hallucination-detector
Detect potential hallucinations by tracing claims back to source materials and validating whether fetched information was actually used to support conclusions. Trigger with /hallucination-check
Detect potential hallucinations by tracing claims back to source materials and validating whether fetched information was actually used to support conclusions. Trigger with /hallucination-check
Batch generation of Hollywood comparable titles using GPT-4o. This skill should be used for generating comps on multiple titles at once, filling gaps in catalog coverage, or running overnight batch processing.
Standard collection development workflow for discovering, evaluating, and acquiring scholarly materials for the library collection
Expert academic paper review including summary, methodology critique, and practical implications
Search and retrieve academic literature from multiple databases. LOAD THIS SKILL WHEN: User says "搜尋文獻", "search literature", "find papers", "PubMed", "學術搜尋" | needs to find research articles | starting literature review. CAPABILITIES: PubMed search, MeSH term expansion, citation metrics, batch retrieval.
Retrieve and summarize current international and Singapore news stories with headlines, brief context, and source links in a professional executive format. Use when you need a quick daily news briefing with verified sources.
고고학 발굴조사보고서 고찰 자동 작성 파이프라인. "고찰 작성해줘" 한 번의 명령으로 완료된 보고서+논문+주변유적 보고서를 분석하여 문화재청 표준양식 고찰을 생성. 폴더1(주보고서), 폴더2(논문), 폴더3(비교유적)을 자동 분석. Use for automated archaeological excavation report discussion writing pipeline: analyzes main report + papers + comparison sites to generate discussion following Korean Cultural Heritage Administration standards. One command processes all folders.
Structure and style guidance for law review articles
This skill should be used when the user asks to "write a law review article", "draft a legal paper", "edit legal writing", "review my legal article", "write for a journal", "format footnotes", or needs guidance on academic legal writing. Based on Volokh's "Academic Legal Writing" with law-review-specific structure and evidence handling.
Search for academic papers using natural language queries via Asta's semantic search across 225M+ papers. Use when finding research papers, exploring literature, or discovering relevant academic work on any scientific topic.
Detect and assess publication bias in meta-analysis using funnel plots, Egger's test, trim-and-fill, and selection models. Use when users need to evaluate whether missing studies might affect their conclusions.
Codexを使った多角的コードレビュー。セキュリティ、パフォーマンス、保守性、設計の4観点で並列分析。 Use for: "codexでレビュー", "多角的レビュー", "Codexに見てもらって", "別視点でレビュー"
Comprehensive arXiv paper search and retrieval tool with keyword search, category filtering, date range filtering, and daily paper fetching capabilities. Use for "搜索arXiv论文", "获取最新论文", "arXiv文献调研", "生成论文报告", "查找cs.AI相关论文".
Fetch and summarize latest articles from RSS feeds. Creates notes with article summaries as bullet points. Use to catch up on blogs without reading everything. Triggers on "rss catchup", "blog catchup", "check feeds", "summarize articles".
Autonomous prior art search and analysis agent. Searches multiple databases, analyzes references, creates claim charts, and assesses patentability impact.
Generate structured literature reviews on research topics by synthesizing findings from multiple papers. Use when conducting research surveys, identifying themes and gaps, or preparing academic writing on any scientific topic.
This skill should be used when the user asks to "update PubMed links", "check reference links", "find PubMed URLs", "download fulltext papers", or discusses PubMed/Medline literature search and reference management. Provides systematic approach for querying PubMed database and updating reference lists with accurate links.
Use Elsevier APIs (Scopus search / abstract / author / trends / institution / open access) via simple CLI scripts.
Citation formatting rules for law review articles using The Bluebook (21st ed.) academic style
This skill should be used when evaluating the quality of book chapters, lessons, or educational content. It provides a systematic 6-category rubric with weighted scoring (Technical Accuracy 30%, Pedagogical Effectiveness 25%, Writing Quality 20%, Structure & Organization 15%, AI-First Teaching 10%, Constitution Compliance Pass/Fail) and multi-tier assessment (Excellent/Good/Needs Work/Insufficient). Use this during iterative drafting, after content completion, on-demand review requests, or before validation phases.
Extract and validate citations with Jaccard overlap calculation. Ensures all claims have verifiable source evidence with ≥0.7 alignment threshold.