Product strategist for scoring and ranking feature ideas using RICE/ICE prioritization frameworks, connecting features to business KPIs (retention, growth, revenue), and identifying quick wins vs strategic bets. Use when evaluating product features, prioritizing roadmap items, analyzing feature requests, or making product investment decisions.
Use this skill when evaluating research projects, POCs, experiments, or prototypes for production readiness. Provides the "What Did We Prove?" framework, production readiness checklist, and gap analysis matrix for systematic research evaluation.
Autonomous Freedom to Operate analysis agent. Identifies blocking patents, assesses infringement risk, and recommends mitigation strategies for product commercialization.
Amazon Bedrock Automated Reasoning for mathematical verification of AI responses against formal policy rules with up to 99% accuracy. Use when validating healthcare protocols, financial compliance, legal regulations, insurance policies, or any domain requiring deterministic verification of AI-generated content.
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).
Assess technical, financial, operational, and organizational feasibility of learning projects including resource requirements, budget, timeline, and risk analysis. Use when evaluating project viability before committing resources. Activates on "feasibility study", "project viability", "resource planning", or "can we do this".
Align training to regulatory compliance requirements including OSHA, FDA, HIPAA, SOX, GDPR, and industry-specific regulations. Verify compliance coverage and identify gaps. Use for mandated compliance training. Activates on "OSHA", "compliance training", "regulatory requirements", or "mandated training".
Expert technical document reviewer. PROACTIVELY review ADRs, Design Docs, and RFCs for quality, completeness, and principle alignment after creating or updating technical documents.
Framework for reasoning about competing hypotheses when analyzing correlated failures. Use when observing patterns across multiple entities and need to determine probable cause with quantified confidence scoring.
Merges medical analysis and cross-system insights into a cohesive, prioritized, patient-facing narrative while preserving all rich content from the agentic analysis.
Leverages the multiple CLIs including PEX, pdf-search, hge, researcher, limitless, pieces, screenapp and more, to extract all relevant LOs across both CICM and ANZCA PEX exams, cross reference them with past SAQ questions, extract examiner comments, cross reference this with recommended textbooks via pdf-search, generate a hypergraph using hge, validate insights with researcher, evaluate against pkm using limitless and pieces, and look for additional context to add polish with screenapp and others. Then leverages the PEX and SAQ skill, as well as the metaskills that exist in .claudeate a scaffolding for a modular, programmatic, state of the art skill that integrates quantitative physiological parameters using the qp skill, teleologically grounded framing using the physiology-style and telos skill and follows all of the principles of the code, mega, and agency skills. Finally it should be recursively optimised with the abduct, critique and refactoring agent skillls. Ergo, this skill makes SOTA PEX LO skills.
Synthesizes lesion data and historical cases into a comprehensive risk profile using WebLLM SmolLM2
Autonomous patent examination agent. Simulates USPTO examination by analyzing applications for compliance with 35 U.S.C. §§ 101, 102, 103, 112 and identifying potential office action issues.
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.
Comprehensive veterinary medicine knowledge for clinical tools including drug dosages, diagnosis codes, vaccine schedules, lab reference ranges, and species-specific guidance. Use when building or improving clinical features like dosage calculators, diagnosis search, vaccine tracking, or lab result interpretation.
指定薬剤・適応・国・データベース特性に基づき、PubMed/Web検索で先行RWD研究・RCT・ガイドラインを調査し、 エビデンスランドスケープを要約する。JMDC/MDV等クレームDBとの差別化観点を必ず含める。
Calculate final scores combining efficacy and safety
Phase 6 of MIP pipeline - Verify all quotes against source text, validate quantitative claims, and generate the appendix with sample annotations.
Detect legacy patterns and guide compatibility decisions.
Polish NFZ drug programme B.56 for prostate cancer (ICD-10 C61). Use when helping clinicians with patient qualification, drug selection, dosing, monitoring, or follow-up for mHSPC, nmCRPC, or mCRPC treatment with apalutamide, darolutamide, enzalutamide, olaparib, niraparib+abiraterone, or talazoparib. Covers eligibility criteria, required diagnostics, treatment duration, and exclusion criteria.
3つの入力モード（薬剤起点/PICO起点/CQ起点）を統一フォーマットに変換し、 後続のRWD研究企画スキルが利用できる構造化データを生成する。
