transformers
Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing inference with pipelines, generating text, training sequence models, or working with BERT, GPT, T5, ViT, and other transformer architectures. Covers model loading, tokenization, training with Trainer API, text generation strategies, and task-specific patterns for classification, NER, QA, summarization, translation, and image tasks. (plugin:scientific-packages@claude-scientific-skills)
umap-learn
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
vaex
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that don't fit in memory.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
exploratory-data-analysis
EDA toolkit. Analyze CSV/Excel/JSON/Parquet files, statistical summaries, distributions, correlations, outliers, missing data, visualizations, markdown reports, for data profiling and insights.
hypothesis-generation
Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for scientific inquiry across domains.
peer-review
Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.
scholar-evaluation
Systematic framework for evaluating scholarly and research work based on the ScholarEval methodology. This skill should be used when assessing research papers, evaluating literature reviews, scoring research methodologies, analyzing scientific writing quality, or applying structured evaluation criteria to academic work. Provides comprehensive assessment across multiple dimensions including problem formulation, literature review, methodology, data collection, analysis, results interpretation, and scholarly writing quality.
scientific-brainstorming
Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.
scientific-critical-thinking
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
scientific-visualization
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.
scientific-writing
Write scientific manuscripts. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), abstracts, for research papers and journal submissions.
statistical-analysis
Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, APA reporting, for academic research.
secure-file-deletion
Securely delete files beyond recovery using overwriting techniques, ensuring data privacy and compliance with data protection regulations
software-architecture-expert
Software architecture design and consulting
brainstorming
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
auth-implementation-patterns
Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.
background-agents
|
biome-gritql
Creates and manages Biome GritQL custom lint rules to enforce coding patterns. Use when creating linter rules, enforcing code conventions, preventing anti-patterns, or when the user mentions Biome, GritQL, custom lint rules, or AST-based linting.
blog-post-writer
Transform brain dumps into polished blog posts in Nick Nisi's voice. Use when the user wants to write a blog post with scattered ideas, talking points, and conclusions that need organization into a cohesive narrative with Nick's conversational, authentic, and thoughtful tone.
dex-workflow
|
e2e-test-loop
|
gwt
|
prd-workflow
|
technical-svg-diagrams
Generate clean, minimal technical SVG diagrams in a consistent Cloudflare-inspired style. Use when creating architecture diagrams, flow diagrams, or component diagrams for blog posts and documentation.
unit-test-loop
|
marimo-inspect
|
marimo-serve
|
marimo-editor
|
obsi-moc-builder
특정 폴더(Single) 또는 하위 구조 전체(Recursive)를 분석하여 구조화된 MOC(Map of Content)를 자동 생성/갱신합니다.
agents-context-architect
프로젝트 구조를 분석하여 최적의 에이전트 컨텍스트 파일(AGENTS.md) 시스템을 구축합니다.
obsi-archive-project
완료된 프로젝트를 검증(Dependency Check), 정리(Cleanup) 후 안전하게 연도별 아카이브로 이동시킵니다.
biz-doc-generator
Word, Excel, PPT, PDF 등 기업용 문서를 생성하고, 결과를 docs/exports에 저장하며 임시파일을 자동 정리합니다.
data-analyst
Python 생태계(Jupyter, Pandas, Scikit-learn)를 활용하여 데이터에서 심층적인 인사이트를 도출하는 전문 분석 워크플로우입니다.
data-model-reporter
데이터 분석/머신러닝 노트북의 결과를 분석하여 표준화된 Model Card 보고서(Markdown)를 자동 생성합니다.
data-notebook-refiner
Jupyter Notebook의 코드 품질, 문서화 수준, 실행 안정성을 표준화된 절차로 개선하는 워크플로우입니다.
dev-coding-debug
체계적인 디버깅(Systematic Debugging) 절차를 통해 버그의 원인을 찾고 해결합니다. (Source: obra/superpowers)
dev-doc-suite
코드베이스를 분석하여 README, API 문서, 아키텍처 가이드를 자동으로 생성/업데이트합니다.
dev-feature-planner
SKILL.md의 모든 표준(문서화, 리스크 평가, 롤백 전략, 엄격한 TDD)을 준수하는 고급 기능 구현 워크플로우입니다.
dev-init
개발 환경(폴더 구조, README)을 신속하게 초기화하는 Dev 전용 워크플로우입니다.
dev-prompt-engineering
Anthropic의 Best Practice를 기반으로 고성능 프롬프트를 설계하고 최적화합니다.
dev-study-planner
체계적인 학습 계획 수립, 실행, 검증을 위한 학습 전용 워크플로우입니다. (퓨처 플래너의 학습 버전)
dev-trend-tracker
최신 기술 트렌드나 도구를 빠르게 파악하고 요약하여 아카이빙하는 워크플로우입니다. (Efficiency Focus)
git-smart-commit
Git 변경사항을 분석하여 Conventional Commits 표준에 맞는 메시지를 작성하고 커밋합니다.
meta-skill-builder
표준 참조 분리 패턴(Standard Reference Separation Pattern)을 사용하여 워크플로우를 새로 생성하거나 개선합니다.
obsi-concept-distiller
AI를 활용해 핵심 개념을 추출하고, 문맥을 분석하여 지식 베이스(20_Learning)와 양방향으로 연결합니다.
obsi-knowledge-manager
프로젝트/인박스의 문서를 수확(Harvest)하거나 기존 지식을 정제(Refine)하여 '골드 스탠다드' 지식 자산을 만듭니다.
obsi-project-kickoff
표준 구조(Overview, Plan 등)를 갖춘 새로운 프로젝트를 자동으로 생성하며, 중복 검사 및 템플릿 선택 기능을 포함합니다.
obsi-weekly-review
데이터 기반으로 한 주를 회고하고, 인박스 제로 및 액션 아이템 추출을 자동화하는 주간 리뷰 워크플로우입니다.
Page 1248 of 1665 · 83227 results