Per-category/per-family models can produce WORSE leaderboard scores than a single global model, even when per-category CV is better.
Set up, review, debug, or validate Orca per-workspace environment recipes — on-demand, disposable runtimes (cloud sandboxes, VMs, or…
Profile and optimize hotspots.
Performance optimization patterns covering Core Web Vitals, React render optimization, lazy loading, image optimization, backend…
Run a critical, multi-dimensional performance review with parallel agents across algorithmic complexity, memory/allocation, data access &…
Full performance audit cycle — dispatch the sibling performance-audit skill (parallel perf lanes + execution-cost map), cross-validate…
For claims based on unjust enrichment – basic provision § 812 para. 1 sentence 1 alternative 1 of the German Civil Code (BGB)…
Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer
Use for performance optimization, performance regression analysis, throughput, latency, memory, CPU, allocation, IO, concurrency…
Evaluate supplied performance facts, hypotheses, experiments, and learning state with causal and leakage discipline.
Screen observable performance-limitation patterns using HR, pace, breathing, fatigue, RPE, and task response.
Agent skill for performance-monitor - invoke with $agent-performance-monitor
Optimizes application performance across frontend, backend, queries, and databases.
Use when optimizing code for performance, reducing bundle size, improving load times, or fixing performance bottlenecks.
Performance profiling for Node.js, Python, and Go: CPU flamegraphs, memory leak detection, bundle analysis, query optimization, and k6…
Performance profiling and bottleneck detection for Node.js, Python, and browser apps
Design game performance testing strategy.
Comprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, web security…
Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.
App registration with Meta AI, camera permission flows