Analytics & Monitoring Agent Skills

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with…

AI-guided de novo protein design — RFdiffusion backbone generation, ProteinMPNN sequence design, structure validation (pLDDT, pTM, MPNN…

Analyze PyTorch profiler and vLLM trace files with Perfetto SQL evidence.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).

Automatically trace Claude Code conversations to Braintrust for observability.

Triage new issues in the Sentry `javascript` project by archiving non-actionable noise.

Query the U.S. Treasury Fiscal Data API for federal financial data including national debt, government spending, revenue, interest rates…

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN)…

How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots…

Interpreting implicit and explicit feedback — edits, regenerations, abandonment.

Analyzes budget versus actual performance to identify financial variances and provide actionable business insights.

Compute fund KPIs (TVPI, DPI, IRR, MOIC), model carried interest and management fees, and generate LP quarterly update narratives.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL).

Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or…

Analyze, describe, and extract information from images using the MiniMax vision MCP tool.

Use when building a VLM-driven extraction pipeline for scanned PDFs containing structured cards (insurance cards, government IDs…

This skill should be used when configuring VS Code Port Monitor extension for development server monitoring.

Diagnose WatchDock configuration, readiness, and file-analysis problems without changing watched source files.

Analyzes web performance using Chrome DevTools MCP.

Conceptual guide to wide events (canonical log lines) for observability.

Detects workflow failures and inefficient patterns then files GitHub issues.