Borrowing it
Nothing to install: this file belongs to Guo-Chenxu/paper-agent. 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/Guo-Chenxu/paper-agent/main/.claude/skills/pdf-annotation-extractor/SKILL.mdgit clone --depth 1 https://github.com/Guo-Chenxu/paper-agentWrote 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/guo-chenxu/paper-agent/pdf-annotation-extractor)<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/pdf-annotation-extractor"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/pdf-annotation-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/guo-chenxu/paper-agent/pdf-annotation-extractor"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/pdf-annotation-extractor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.01070 |
| Opus 5 | $0.00023 | $0.00535 |
| Sonnet 5 | $0.00009 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
pdf-annotation-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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Annotation Extractor
Goal
Read a PDF and extract:
- The PDF annotation list, including highlight, underline, strikeout, sticky note, text comment, and similar annotations.
- The source text snippet corresponding to each annotation.
- A surrounding context excerpt for every annotation.
- The annotation author, creation/modification time, and comment content.
Every annotation entry must include context: the sentence-level page text located by the annotation coordinates, starting after the previous period (. or 。) and ending at the next period. Markdown must show a Context section for every annotation even when no extractable context is found. Markdown is the default output because it is easy to read manually. Use JSON when downstream programmatic processing is needed.
When To Use
- The user asks to "extract PDF annotations", "export highlights", "organize paper comments", or read comments/notes/annotations.
- The user provides an academic-paper PDF and wants a new file containing annotations plus their corresponding source text snippets.
- The user needs to convert highlights/comments from a PDF reader into Markdown or JSON.
Requirements
The script depends on PyMuPDF (fitz). If the dependency is missing, install it first:
python -m pip install pymupdf
Quick Reference
| Need | Use |
|---|---|
| Human review | Markdown output |
| Programmatic processing | JSON output |
| Per-annotation sentence context | context field / **Context:** section, located by annotation coordinates |
| Highlighted or underlined text | selected_text field / **Selected Text:** section |
Basic Workflow
Step 1: Choose output format
Prefer Markdown when the output is for reading, review, and copying.
python .claude/skills/pdf-annotation-extractor/scripts/extract_pdf_annotations.py \
./paper-annotation.pdf \
--output ./paper-annotation_annotations.md
Use JSON when structured data is needed:
python .claude/skills/pdf-annotation-extractor/scripts/extract_pdf_annotations.py \
./paper-annotation.pdf \
--format json \
--output ./paper-annotation_annotations.json
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.
- 9d ago First seen · 130 lines · 47 tokens per session scan A 27c282c2acaa
pdf-annotation-extractor is a skill published in the GitHub repository Guo-Chenxu/paper-agent (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,070 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
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.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.