Agent Skills Hub

fiftyone-find-duplicates

Find, review, and remove duplicate or near-duplicate images in FiftyOne datasets using computer vision similarity embeddings.

scikit-learn

Classical machine learning with scikit-learn. Use for classification, regression, clustering, dimensionality reduction, preprocessing, model evaluation, and building robust ML pipelines in Python.

robot-perception

Robot perception system design, configuration, and optimization for cameras, LiDAR, and sensor fusion pipelines. Includes camera calibration, 3D reconstruction, and production deployment best practices.

pytorch-lightning

PyTorch Lightning skill for scalable deep learning: automates model training, multi-GPU orchestration, data pipelines, and distributed training strategies like DDP, FSDP, and DeepSpeed.

visual-creative

AI-powered creative visual prompt generator for posters, banners, product shots, and social media content.

ship-learn-next

Transform passive learning content like transcripts and tutorials into actionable Ship-Learn-Next cycles with concrete implementation plans and progress-oriented quests.

cn-daily-tools

An all-in-one Chinese daily utility toolkit: weather, currency exchange, news, and package tracking. Zero configuration, no API keys required.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

context-fundamentals

Foundational guidelines for context engineering: optimizing token budgets, attention mechanics, and system architecture for AI agents.

pytdc

Access AI-ready datasets, benchmarks, and molecular oracles for drug discovery, including ADME, toxicity, DTI, and molecular generation tasks.

reflect-appworld-failure

Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples.

screenshot-capture

Automated screenshot-to-knowledge workflow for Enzo. Captures, categorizes, extracts content, and logs patterns from screenshots to build a structured reference library.