Analytics & Monitoring Agent Skills for Perplexity

Use when asked to select chart types for analytics dashboards, choose BI visualizations, or design data displays.

Analytics and BI engineer — dashboards, metrics design, reporting pipelines, and data storytelling.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral).

Use proactively whenever LLM API costs come up -- or should.

Generate/create Loki configs — ingester, querier, compactor, ruler, S3/GCS/Azure backends.

Build, rebuild, and deploy the Marketing OS control center: a self-contained single-page dashboard rendered from the OS files, eleven…

Operate and maintain the local MCP server for this project.

Full token research workflow using Messari x402 API.

Analyze and improve the improvement process.

Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform.

Check status of running subagents including token usage and context limits

Write a monitoring setup guide for a service — defining what to measure, how to alert on it, and how to build the observability stack…

This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy…

Automatically discover observability and monitoring skills when working with monitoring.

Manages and customizes the OMA agent's visual Heads-Up Display to optimize terminal visibility and session monitoring.

Help users deploy, validate, run, and parse OmniDocBench evaluations.

Read and render the output of a local Output SDK workflow trace file as clean readable markdown.

Debug LLM applications using the Phoenix CLI.

Build and run evaluators for AI/LLM applications using Phoenix.

Verifies connectivity and ensures the Claude Code environment is correctly synced with the Eidos implementation.

Measures how concentrated an Indian equity portfolio actually is, rather than how many line items it has.