Build and train graph neural networks, models that learn from connected entities, using PyTorch Geometric. The skill covers classifying nodes or whole graphs, predicting missing connections, and modeling molecular properties or networks with multiple entity types.
Build PyTorch machine learning workflows for molecules, proteins, and biomedical relationships. Get guidance on datasets, model selection, training, and evaluation for property prediction, protein modeling, molecule generation, and planning synthesis routes from target molecules.
Write and edit Remotion documentation pages with consistent API explanations, clear headings, and TypeScript-checked code examples. Follow the project workflow to add navigation entries, generate social preview cards, and verify that documentation builds successfully.
Turn implementation plans and specifications into an ordered tasks.md checklist. Organize work around user stories, meaning goals expressed from a user's perspective, with file paths, dependencies, parallel work opportunities, and independent verification criteria.
Use UMAP to reduce data with many features into fewer dimensions for plotting or further analysis. The skill guides parameter choices, preprocessing for clustering, label-guided projections, and transforming new data with an already trained model.
Get guidance on fine-tuning language models with Unsloth, including LoRA and QLoRA methods for training with fewer resources. The skill points to documentation for understanding APIs, implementing training code, debugging problems, and exploring speed and memory optimizations.
Analyze tabular datasets too large to fit in memory using Vaex. Filter rows, calculate statistics, visualize distributions, convert file formats, and prepare machine learning workflows with operations that defer computation until results are needed.
Turn user data and interviews into research-backed personas, or representative user profiles. The toolkit also supports mapping user journeys, planning usability tests, and combining research findings to guide and validate design decisions.
Turn a feature specification into a technical implementation plan. Organizes technology choices, research decisions, data models, and interface agreements into project files, while checking that the design follows the project's documented principles.
Build a planned feature by following an existing task list and technical plan. The skill respects task dependencies, runs tests before related implementation where applicable, records progress, and checks the completed work against the specification.
Search UniProt for proteins by name, gene, or organism and retrieve sequences and functional annotations. Supports FASTA, a text format for sequences, identifier conversion between databases, batch retrieval, and downloads of large result sets through its REST API.
Set up W&B to record machine learning metrics and settings, visualize training progress, and compare experiments. Includes automated searches for training settings, version tracking for datasets and models, and shared reports for team collaboration.
Organize paper or report submissions with stage-specific checklists and templates. Link checks to actual files, prepare cover letters, and track each reviewer comment alongside the response, revision, and location of the change.
Create concise medical treatment plans in LaTeX and PDF, covering goals, interventions, timelines, and monitoring. Templates support chronic disease care, rehabilitation, mental health, and perioperative care, with a first-page summary and diagrams showing care pathways.
Turn text into audio files for narration, product demos, phone prompts, or accessibility reads using the OpenAI Audio API. Choose built-in voices and delivery directions, then generate a single clip or a batch of files.
Create or update a project's governing development principles, covering code quality, testing, and architectural constraints. Maintain the constitution document, record version changes, and align related planning, specification, and task templates with the revised rules.
Analyze research data with suitable statistical tests, regression, correlation, or Bayesian methods. Check assumptions, estimate effect sizes and uncertainty, plan sample sizes, and prepare figures, tables, and reports following APA academic reporting conventions.
Turn a plain language feature request into spec.md with user stories, testable requirements, and acceptance criteria. Create a feature branch and a separate quality checklist, documenting assumptions and clarifying important gaps before planning begins.
Guide feature changes and bug fixes through test-driven development: write a failing test, add the minimum code to pass, then improve the structure. Check coverage and include tests for boundary conditions, errors, and relevant integration points.
Create finished videos from existing clips, audio, images, and copy using local FFmpeg. Remove silent pauses, embed supplied subtitles, adjust volume, and prepare video dimensions and encoding for Shorts, Reels, or TikTok.
Diagnose and fix Claude Code plugin hook failures on Windows. Covers conflicts between WSL and Git Bash, path handling problems, and errors involving .sh arguments, using error messages and configuration files.
Investigate bugs, failing tests, and build errors through reproduction, logs, and comparisons with working code. Follow a staged process to test possible causes, implement a focused fix, and check that the problem is resolved.
Investigate web topics through repeated searches, page visits, link following, and evidence checks. Produce a structured report with source records, working notes, and an action log that lets readers review how findings were reached.
Convert requirements into a detailed implementation plan before coding begins. Break work into small actions with exact file paths, code examples, test commands, expected results, and commit steps so another developer can follow the plan.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)