Analytics & Monitoring Agent Skills for Claude Desktop

Use this starter when a task lands in the Conservation genomics and eDNA frontier leaf and the repository has curated resources but no…

How to manage context blocks (system prompt sections) in NVIDIA OO Agents.

Manage what a NVIDIA OO agent sees and remembers — context blocks, event history and queries, history summarization, and persistent…

Show current session status including context usage estimate and project state.

This skill should be used when the user asks to "set up a status line", "configure the footer", "show context window usage", "add a…

Inspect and manage the live agent context window with Context X-Ray.

Retrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI and REST API.

Ingest a corpus of session logs (JSONL transcripts, chat exports) and extract a persona profile — vocabulary frequency, unique idioms and…

Use when AI inference costs are growing unexpectedly, when comparing model choices by cost/quality ratio, or when optimizing token usage…

Computes cost of equity (CAPM), cost of debt (synthetic rating), and weighted average cost of capital (WACC) for any company in any…

Prepare R packages for CRAN submission by checking for common ad-hoc requirements not caught by devtools::check().

Investigate a Linux workstation crash or unexpected reboot.

Create, update, inspect, or repair Data Analytics semantic layers.

Create a new built-in classification evaluator for Phoenix evals.

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models.

Analyzes credit data quality across banking, consumer finance, and lending datasets using data tables and accompanying dictionaries.

Run a complete, read-only audit of a HubSpot CRM portal (duplicates, completeness, data quality, freshness, deliverability, pipeline…

Use when starting a new ML task that structurally resembles a known competition (recommendation ↔ retail, demand ↔ supply, churn ↔ fraud…

Use when designing the empirical study for a Journal of International Business Studies (JIBS) manuscript — matching a cross-country and/or…

End-to-end cross-national comparison study using KNHANES + NHANES + CHNS (or other parallel surveys).

Use when estimating and reporting results for a Journal of International Marketing (JIM) manuscript — measurement-invariance testing…