checkpoint-resume
Exactly-once processing semantics with distributed coordination for file-based data pipelines. Atomic file claiming, status tracking, and automatic retry with in-memory fallback.
782 repo starsObserved in 3 repos
Development
Development skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
ml-experiment
Design and run machine learning experiments with proper evaluation using jupyter_execute, including training, benchmarking, and ablation studies. Use when the user wants to train models, compare algorithms, run ablation studies, evaluate ML performance, or reproduce paper results.
782 repo starsObserved in 2 repos
Development
row-level-security
Implement PostgreSQL Row Level Security (RLS) for multi-tenant SaaS applications. Use when building apps where users should only see their own data, or when implementing organization-based data isolation.
782 repo starsObserved in 2 repos
Development
distributed-lock
Prevent race conditions across multiple instances. Only one instance can hold a lock at a time. Automatic expiration prevents deadlocks.
782 repo starsObserved in 1 repos
Development
feature-dev
Guided feature development with codebase understanding and architecture focus
781 repo starsObserved in 1 repos
Development
select-solver
Guides users through selecting the right PINA solver for their problem, or creating a custom solver when no built-in fits. Use when the user asks "what solver should I use", "how do I train this", "which solver", "choose a solver", "pick a solver", "solver selection", "how do I set up training", "what's the right solver", or similar. Also triggers when the user mentions specific solver names (PINN, CausalPINN, SelfAdaptivePINN, SupervisedSolver, etc.) or asks about custom training loops / custom solvers.
781 repo starsObserved in 1 repos
Development
select-trainer
Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options. Use when the user asks "how do I train", "how to train", "set up training", "trainer", "Trainer", "train my model", "fit", "training loop", or similar. Also triggers when the user mentions batching, training configuration, train/val/test split, or is confused about how to start training.
781 repo starsObserved in 1 repos
Development
azqr-developer
Expert guidance for developing and contributing to Azure Quick Review (azqr) - A Go-based CLI tool for Azure resource compliance analysis
780 repo starsObserved in 2 repos
Development
schematics
Use this skill when working with Spartacus schematics - Angular schematics for installing, configuring, and migrating Spartacus libraries. Trigger when the user mentions writing, debugging, or testing schematics, works with migration scripts or constructor/component deprecations, creates feature schematics configuration, adds new library installation schematics, tests schematics with verdaccio, or updates migrations.json or deprecation data files. Even if the user just mentions 'schematics', 'ng add', or 'ng update' in the context of Spartacus development, load this skill.
780 repo starsObserved in 1 repos
Development