Analytics & Monitoring Agent Skills for Devin Desktop

Build and review governed Foggy semantic query payloads for existing models.

Futures markets: contract specs, margin, rollover dates, commodity futures, index futures, interest rate futures, contango/backwardation…

Execute Gemini CLI for AI-powered code analysis and generation.

Reference for accessing session ID via ${CLAUDE_SESSION_ID} automatic substitution

Use this skill when the user wants to analyze Claude token usage, understand Claude API spending, check cache hit rates, review Claude…

When the user wants traffic data, conversion tracking, user behavior on location pages, GBP traffic attribution, or geographic traffic…

GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations.

Build Gradio web UIs and demos in Python.

Validate OpenShift Grafana dashboards.

Execute Groq's primary workflow: chat completions with tool use and JSON mode.

Optimize Groq costs through model routing, token management, and usage

Consolidate PostHog error tracking issues that are the same actual error reported under different fingerprints.

GTmetrix integration. Manage Accounts. Use when the user wants to interact with GTmetrix data.

Debug Guidewire InsuranceSuite issues including Gosu code, Cloud API integrations, and system performance problems.

Generates high-quality AI videos, images, and digital human avatars using Aliyun Bailian models.

Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank…

Diagnose Claude Code hook installation, delivery, and ingestion issues.

When the user wants to optimize hospitality purchasing, manage hotel/restaurant suppliers, or improve procurement processes.

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm.

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU.

Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to…