AI Agent Skills

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom mode…

Delegate one complex task to a single subagent, review its work in two stages before merging back. Sequential — one agent at a time, with oversight. Use when a task is c…

Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parall…

Coordinate small teams of specialized Codex agents with bounded parallelism, explicit ownership, native messaging, and evidence-based synthesis. Use when two or more ind…

Design CI/CD pipelines that run test suites. Covers GitHub Actions and GitLab CI templates, parallelism and sharding, artifact management, flaky-test quarantine

Analyzes large tasks for independent subtasks that can be safely parallelized. Produces a DAG-based dispatch plan with dependency ordering and maximum parallelism.

Diagnose slow, expensive, or regressed Apache Spark and PySpark applications by comparing runtime evidence against a healthy run. Use for long stages, stragglers, skew,…

Getting started with Intel oneTBB for C++ parallelism on Intel CPUs. Use when a C++ loop or reduction should run on multiple threads with oneTBB, when the user

Guides the agent to avoid foundational concurrency mistakes in Go: confusing concurrency with parallelism, assuming concurrency is always faster, misusing channels vs mu…

Use when facing 2+ independent tasks or investigations that can be worked on without shared state or sequential dependencies — fan out to specialized sub-agents with iso…