Analytics & Monitoring Agent Skills for Claude Code

Show Memoir status for the current Codex project: store path, branch, commit count, memory count, and namespaces.

NVIDIA's runtime safety framework for LLM applications.

Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc).

Detect recurring patterns using the Agent Monitor's workflow intelligence — toolFlow transitions (tool A → B frequency matrices)…

PostHog error tracking for Angular

Deep learning framework (PyTorch Lightning).

Cheminformatics toolkit for fine-grained molecular control.

Guide for Splitrail's terminal UI and file watching.

Authoring guide for Pega GenerativeAI connector rules (Rule-Connect-GenerativeAI), including model configuration, prompt FieldValue…

Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement.

Configure the UniFi Protect MCP server for Claude Code, Codex, or OpenClaw — set NVR host, credentials, and permissions

Query STRING API for protein-protein interactions (59M proteins, 20B interactions).

Control Wan camera, FLF, and Animate.

Accesses multi-market equities, PIT macroeconomic data, factor analytics, and backtesting tools via the Xiaoshi financial API.

Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace…

Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments.

Statistical experiment design and analysis capabilities for product experimentation

Add PostHog error tracking to capture and monitor exceptions.

Agent Designer - Multi-Agent System Architecture

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems.

Tracks per-agent token usage and flags waste in parallel dispatch.