Analytics & Monitoring Agent Skills for Windsurf (legacy)

Signals scout that watches the project's most-viewed dashboards and insights for anomalies — bursts, drops, flat-lines, and trend breaks…

Signals scout for observability gaps — significant event volumes with no insight, dashboard, or alert coverage.

Signals scout for PostHog revenue analytics.

Signals scout for PostHog web traffic. Watches per-channel session volume, attribution breakage, and landing-page health (bounce and 404…

Simple Preference Optimization for LLM alignment.

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13).

Graph analytics over a sparq RDF graph with the opt-in sparq-algos crate: project the graph onto a directed NodeGraph and run PageRank…

Provides patterns to configure Spring Boot Actuator for production-grade monitoring, health probes, secured management endpoints, and…

Design support metrics dashboard -- CSAT, FRT, TTR, ticket deflection rate, volume trends, and agent efficiency.

Support operations reconnaissance -- audit current ticket volume, SLA compliance, knowledge base coverage, escalation paths, and CSAT to…

Shows Synthetic Monitoring check health - check inventory, per-check pass/fail status with success rates, and success-rate timelines as…

Restore system responsiveness via safe, ordered process cleanup and agent-swarm

Build machine learning models using tidymodels for tabular data

Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner.

Score telemetry field name similarity across syntactic, taxonomic, and semantic layers.

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.