deepxiv_sdk
DeepXiv/deepxiv_sdk
This skill builds a structured markdown baseline table for any research topic by leveraging the DeepXiv SDK to search arXiv papers, screen metadata, inspect structures, and extract experimental datasets and scores.
919 45MITUpdated 2026-08-12
82
GreatOverview
The skill provides a rigorous, step-by-step methodology to transform a broad research topic query into a clean, comparative markdown baseline survey. Using the DeepXiv command-line tools (`deepxiv search`, `paper --brief`, `paper --head`, and `paper --section`), it guides agents to search for relevant literature, prioritize empirical papers with open-source code, inspect specific evaluation sections, and compile findings into a standardized format featuring tasks, benchmarks, and verified scores.
Capabilities
- ▸Executing targeted arXiv searches with date ranges and JSON output
- ▸Screening candidate papers using brief metadata summaries
- ▸Inspecting paper section headers to locate experiments and evaluations
- ▸Extracting datasets, metrics, and quantitative scores accurately without hallucinations
- ▸Generating formatted markdown summary tables containing source links and open-source statuses
Best for
Creating a state-of-the-art comparison table for academic literature reviews, Surveying recent benchmark scores and evaluation setups for specific machine learning topics, Filtering and identifying open-source implementations associated with recent research papers
Works with
Claude CodeCursorGitHub CopilotCodexChatGPTGemini CLIOpenCode
Evoa Score breakdown= Σ (score × weight)
82Task 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%100 → +15.0
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%75 → +6.0
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
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 total82.2 / 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
Interacts with external command-line tools and web/API services; ensure API keys and credentials are handled securely.
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.