Analytics & Monitoring Agent Skills for Claude Desktop

Query Pennylane read-only and produce work lists: uncategorised transactions, invoices without a justification, supplier and customer…

Use when executing and reporting the analysis for a Manufacturing & Service Operations Management (M&SOM) manuscript — proving structural…

Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and…

Product analytics — PostHog, Mixpanel, events, funnels, cohorts, retention, North Star metric, OKRs, and product dashboards.

Analyze Rust compilation profiling data using DuckDB to find performance bottlenecks, trait explosions, and monomorphization issues.

Produce incident analysis and atomic prod knowledge updates from logs, metrics, traces, tickets and code evidence.

Analyze log files by stripping ANSI escape sequences first.

Use when the user has a known, already-observed anomaly in their data — a metric spike or drop, an outlier, an unexpected number — and…

Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs.

Generates interactive Apache ECharts visualizations and standalone HTML dashboards from raw datasets, tables, or analytical results.

Create and manage APM service remapping rules — rewrite service names at ingestion time to collapse noisy inferred entities, clean up…

When the user wants to set up, interpret, or improve their app analytics and tracking.

Monitor Apple Notes automation health and performance metrics.

Instrument browser/web apps with the Application Insights JavaScript SDK (@microsoft/applicationinsights-web).

Execute this skill enables AI assistant to profile application performance,

Show experiment dashboard with results, active loops, and progress.

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly).

Run a single experiment iteration. Edit the target file, evaluate, keep or discard. Use when the user runs /ar:run or asks for one manual…

Show experiment dashboard with results, active loops, and progress.

Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance…

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator…