from Zorai309
Conducts deep performance audits across databases, memory, algorithms, concurrency, I/O, bundling, and more using specialist agents and pattern-based detection.
This skill runs a coordinated set of specialist agents to find performance anti-patterns across a codebase. Each agent focuses on a domain (database queries, memory, algorithmic complexity, concurrency, bundle size, dead code, I/O, rendering, data structures, error handling, caching, build config, and security-related performance). Agents use pattern-based search (grep/glob) and limited-context reads to surface high-impact issues and recommended fixes, then the skill consolidates findings into a prioritized audit report.
Use when you need a performance-focused code review or audit: 'optimize my code', 'find bottlenecks', 'speed up my app', or after a release that introduced regressions. Good for large codebases where focused, domain-specific checks catch issues human reviewers may miss.
Likely compatible with CLI and API-based multi-agent orchestrators and agent runtimes (Copilot/Codex-style CLI adapters, Gemini/Claude/other model CLIs via the host orchestration).
This skill has not been reviewed by our automated audit pipeline yet.
Knowledge Base (Help Center)
Guidance and templates for designing help center architecture, writing effective support articles, and optimizing search to maximize self-service deflection.
OpenAI CLIP
Contrastive language–image pre-training (zero-shot image classification, image-text similarity, and cross-modal retrieval).
Weights & Biases (wandb)
Integrate Weights & Biases for ML experiment tracking: log metrics, hyperparameters, checkpoints, run sweeps and view collaborative dashboards.
EconML (Microsoft) — Heterogeneous Treatment Effects
Guidance and examples for using Microsoft EconML to estimate heterogeneous treatment effects (Double ML, Causal Forest, Deep IV) from observational data.
