paper-deep-reading-skill
Eroticoo/paper-deep-reading-skill
This skill provides an automated workflow to read local academic PDF papers in depth, extract key sections and figures, and generate a structured Markdown report backed by visual snapshots. It handles everything from initial folder setup and text extraction to precision cropping of theorems and experimental evidence.
48 2No licenseUpdated 2026-04-21
61
GoodOverview
Designed to empower researchers and students, the paper-deep-reading skill orchestrates Python utilities to analyze academic papers end-to-end. It systematically probes PDFs, extracts text layers or OCR fallbacks, and captures source-grounded snapshots of titles, technical cores (such as formal proofs, system models, and algorithms), and experimental evidence. The resulting Markdown report follows a rigorous structure—including audience-specific recommendations for beginners, graduate students, and professors—and automatically formats images with public URLs for easy sharing or publishing.
Capabilities
- ▸PDF text extraction and structure probing
- ▸Automated precision snapshot capture for academic figures, tables, and theorems
- ▸LaTeX equation transcription and formatting
- ▸Customizable Markdown report generation with academic metadata
- ▸Image URL prefix rewriting for public asset hosting and validation
Best for
Generating comprehensive review reports for academic research papers, Extracting and explaining complex mathematical theorems and system models from PDFs, Creating screenshot-backed summaries tailored for different academic audiences (students vs. professors)
Works with
Codex
Evoa Score breakdown= Σ (score × weight)
61Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%70 → +10.5
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%38 → +4.6
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%43 → +3.4
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%25 → +1.3
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total71.3 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Executes local Python scripts for PDF processing and text extraction. Users should ensure that input PDF files are trusted and scanned for malicious content if sourced from untrusted locations.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.