"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/pdf-asset-extractor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/u9401066/med-paper-assistant/pdf-asset-extractor"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/pdf-asset-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00084 | $0.03390 |
| Opus 5 | $0.00042 | $0.01695 |
| Sonnet 5 | $0.00017 | $0.00678 |
| Haiku 4.5 | $0.00008 | $0.00339 |
Grade A, and why
pdf-asset-extractor 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 11d 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- pdf-asset-extractor — 100% identical, 129 lines differ
- pdf-asset-extractor — 100% identical, 129 lines differ
- pdf-asset-extractor — 100% identical, 129 lines differ
- pdf-asset-extractor — 100% identical, 129 lines differ
How it starts
The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Asset Extractor (MCP Tools)
描述
將 PDF 文件分解為可查詢的資產（圖片、表格、章節），並建立跨文獻知識圖譜。
核心能力：
- 📄 PDF 匯入 → 雙引擎（PyMuPDF 快速 / Marker 高精度）自動提取圖片、表格、文字
- 🖼️ 圖片提取 → 以 base64 返回，支援 Vision AI 分析
- 📊 表格提取 → 轉換為 Markdown 格式
- 🧭 章節導航 → 動態層級 Section Tree（支援任意深度）
- 🔍 知識圖譜 → 跨文獻關係查詢 (LightRAG)
- 📈 圖譜視覺化 → 導出 Mermaid 圖表
觸發條件
- 「ingest PDF」、「匯入 PDF」、「解析文件」、「分析論文」
- 「看 manifest」、「文件結構」、「有什麼圖表」
- 「取得圖片」、「fetch figure」、「拿表格」、「extract」
- 「知識圖譜」、「cross-document」、「比較文獻」、「RAG」
- 「視覺化圖譜」、「export graph」、「mermaid」
- 「章節」、「section」、「導航」、「樹狀結構」
🔧 雙引擎策略
| 引擎 | 強項 | 弱項 | 觸發方式 |
|---|---|---|---|
| PyMuPDF (預設) | 快速、輕量 (~50MB) | 版面分析精度較低 | ingest_documents() |
| Marker (高精度) | 精確 bbox、section hierarchy | 重模型 (~1GB)、較慢 | ingest_documents(use_marker=True) 或 parse_pdf_structure() |
Marker 產出額外資料
blocks.json— 結構化區塊（含 bbox、polygon、section_hierarchy）- 支援 Section Navigation 動態層級導航
⚠️ 重要警告
🖼️ 圖片 Context 限制
Base64 圖片非常大，一次只處理一張！
- 一張圖片 ≈ 200KB base64 ≈ ~270K tokens
- 對話 context 有限，多張圖片會快速耗盡
- 建議流程：先
inspect_document_manifest→ 選定目標圖 → 一次 fetch 一張
👁️ 視覺能力提醒
如果 AI 有視覺能力（Vision），可直接分析返回的圖片 如果是純文字 AI，應誠實告知無法分析圖片內容
📸 圖片 ID 命名規則
系統以
fig_{page}_{index}命名，非解析圖說文字 需手動對照 manifest 頁碼與實際 Figure 編號
🔧 可用 MCP Tools
文件處理
| Tool | 用途 | 參數 |
|---|---|---|
ingest_documents |
匯入 PDF（ETL 流程） | file_paths: list[str], async_mode: bool, use_marker: bool |
parse_pdf_structure |
Marker 結構化解析（單檔） | file_path: str |
get_job_status |
查詢 ETL 進度 | job_id: str |
list_jobs |
列出所有工作 | active_only: bool |
cancel_job |
取消 ETL 工作 | job_id: str |
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.
- 11d ago First seen · 391 lines · 84 tokens per session scan A a13fff95f85c
pdf-asset-extractor is a skill published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 10d ago), licensed Apache-2.0. It adds 84 tokens to every session and 3,390 once invoked, about $0.0004 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
read
Read PDF page by page with structured output — key arguments, terms glossary, thesis connections. Use when reading academic papers, books, or articles.
release-governance
Use when preparing, auditing, releasing, PDF-hardening, or rebuttal-hardening academic manuscripts, datasets, artifacts, reviewer packets, or claim registers involving multiple refs, local assets, human labels, agent-assisted drafts, wide tables, figure provenance, submission PDFs, or evidence-boundary checks.
proposal-import
Import an existing proposal (usually PDF) into the standard single-file format — extract text and references, strip personal data, mark gaps. Use when the user has a draft from Word, LaTeX, Overleaf or another tool, pastes the text of an older proposal, or wants to carry existing work over and continue it here.
proposal-publish
Build a PDF (or docx fallback) from a proposal file via pandoc — compact layout, typst-first, with install guidance when tools are missing. Also offers a stripped hand-in export, and hands over to a workspace build script where one exists. Use when the user wants a PDF or something to email, print or hand to their…
book-to-skill
Book-to-skill takes technical books, documentation, or other long-form sources and converts them into a skill made of a core definition plus per-chapter files, a glossary, and cheatsheets, so an agent can load only the relevant section instead of the whole document. It supports PDF, EPUB, DOCX, HTML, and several other…
tikz-figure-review
Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered…