Loading...
Loading...
Found 18 Skills
Advanced test optimization with cargo-nextest, property testing, and performance benchmarking. Use when optimizing test execution speed, implementing property-based tests, or analyzing test performance.
Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.
Use when building gameplay systems in Godot 4.7: enemy AI that patrols, chases and attacks, state machines, behavior trees (LimboAI), NavigationAgent3D pathfinding and avoidance for 100 to 1000 enemies, 'agents stack up' or 'path is empty', hitbox and hurtbox combat, fast bullets going through walls, save and load, inventory, quests, dialogue (Dialogue Manager), input remapping, procedural dungeons, or measuring agent counts and frame time headless.
Set up performance benchmarks and CodSpeed harness for a project. Use this skill whenever the user wants to create benchmarks, add performance tests, set up CodSpeed, configure codspeed.yml, integrate a benchmarking framework (criterion, divan, pytest-benchmark, vitest bench, go test -bench, google benchmark), or when the user says 'add benchmarks', 'set up perf tests', 'create a benchmark', 'benchmark this', or wants to measure performance of their code for the first time. Also trigger when the optimize skill needs benchmarks that don't exist yet.
Design, implement, optimize, and review SIMD code in .NET. USE FOR: vectorizing scalar loops with TensorPrimitives, Vector64/128/256/512, or platform hardware intrinsics; reviewing existing SIMD code, including Vector<T>, for contract equivalence, tail handling, memory safety, portability, fallbacks, and measured performance. DO NOT USE FOR: performance work unrelated to SIMD or vectorization.
Optimize code performance through iterative improvements (max 2 rounds). Benchmark execution time and memory usage, compare against baseline implementations, and generate detailed optimization reports. Supports C++, Python, Java, Rust, and other languages.
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
AscendC Operator End-to-End Development Orchestrator. Used when users need to develop new operators, implement custom operators, or complete the full process from requirements to testing. Keywords: operator development, end-to-end, full process, workflow orchestration, new operator creation.
Analyzes and optimizes SQL queries using EXPLAIN plans, index recommendations, query rewrites, and performance benchmarking. Use for "query optimization", "slow queries", "database performance", or "EXPLAIN analysis".