Per-category/per-family models can produce WORSE leaderboard scores than a single global model, even when per-category CV is better.
Use when drafting an IEEE PerCom rebuttal after being invited following the initial reviews, covering the bounded single-round reply that…
Use when preparing an accepted IEEE PerCom paper for its IEEE Xplore camera-ready, covering de-anonymization, the IEEEtran compsocconf…
Use when auditing an IEEE PerCom research-track submission for HotCRP readiness, covering the mandatory paper-registration step, the…
Structured performance profiling workflow.
Performs two perfection passes plus polish for moderate code refinement with cleanup.
Performs three perfection passes plus polish for maximum code refinement with cleanup.
Backend, database, and infrastructure performance expert covering API response times, query and index optimization, N+1 elimination…
Keep apps and templates loading fast. Read when adding a data model, a list/read action, a page or sidebar that loads data, or when…
Agent skill for performance-monitor - invoke with $agent-performance-monitor
Performance optimization guide for Capacitor apps covering bundle size, rendering, memory, native bridge, and profiling.
Performance profiling for Node.js, Python, and Go: CPU flamegraphs, memory leak detection, bundle analysis, query optimization, and k6…
Design game performance testing strategy.
Dark web monitoring involves systematically scanning Tor hidden services,
App registration with Meta AI, camera permission flows
Automate Perplexityai tasks via Rube MCP (Composio).
Create Persian RTL .pptx decks with python-pptx.
Use when auditing persistence and runtime performance through the evaluation platform with mandatory research, coordinated data-layer…
Coordinates 4 specialized audit workers (query efficiency, transaction correctness, runtime performance, resource lifecycle).
Use to summarize persona goals, pains, proof points, and questions for
Generate user persona documents and empathy maps from templates