Discover DevOps skills, compare source repositories and read the instructions for each workflow.
Verify a CVlization inference example is properly structured, builds successfully, and runs inference correctly. Use when validating inference example implementations or debugging inference issues.
Run CVlization examples on the `ssh l1` GPU host by copying only the needed example directory plus the shared `cvlization/` package into `/tmp`, then launching the example’s Docker scripts.
Verify a CVlization training pipeline example is properly structured, can build, trains successfully, and logs appropriate metrics. Use when validating example implementations or debugging training issues.
Patterns for AWS Lambda, DynamoDB, SQS, and Secrets Manager. Use when working on serverless AWS projects.
Generate images using Google Gemini with customizable options
Write in Steven's voice—pragmatic, curious, pedagogical. Opens with measurable payoffs, builds mental models from first principles, uses worked examples, and handles uncertainty honestly. Use for essays, blog p...
Expert code research using GitHub CLI for repository discovery, code search, and deep analysis
Build React UIs using Wix Design System with local documentation
TanStack Start best practices for full-stack React applications. Server functions, middleware, SSR, authentication, and deployment patterns. Activate when building full-stack apps with TanStack Start.
TanStack Query (React Query) best practices for data fetching, caching, mutations, and server state management. Activate when building data-driven React applications with server state.
Best practices for integrating TanStack Query with TanStack Router and TanStack Start. Patterns for full-stack data flow, SSR, and caching coordination.
TanStack Router best practices for type-safe routing, data loading, search params, and navigation. Activate when building React applications with complex routing needs.
Java Backend Coding Technology skill for designing, implementing, and reviewing functional Java backend code. Use when working with Result, Option, Promise types, value objects, use cases, or when asked about J...
Fix ALL issues found in the preceding review. Thorough, relentless, complete.
Thorough parallel JBCT code review. Launches 10 focused reviewers plus aggregator for comprehensive compliance checking.
Evaluate model predictions against ground truth using COCO, Open Images, or custom protocols. Use when computing mAP, precision, recall, confusion matrices, or analyzing TP/FP/FN examples for detection, classif...
Finds duplicate or near-duplicate images in FiftyOne datasets using brain similarity computation. Use when deduplicating datasets, finding similar images, or removing redundant samples.
Visualizes datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when exploring dataset structure, finding clusters, identifying outliers, or understanding data distribution.
Develops custom FiftyOne plugins (operators and panels) from scratch. Use when creating plugins, extending FiftyOne with custom operators, building interactive panels, or integrating external APIs.
Triages FiftyOne GitHub issues by categorizing as fixed, won't fix, not reproducible, or still valid. Use when reviewing GitHub issues, triaging bugs, or closing stale issues in the voxel51/fiftyone repository.
Exports FiftyOne datasets to standard formats (COCO, YOLO, VOC, CVAT, CSV, etc.). Use when converting datasets, exporting for training, creating archives, or sharing data in specific formats.
Imports datasets into FiftyOne with automatic format detection. Supports all media types (images, videos, point clouds), label formats (COCO, YOLO, VOC, KITTI), and multimodal grouped datasets. Use when importi...
Writes Python code following FiftyOne's official conventions. Use when contributing to FiftyOne, developing plugins, or writing code that integrates with FiftyOne's codebase.
Run ML model inference (YOLO, YOLOv8, CLIP, SAM, Detectron2, etc.) on FiftyOne datasets. Use when running models, applying detection, classification, segmentation, embeddings, or any model prediction task. Also...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.