Analytics & Monitoring Agent Skills for Claude Code

Detect quiet failures in LLM agents - tool skipping, gibberish outputs, infinite loops, and degraded quality.

Full single-cell RNA-seq pipeline from raw counts to biological interpretation.

When to use scGPT, Geneformer, UCE, and the perturbation models, and when a linear baseline beats them.

Builds site selection and cannibalization analysis workflows in CARTO.

Fetch financial data from EODHD API — historical prices, fundamentals, options, technical indicators, news, sentiment, macro indicators…

Define Service Level Objectives (SLOs) and an error budget policy for a service.

Guides the selection of SLIs, configuration of SLOs, and management of error budgets to ensure service reliability.

Guide SLI selection, SLO setting methodology, and Error Budget management.

Guides Service Level Indicator (SLI) selection, Service Level Objective (SLO) definition, and Error Budget management for reliable…

Compact Snakemake workflow patterns. Keep rules short, complex logic in Python modules.

Social media monitoring, narrative tracking, and open-source intelligence for journalists.

Route a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via continue.

Use when hardening the reproducibility of a SOSP paper's results before submission — pinning the OS-level environment, recording hardware…

Performance profiling principles. Measurement, analysis, and optimization techniques.

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark.

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark.

Use when the exhibits of a Journal of Urban Economics (JUE) manuscript must make the spatial pattern visible — maps, event-study plots…

Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice…

Bring declared user journeys within pre-declared performance budgets, proven by measurement.

Use when designing or diagnosing how an LLM application assembles, renders, mutates, retrieves, caches, evicts, or compacts model-visible…

Operate the SpikingJelly package for SNN modeling, datasets,