Analytics & Monitoring Agent Skills for Claude Desktop

Designs and reports domain-specific sensitivity and robustness checks for quantitative economics, forecasting, and measurement manuscripts…

Refines and sharpens quantitative economics research topics to meet publication standards for the Journal of Quantitative and…

Stress-tests systems engineering models and packages reproducibility artifacts tailored for the Journal of Systems Engineering (《系统工程学报》).

Constructs and audits formal mathematical and operational system models aligned with the publication standards of the Journal of Systems…

Instrument code so production behavior is visible: structured logging, metrics, tracing, alerting.

Optimize application performance beyond the frontend: Core Web Vitals, load times, server response, database queries, caching, profiling.

Iterative Python via live Jupyter kernel (hamelnb).

Iterative Python via live Jupyter kernel (hamelnb).

Guides empirical heterogeneity analysis for World Economy manuscripts using open-economy and international trade theory margins.

Constructs rigorous, testable cross-border transmission mechanism analyses aligned with the publication standards of The Journal of World…

Use when: (1) You have limited daily submission quota and 50+ skill files to explore, (2) Most Kaggle experiments cost 1 quota each but…

Use when: (1) Entering a new Kaggle competition and unsure what type it is, (2) Need to choose between forking public kernels vs building…

Use when: (1) Your OOF score improved but LB didn't (or got worse), (2) You need to decide whether to submit based on OOF alone, (3)…

Optimal blending strategy for Kaggle competitions: 80/20 rule (re-ranking vs raw).

Generates publication-quality figures for ML papers from research context.

Use when editing worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, pricing tiers, tokenizer IDs, or…

Central hub for building, testing, and iterating on ADK agents.

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration…

Agent skill for consensus-coordinator - invoke with $agent-consensus-coordinator

Agent skill for matrix-optimizer - invoke with $agent-matrix-optimizer

Guidelines to create/update a new mode for PostHog AI agent.