Analytics & Monitoring Agent Skills for Devin Desktop

Use when a Journal of Urban Economics (JUE) manuscript needs a spatial model to interpret its mechanism — a spatial-equilibrium frame, a…

Processing and analysis of spatially resolved transcriptomics across sequencing-based (Visium, Visium HD, Slide-seq, Stereo-seq) and…

Feature engineering patterns for spatiotemporal graph prediction tasks.

AI & LLM Systems Architect - Design RAG pipelines, vector search, semantic caching, evals, and tool-calling guardrails.

SRE & Observability Specialist - OpenTelemetry distributed tracing, Prometheus metrics, structured logs, and resilience controls.

Use when after harmonizing MS/MS spectra and metadata fields (compound

Use when drafting, revising, or diagnosing an LLM system prompt, message layout, tool description, tool schema, or structured-output…

Summarize a sprint's worth of Claude Code activity — sessions grouped by project (cwd), per-model cost breakdown, token efficiency (cache…

Analyze Fabric Data Warehouse performance via CLI using sqlcmd and queryinsights views.

Defines service level objectives, creates error budget policies, designs incident response procedures, develops capacity models, and…

Use when building comprehensive monitoring and observability systems.

Applies an SRE observability mindset to systems, automation, deployments, recovery procedures, scripts, services, and AI-assisted…

Review code and configuration for SRE concerns — SLO/SLA coverage, observability gaps, toil, alerting blind spots, and reliability…

SLO and error-budget reasoning for Site Reliability Engineering: defining what "reliable enough" means for a system, measuring it…

Autonomous trend analysis combining quantitative and qualitative methods.

Collect WebContainer diagnostic info: boot state, file system, process

Interactive naming convention standardization for TMDL-based Power BI semantic models.

Guidance for instrumenting webapps with Azure Application Insights.

Query and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis.

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders).

Analyze a startup from three perspectives: VC investor, job applicant, and CEO/founder.