Analytics & Monitoring Agent Skills

Read accumulated cost-tracking spend + budget config, compute utilization, emit 50/75/90/100% alert ladder

Analyze token usage patterns and recommend cost optimizations with estimated savings

Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost

Read every docs/benchmarks/runs/*.json and surface drift in win rate, latency, escalation rate, and LLM-baseline cost over time

Counts what a codebase is made of - files, lines split into code, comments and blanks, declared types (classes, interfaces, enums…

Establishes CPU/GPU baselines before resource-intensive operations.

Create dac dashboards by writing YAML or TSX definition files.

Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables…

Creates comprehensive dashboard and analytics interfaces that combine data visualization, KPI cards, real-time updates, and interactive…

Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics.

Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation.

Assess configurable customer health; avoid universal scores.

Design a customer health scoring model — define signals, weights, thresholds, and action triggers.

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, integrate with scanpy/PyTorch, for…

Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for…

Use when the user wants an iterative, self-checking exploratory analysis of a dataset — surfacing findings that are each verified by…

Structure a product data analysis, metric deep-dive, funnel analysis, or cohort study.

🐉 Fetches and parses time-series data from various sources.

Process automate data cleaning, transformation, and validation for ML

Data quality and pipeline health check — freshness, schema drift, null rates, orphaned records, pipeline status.