Skill Creator
gar-ai
27 published skills · 0 GitHub stars across the catalog. View on GitHub ↗
git-worktree-manager
Manage Git worktrees for parallel feature development. Use when the user wants to work on multiple branches simultaneously, create worktrees, switch between features, open terminals/editors for worktrees, or manage parallel development workflows.
lint-service
Unified linting scripts for all services in the monorepo. Use when the user wants to lint code, check formatting, or run type checks.
mithril-cache-agent
Build mithril-cache for torch.compile caching. Use when implementing content-addressable storage, cache keys, eviction, or framework hooks.
mithril-checkpoint-agent
Build mithril-checkpoint compression for PyTorch models. Use when implementing byte grouping, compression pipeline, or checkpoint I/O.
mithril-core-agent
Build mithril-core shared infrastructure. Use when implementing storage, compression, hashing, or common types for the Mithril ML toolkit.
mithril-dedup-agent
Build mithril-dedup for ML dataset deduplication. Use when implementing MinHash, LSH, clustering, or document I/O.
rust-async-concurrency
Manage concurrent operations with channels, semaphores, locks, and streams. Use when coordinating parallel work or limiting resource usage.
rust-graceful-shutdown
Implement graceful shutdown with signal handling and broadcast channels. Use when building long-running services or daemons.
rust-tokio-essentials
Core Tokio patterns including runtime setup, spawn_blocking for CPU work, and avoiding blocking operations. Use for any async Rust development.
rust-code-quality
Apply rustfmt and clippy linting standards for consistent, safe Rust code. Use before commits and in CI pipelines.
rust-error-handling
Design error types using thiserror for libraries and anyhow for applications. Use when defining error hierarchies or handling fallible operations.
rust-project-setup
Initialize Rust projects with proper structure, essential crates, and Cargo.toml configuration. Use when starting new Rust binaries or libraries.
rust-candle-whisper
Implement native Rust ML inference with Candle framework. Use when building GPU-accelerated ML pipelines without Python dependencies.
rust-gpu-scheduling
Implement GPU scheduling with VRAM budgets, work queues, and model lifecycle management. Use when building ML pipeline orchestrators.
rust-pyo3-bridge
Bridge Rust and Python using PyO3 with proper GIL handling and async compatibility. Use when integrating Python ML models or libraries.
rust-s3-patterns
Implement S3 operations with rust-s3 including streaming downloads, multipart uploads, and batch operations. Use for cloud storage integration.
rust-metrics
Expose Prometheus metrics with counters, gauges, and histograms. Use for production monitoring and alerting.
rust-tracing
Instrument code with tracing spans and structured logging. Use for observability and performance analysis.
rust-code-organization
Structure Rust code using modules, traits, builders, and newtypes. Use when designing APIs, abstracting behavior, or preventing type confusion.
rust-repository
Implement the repository pattern for database abstraction with sqlx, transactions, and retry logic. Use when building data access layers.
rust-iterators
Leverage iterator chains for efficient, lazy data processing without intermediate allocations. Use when processing collections.
rust-memory
Minimize allocations and cloning using references, Cow, and smart pointers. Use when optimizing hot paths or memory-constrained code.
rust-release-profile
Configure release builds for maximum performance with LTO, optimizations, and binary stripping. Use for production deployments.
rust-async-testing
Write async tests with tokio::test and configure multi-threaded test runtimes. Use when testing async code.