Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
Estimate causal effects from existing data. Use when fitting or interpreting DiD, ITS, synthetic control, regression discontinuity, or other treatment-effect analyses, including robustness checks and counterfactual plots. For choosing a study design before analysis, use designing-experiments instead.
Benchmark indicator performance with BenchmarkDotNet. Use for Series/Buffer/Stream benchmarks, regression detection, and optimization patterns. Target 1.5x Series for StreamHub, 1.2x for BufferList.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
| Design and implement repeatable preprocessing pipelines for cleaning, encoding, transforming, and validating ML input data.
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
| Property-based testing with fast-check (TypeScript/JavaScript) and Hypothesis (Python). Generate test cases automatically, find edge cases, and test mathematical properties. Use when user mentions property-based testing, fast-check, Hypothesis, generating test data, QuickCheck-style testing, or finding edge cases automatically.
| Produce a prioritized performance-optimization roadmap across frontend, backend, and infrastructure. Use as an explicit/manual helper after bottlenecks are known or suspected, not as the owner of regression detection, profiling capture, or test execution.
Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
> Prowler documentation style guide and writing standards.
Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.
Compatibility alias for the descriptive PyMC skill name. Delegate to the canonical local `pymc` payload while preserving route and README compatibility.
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
Codex-compatible Ralph loop runner with dual engines (compat local state loop + optional open-ralph-wiggum backend).
Core cheminformatics toolkit for SMILES/SDF/InChI parsing, descriptors (MW, LogP, TPSA), fingerprints, ECFP/Morgan fingerprints, substructure search, 2D/3D generation, similarity, reactions, and datamol-style molecule standardization when no separate wrapper skill is routed.
高级报告生成专家，支持多格式输出、数据可视化和交互式报告生成。
Prepare and request a code review after implementation or before merge by assembling scope, requirements, git range, and reviewer instructions.
Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.
Review-feedback handling route for CodeRabbit, GitHub, PR, or human reviewer comments. Use before implementing suggestions to verify each finding. Do not use for a fresh code review, security audit, TDD, or final completion evidence.
Single-cell RNA-seq and retained scverse workflow owner. Load .h5ad/10X data, manage AnnData metadata, plan scVI/scANVI batch-correction workflows, QC, normalization, PCA/UMAP/t-SNE, Leiden clustering, marker genes, cell type annotation, trajectory, for scRNA-seq analysis.
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve quantum chemistry calculations, molecular property prediction, DFT or semiempirical methods, neural network potentials (AIMNet2), protein-ligand binding predictions, or automated computational chemistry pipelines. Provides cloud compute resources with no local setup required.
Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.
Use when planning an end-to-end scholarly publishing workflow, including manuscript source-of-truth, submission assets, revision/rebuttal files, camera-ready checks, reproducible build expectations, and publication package structure.
Open-ended scientific ideation partner. Use for research gaps, mechanism exploration, interdisciplinary connections, assumptions, possible research directions, and lightweight literature matrix or A+B paper-combination idea mapping. For structured testable hypotheses and validation plans, use hypothesis-generation instead.
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
Write research/technical reports with strong structure + figure standards. Supports Markdown/HTML/PDF outputs (Quarto optional), executive summary, methods, results, discussion, and reproducibility appendix.
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data leakage detection, and semantic validation. MANDATORY for: data preprocessing, feature engineering, standardization, normalization, interpolation, missing value handling, feature selection, or ANY data transformation task. Covers grouped time-series, cross-sectional, panel data. Detects: time travel leakage, causal inversion, ID misuse, semantic-numeric fallacies, distribution blindness. User's hard-won lessons from real project failures.
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.
Use when writing or revising scientific manuscript prose: IMRAD sections, abstracts, figure/table captions, citation-integrated paragraphs, reporting-guideline language, terminology, clarity, and journal-submission text.
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
CLI-first web scraping & content extraction with optional MCP server. Use when you have target URLs and need clean, selector-based outputs (html/md/txt).
Dedicated security-audit route for OWASP-style risks, secret leaks, auth flaws, injection, unsafe input handling, SSRF/XSS, and sensitive-data exposure. Use instead of code-reviewer when the prompt explicitly asks for security, vulnerability, threat, auth, or OWASP review.
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
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.
Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time.
Build research slides with text-first source (Slidev/Marp/Reveal/Quarto) and reproducible export (PDF). Includes structure, figure reuse rules, and quality checklist for top-tier scientific presentations.
Intelligent file write error handler: diagnoses permissions, disk space, path length, file locks before retrying. Use when you encounter 'Error writing file', 'Permission denied', 'Access denied', 'No space left', or related file write failures.
Compatibility router for /speckit.* workflows into /vibe-first Codex execution.
Perform cross-artifact consistency analysis across spec.md, plan.md, and tasks.md. Use after task generation to identify gaps, duplications, and inconsistencies before implementation.
Generate custom quality checklists for validating requirements completeness and clarity. Use to create unit tests for English that ensure spec quality before implementation.
Create or update project governing principles and development guidelines. Use at project start to establish code quality, testing standards, and architectural constraints that guide all development.
Structured clarification workflow for underspecified requirements. Use before planning to resolve ambiguities through coverage-based questioning. Records answers in spec clarifications section.
Execute all tasks from the task breakdown to build the feature. Use after task generation to systematically implement the planned solution following TDD approach where applicable.
Generate technical implementation plans from feature specifications. Use after creating a spec to define architecture, tech stack, and implementation phases. Creates plan.md with detailed technical design.
Create or update feature specifications from natural language descriptions. Use when starting new features or refining requirements. Generates spec.md with user stories, functional requirements, and acceptance criteria following spec-driven development methodology.
Break down implementation plans into actionable task lists. Use after planning to create a structured task breakdown. Generates tasks.md with ordered, dependency-aware tasks.
Convert tasks from tasks.md into GitHub issues. Use after task breakdown to track work items in GitHub project management.
| Split datasets into training, validation, and test partitions with the right stratification and temporal rules. Use as a narrow preprocessing helper once the broader ML workflow is already chosen, not as the main route owner for an end-to-end ML task.
Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified.
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
Statistics, probability, linear algebra, and mathematical foundations for data science
Enforces structured, highly documented storage for code and data projects. Use when working on machine learning scripts, data processing, code creation, or script modification that should preserve clear structure and documentation.
Stage-based submission checklists for papers/reports: pre-submission, submission, revision/rebuttal, camera-ready. Includes templates (cover letter, rebuttal matrix) and quality gates.
Root-cause route for actual bugs, failing tests, build errors, crashes, stack traces, and unexpected behavior. Do not use for test-first/TDD feature work, test-report packaging, review-feedback handling, or final completion evidence.
Test-first development route for TDD, writing failing tests first, RED -> GREEN -> REFACTOR, and behavior-changing feature/bug/refactor work. Do not use for already-failing test root-cause debugging, test-report packaging, or final completion evidence.
Claude Skills — questions
Answers built from the skills we actually parsed.