Verify scientific claims, check calculations, validate experimental designs, and fact-check citations. Use when: (1) checking a claim against evidence, (2) validating statistical analyses, (3) verifying experimental reproducibility claims, (4) fact-checking references, (5) adversarial review of research. NOT for: generating new content (use scienceclaw-generation), simple QA (use scienceclaw-qa).
# Reproducibility Checklist — Open Science Best Practices
Medical device standards compliance verification skill for ISO 13485, ISO 14971, IEC 62304, IEC 60601, and related standards
Measurement System Analysis (MSA) skill for Gage R&R studies with variance component analysis and measurement adequacy assessment
Performs statistical analysis for A/B testing experiments
Test equipment integration for signal analysis (oscilloscope and logic analyzer)
Power consumption measurement and analysis expertise for embedded systems. Integrates with power analyzer tools to measure, profile, and optimize power consumption in battery-powered and energy-efficient designs.
Develop survey instruments, implement sampling strategies, optimize response rates, and manage multi-mode data collection
Develop, validate, and adapt measurement instruments including factor analysis, reliability testing, and cross-cultural validation
Nanoparticle Tracking Analysis skill for single-particle size and concentration measurements
Laboratory Information Management System skill for nanomaterial sample tracking and data management
LabVIEW instrument control skill for DAQ systems, hardware integration, and real-time data acquisition
Measurement System Analysis skill for Gage R&R studies with variance component analysis.
Specialized skill for air pollution control equipment selection and design including scrubbers, baghouses, ESPs, oxidizers, and BACT/LAER determination.
Automated test equipment control and data acquisition skill for hardware validation, with VISA/SCPI instrument communication, test sequence scripting, and measurement uncertainty analysis.
Assist in constructing type soundness proofs using progress and preservation theorems
Supply chain master data quality monitoring and improvement skill
Sensor and robot calibration using specialized robotics calibration tools
Weights & Biases integration skill for experiment tracking, hyperparameter sweeps, and artifact versioning.
MLflow integration skill for experiment tracking, model registry, and artifact management. Enables LLMs to log experiments, compare runs, manage model lifecycle, and retrieve artifacts through the MLflow API.
Guide for experiment tracking tool setup (MLflow, Weights & Biases, etc.), reproducibility assurance, model registry, and experiment comparison methodology. Use this skill for ML experiment management involving 'experiment tracking', 'MLflow', 'W&B', 'Weights and Biases', 'reproducibility', 'model registry', 'experiment comparison', 'hyperparameter logging', etc. Enhances the training-manager's experiment management capabilities. Note: model architecture design and feature engineering are outside this skill's scope.
Methodology for analyzing changes according to Semantic Versioning (SemVer) rules and determining the appropriate version number. Use this skill for 'SemVer analysis', 'version number determination', 'Breaking Change assessment', 'version bump decisions', and other version management tasks. Note: automatic git tag creation and CI/CD release execution are outside the scope of this skill.
코드베이스의 의존성 그래프를 분석하고 결합도/응집도를 정량적으로 측정하는 도구와 방법론. '의존성 분석', '결합도 측정', '순환 의존성', '모듈 결합도', '응집도 분석', '의존성 그래프', '커플링 분석' 등 코드 의존성 관련 분석에 이 스킬을 사용한다. legacy-analyzer와 refactoring-strategist의 의존성 분석 역량을 강화한다. 단, 전체 파이프라인 오케스트레이션은 이 스킬의 범위가 아니다.
MLflow, Weights & Biases 등 실험 추적 도구 설정, 재현성 보장, 모델 레지스트리, 실험 비교 방법론 가이드. '실험 추적', 'MLflow', 'W&B', 'Weights and Biases', '재현성', '모델 레지스트리', '실험 비교', '하이퍼파라미터 로깅' 등 ML 실험 관리 시 이 스킬을 사용한다. training-manager의 실험 관리 역량을 강화한다. 단, 모델 아키텍처 설계나 피처 엔지니어링은 이 스킬의 범위가 아니다.
