Analytics & Monitoring Agent Skills for Claude Desktop

Watch another running Claude Code session in real time and narrate its activity in Japanese with detailed term-by-term explanations.

This skill automates the setup of machine learning experiment tracking using tools like MLflow or Weights & Biases (W&B).

Use when adding Heystack observability to a project, or when the user mentions @heystack/otel, "set up Heystack", "add…

Scaffolds new `packages/frontend/editor-ui` experiments using the n8n experiment standard. Use when creating a new editor-ui experiment, adding a PostHog experiment scaffold, or setting up…

Sexual Health Analyzer

Model interpretability and explainability using SHAP (SHapley Additive exPlanations).

Design and build AI agents for any domain.

Use when designing or reviewing the tool/function interface an LLM agent calls through — naming and scoping tools, shaping observation…

Guides instrumenting Go (and TypeScript/PHP) services with structured logging, RED/USE metrics, and distributed tracing so production…

Real-time shipment monitoring and exception management skill with proactive alerting and customer communication

Set up observability for Shopify app integrations with query cost tracking,

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).

Use when packaging code, run files, test collections, or judgments for a SIGIR submission — deciding between an artifact inside a…

Use when designing or auditing the empirical program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff…

Use this skill when the user asks about Sigma Computing dashboards, wants to extract

Use when designing or auditing ACM SIGMETRICS evaluations, covering theorem-plus-validation rigor, stating and testing modeling…

Cross-product Signals scout. Looks for cross-product correlations and explores the surfaces the per-product specialist scouts don't cover.

Signals scout for PostHog session replay.

Use when a policy or controller trained/tuned in simulation must run on the real robot — close the gap with domain randomization for what…

Automate Simple Analytics tasks via Rube MCP (Composio).

Process-based discrete-event simulation framework in Python.