All authors
Claude Skills by MarieLynneBlock
github.com/MarieLynneBlock304 skills3 installs300 views
- Feature Engineering And Leakage Checks[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Forecastic Evaluation[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Gradient Boosting[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Hypothesis Testing And Ab Evaluation[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Imbalanced Classification[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- MatplotlibLow-level plotting library for full customisation. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualisation.Votes: 0GitHub stars: 4
- MlflowDesign, implement, audit, and troubleshoot MLflow workflows across projects. Use when tracking experiments, comparing runs, recording datasets and lineage, evaluating models, packaging custom pyfunc models, managing model versions and aliases, tracing or evaluating GenAI/RAG/agents, or preparing batch and online inference. Covers classical ML, deep learning, and custom pipelines; Python workflows and R integration guidance; local Windows/WSL, OpenShift 4, and AWS. Emphasises leakage-safe eval...Votes: 0GitHub stars: 4
- Model RecommendationAnalyse chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiencyVotes: 0GitHub stars: 4
- Model Selections And Cross Validation[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- NetworkxComprehensive toolkit for creating, analysing, and visualising complex networks and graphs in Python. Use when working with network/graph data structures, analysing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualising network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.Votes: 0GitHub stars: 4
- Numpy Scipy Statistics[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Opencv[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Pandas Data WranglingUse when cleaning, typing, filtering, deduplicating, joining, aggregating, reshaping, or time-aligning tabular data with pandas, or debugging row loss, join fan-out, null handling, index alignment, schema drift, and wrangling memory use. Produces explicit data contracts, reproducible transformations, reject accounting, and invariant checks. Data wrangling only, not exploratory analysis, modelling, feature engineering, visualisation, or orchestration.Votes: 0GitHub stars: 4
- PlotlyInteractive visualisation library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualisation.Votes: 0GitHub stars: 4
- PolarsFast 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.Votes: 0GitHub stars: 4
- Powerbi ModelingPower BI semantic modelling assistant for building optimised data models. Use when working with Power BI semantic models, creating measures, designing star schemas, configuring relationships, implementing RLS, or optimising model performance. Triggers on queries about DAX calculations, table relationships, dimension/fact table design, naming conventions, model documentation, cardinality, cross-filter direction, calculation groups, and data model best practices. Always connects to the active m...Votes: 0GitHub stars: 4
- PymcBayesian modelling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.Votes: 0GitHub stars: 4
- Scikit Learn Pipelines And Column Transformers[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Scikit LearnMachine 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.Votes: 0GitHub stars: 4
- SeabornStatistical visualisation with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualisation.Votes: 0GitHub stars: 4
- Shap And Model Explainability[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- ShapModel interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analysing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box mo...Votes: 0GitHub stars: 4
- Statsmodels Time Series[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Survival AnalysisExpert-standard support for survival and time-to-event analysis at any experience level: cohort design, code, diagnostics, evaluation, interpretation and review. Use for customer churn, retention, failure, readmission or other censored outcomes; Kaplan-Meier, Cox proportional hazards, AFT, competing risks, delayed entry, recurrent events, time-varying covariates, discrete-time models, survival forests, calibration, temporal leakage, immortal time, large-cohort runtime or survival-model audits...Votes: 0GitHub stars: 4
- Tabular Performance At Scale[TODO] Define the specific workflow this skill standardises, including default libraries, quality checks, and expected deliverables.Votes: 0GitHub stars: 4
- Umap LearnUMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualisation, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.Votes: 0GitHub stars: 4
- Api DesignApplies REST and GraphQL design principles to produce or review an API contract.Votes: 0GitHub stars: 4
- Openapi To Application CodeGenerate a complete, production-ready application from an OpenAPI specificationVotes: 0GitHub stars: 4
- Code ReviewApplies a consistent, language-agnostic review framework to any code change. It evaluates code across five dimensions, produces prioritised findings with inline suggestions, and distinguishes blockers (must fix before merge) from improvements (worth addressing but not blocking).Votes: 0GitHub stars: 4
- DiagnosePerform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fitness, and safety — producing a scored report with prioritised remediation actions.Votes: 0GitHub stars: 4
- DoublecheckThree-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.Votes: 0GitHub stars: 4
- Review And RefactorReview and refactor code in your project according to defined instructionsVotes: 0GitHub stars: 4
- Create Github Action Workflow SpecificationCreate a formal specification for an existing GitHub Actions CI/CD workflow, optimised for AI consumption and workflow maintenance.Votes: 0GitHub stars: 4
- Dynatrace ObservabilityUse when investigating Dynatrace incidents, validating releases, writing DQL, triaging security findings, or operating Dynatrace with dtctl.Votes: 0GitHub stars: 4
- Csharp NunitGet best practices for NUnit unit testing, including data-driven testsVotes: 0GitHub stars: 4
- Csharp TunitGet best practices for TUnit unit testing, including data-driven testsVotes: 0GitHub stars: 4
- Csharp XunitGet best practices for XUnit unit testing, including data-driven testsVotes: 0GitHub stars: 4
- Dotnet Best PracticesEnsure .NET/C# code meets best practices for the solution/project.Votes: 0GitHub stars: 4
- Dotnet Design Pattern ReviewReview the C#/.NET code for design pattern implementation and suggest improvements.Votes: 0GitHub stars: 4
- Game EngineExpert skill for building web-based game engines and games using HTML5, Canvas, WebGL, and JavaScript. Use when asked to create games, build game engines, implement game physics, handle collision detection, set up game loops, manage sprites, add game controls, or work with 2D/3D rendering. Covers techniques for platformers, breakout-style games, maze games, tilemaps, audio, multiplayer via WebRTC, and publishing games.Votes: 0GitHub stars: 4
- Minecraft Plugin DevelopmentUse this skill when building or modifying Minecraft server plugins for Paper, Spigot, or Bukkit, including plugin.yml setup, commands, listeners, schedulers, player state, team or arena systems, persistent progression, economy or profile data, configuration files, Adventure text, and version-safe API usage. Trigger for requests like "build a Minecraft plugin", "add a Paper command", "fix a Bukkit listener", "create plugin.yml", "implement a minigame mechanic", "add a perk or quest system", or...Votes: 0GitHub stars: 4
- Spirograph Python MatplotlibCreate easy Python scripts that generate beautiful, unique spirograph-style generative art with Matplotlib, support multi-colour or gradient background and main palettes, and always save the result as a PNG. Use when the user asks for creative coding, spirographs, procedural art, or quick art scripts with tunable inputs.Votes: 0GitHub stars: 4
- Git WorkflowCovers the full git workflow for a software project: branch naming conventions, commit message authoring (Conventional Commits standard), PR description templates, and merge strategy advice. It produces ready-to-use git artefacts, not generic advice.Votes: 0GitHub stars: 4
- Commit Message StorytellerAnalyses git diffs or staged changes and generates narrative commit messages that explain WHY a change was made, not just what changed — following Conventional Commits format. Use when asked to "write a commit message", "generate a commit", "describe my changes", "what should I commit this as", "commit this", "summarise my diff", or "help me commit". Works with git diff output, staged files, or plain descriptions of changes.Votes: 0GitHub stars: 4
- Gh CliGitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organisations, extensions, and all GitHub operations from the command line.Votes: 0GitHub stars: 4
- Git CommitExecute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical groupingVotes: 0GitHub stars: 4
- Git Flow Branch CreatorIntelligent Git Flow branch creator that analyses git status/diff and creates appropriate branches following the nvie Git Flow branching model.Votes: 0GitHub stars: 4
- Pr DashboardOpen a GitHub PR dashboard in the browser. Use when the user asks to see their pull requests, open the PR dashboard, show PRs for a date range, or check PR status. Trigger phrases include "show my PRs", "open PR dashboard", "pull request dashboard".Votes: 0GitHub stars: 4
- Repo Story TimeGenerate a comprehensive repository summary and narrative story from commit historyVotes: 0GitHub stars: 4
- Java DocsEnsure that Java types are documented with Javadoc comments and follow best practices for documentation.Votes: 0GitHub stars: 4