Skill UI

This guide helps scholars assess if their social, economic, or cultural history manuscript aligns with the rigorous, problem-driven standards of Past & Present. It instructs authors on framing their research around a core "big question"—a genuine historical problem—ensuring comparative significance, adhering to historiographical expectations, and meeting specific academic standards like double-blind review and Chicago style.

This skill processes raw mentions of conditions and diagnoses extracted from clinical notes. It performs synonym deduplication, filters out negated or hypothetical mentions, and assigns a structured clinical status (active, resolved, or historical). The output is a clean, reconciled problem list, structured for USCDI Problem or FHIR Condition elements.

This skill enhances raw clinical entity recognition by assigning three critical axes: Negation, Temporality, and Uncertainty (ConText). It determines the clinical status of a mention (e.g., affirmed, negated, historical, or uncertain), ensuring that basic NER results are transformed into clinically faithful assertions before grounding to standards like FHIR. Essential for accurate problem list generation and differential diagnosis support.

This technique segments unstructured clinical documents (such as HPI, PMH, and A&P sections) into contextually rich, canonical chunks. This is crucial for improving the precision of downstream NLP tasks like Named Entity Recognition (NER) and de-identification. By identifying and normalizing headers and mapping them to LOINC codes, the system ensures that the source context (e.g., historical vs. active) is maintained, leading to significantly more accurate results.

This robust methodology guides users to strip away assumed constraints, industry conventions, or historical precedents. By isolating only the fundamental, independently supported primitives (like physics, core math, or measured needs), it enables the rebuilding of the simplest, most robust solution that genuinely satisfies real-world constraints, bypassing artificial or arbitrary limitations.

A writing skill inspired by Dangnian Mingyue, author of 'Those Stories of the Ming Dynasty'. It teaches how to make history engaging and accessible using humor, modern language, psychological insight into historical figures, and vivid power-struggle narratives. Ideal for writers, educators, and content creators who want to humanize historical events and bring the past to life for general audiences.

A comprehensive guide to adopting the narrative style of top-tier AI and technology media. Learn how to move beyond surface-level reporting (What/How) by focusing on the founder's underlying 'Why' (motive). This framework utilizes historical depth, non-consensus insights, and a founder-companion perspective to create authoritative, deep-dive articles on AI, entrepreneurship, and future technology trends.

A comprehensive guide to developing gothic, mysterious, and historically reconstructed narratives in the style of Li Bihua. This skill focuses on themes of fate, intense love, tragedy, and female obsession, guiding users through the unique 'Qi Qing' (gothic/supernatural) genre, far beyond typical romance.

A rigorous, verification-first methodology for citing facts from the post-WWII international military tribunals, including IMT, NMT, and IMTFE. This guide teaches users how to distinguish between legal instruments (e.g., London Charter vs. Tokyo Charter) and verifies claims against authoritative historical archives (e.g., Avalon Project, Blue/Green Series) to maintain the highest standard of academic accuracy in international criminal law research.

Mine ancient French legal sources from Gallica (BNF) via stable APIs: parliamentary debates since 1871, old case reports (Sirey, Dalloz), doctrine, theses, official texts, and legal journals. Retrieve OCR extracts, page numbers, and image links for verification. Ideal for historical legal research and genealogy of laws before modern databases.

An expert agent designed to collect critical data assets—including metadata, data lineage, and query logs—from any data warehouse platform. It uses the push ingestion API to send this data directly to Monte Carlo. This method is essential for integrating data sources that cannot be reliably covered by standard pull collectors, such as custom lineage paths or historical query logs.

OrcaReplay enables agents to query past execution recordings instead of relying on memory. It supports replaying or forking previous agent runs to investigate why specific actions occurred or to reproduce failures. This skill ensures accurate debugging by reading traces directly, distinguishing between recorded evidence and inferred data, and safely re-executing commands within isolated environments to verify historical behavior.