Evaluate trained machine learning models using metrics suited to the task. Compare candidates consistently, review decision thresholds and probability estimates, and identify weaknesses in validation before deployment or publication.
Explore scientific data across more than 200 file formats to understand its structure, contents, and quality. Produce Markdown reports with statistical summaries, format-specific findings, and recommendations for preprocessing, visualization, and further analysis.
Turn Figma screens and components into code that follows an existing project's conventions. The workflow retrieves design details and assets, reuses existing components, and checks the resulting interface against Figma screenshots.
Organize scattered files by type, purpose, or date, find duplicates, and review older material. Get a proposed folder structure, then approve file moves and renaming, with confirmation required before any deletion.
Search local VCO/vibe documentation, configuration, and skill descriptions for evidence behind rules or recommendations. Retrieve ranked excerpts with file paths and line numbers so explanations can point directly to the supporting source passages.
Set up and run fluid dynamics simulations in Python to study turbulence, vortices, shallow water, and layered flows. Covers choosing equation solvers, configuring parameters, parallel execution, and plotting fields and energy spectra.
Find and retrieve economic indicators from FRED, including GDP, unemployment, inflation, and interest rates. Supports comparisons across periods, changes in reporting frequency, historical releases before revisions, regional data, and publication schedules for economic research.
Generate photos, illustrations, concept art, and presentation assets from text, or edit existing images with specific instructions. Choose among supported OpenRouter models and save the result as a PNG file at a specified location.
Turn raw test results into readable reports with pass and fail totals, unstable tests, and coverage, meaning how much code tests exercise. Package results for releases, quality assurance, or reviews, with follow-up actions.
Check CPU cores, GPUs, available memory, and disk space before demanding computing tasks. Save a JSON report with recommendations for parallel workers, GPU use, and processing data in chunks when memory is limited.
Analyze genomic regions with gtars using Python or command-line tools. Find overlaps, generate coverage tracks showing read density, prepare regions as tokens for machine learning, and split single-cell fragment data for further analysis.
Prepare pathology image datasets by detecting tissue in whole slide images and extracting smaller image tiles. Use random, grid, or score-based selection, preview extraction locations, and apply preprocessing filters to review and prepare the resulting tiles.
Coordinate multiple AI agents under a lead coordinator for research, development, and review. Assign specialized roles, use voting to make shared decisions, preserve collective knowledge, and pause or resume work through managed sessions.
Develop testable scientific hypotheses from observations, preliminary data, and published evidence. The skill compares competing explanations, defines measurable predictions, proposes experiments, and organizes evidence and decision criteria into a structured research report.
Write Python tests with Hypothesis that generate varied inputs and check properties, rules that should always hold. Discover edge cases, reduce failures to simpler examples, and save failing inputs for replay alongside conventional tests.
Generate and edit images through the OpenAI Image API using a bundled command-line script. Create product shots, illustrations, and covers, replace backgrounds, remove objects, produce transparent images, or generate batches of variations.
Learn how to organize the instructions, conversation history, documents, and tool results an AI agent receives. Explains context limits and loading information as needed, helping you review agent designs and investigate behavior caused by poorly managed context.
Develop articles, blog posts, and newsletters with help researching sources, building outlines, strengthening openings, and reviewing each section. Preserve the writer’s voice while refining structure, clarity, supporting evidence, and citation formatting across successive drafts.
Guide multi-step research with source checks, comparisons across sources, and recovery from tool errors. The skill tracks retrieved evidence and unresolved gaps so reports show what supports their claims and what remains unverified.
Turn development errors and debugging attempts into a structured Chinese report covering causes, fixes, and prevention steps. Create a Git commit that references the report, and update an index for later review.
Learn programming through tutorials tailored to your experience, goals, and actual project code. Keep a shared learning history across projects, record questions, and use quizzes with spaced review to revisit concepts based on demonstrated understanding.
Look up how genetic differences affect medication response using ClinPGx. Retrieve gene–drug relationships, clinical guidelines, genetic variant functions, and drug labels to gather evidence for research and reviews of genotype-based dosing recommendations.
Draft case reports, diagnostic reports, clinical trial reports, and patient records using document-specific structures and templates. The skill guides completeness checks, patient de-identification, and documentation aligned with named clinical reporting guidelines and regulatory frameworks.
Creates LaTeX/PDF reports for pharmaceutical and clinical research. Compares patient groups by biomarkers, measurable biological indicators, and prepares treatment recommendation documents with evidence ratings, statistical results, and decision flowcharts.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)