Analytics & Monitoring Agent Skills for Claude Desktop

Together AI performance tuning for inference, fine-tuning, and model

Together AI reference architecture for inference, fine-tuning, and model

Plan a token-efficient Claude Code or Codex setup, or get a quick health check.

Automate Token Metrics tasks via Rube MCP (Composio).

Generate detailed token usage report with threshold analysis and recommendations

Pick TokenLab models for chat, coding, image, video, audio, embeddings, reranking, decisions, and translation by reading public model…

Use when analyzing conversation patterns — extracts dialog from Claude Code or Codex CLI history, classifies each user message across 6…

Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular…

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode

Convert evaluation traces and production logs into SFT examples and preference pairs.

OpenTelemetry setup, span context propagation, sampling strategies, Jaeger queries

Generate distributed tracing schemas for OpenTelemetry with Jaeger/Zipkin integration

When the user wants to implement shipment tracking, product traceability, or supply chain visibility.

Builds trade area and catchment analysis workflows in CARTO.

Personal US-equity options trading KB. `/trade setup` scaffolds a knowledge dir; `/trade import [file]` parses a raw file (PDF/image) into…

Query TradingView market data through the bundled tradingview MCP server without a desktop app or login.

Convert and browse session transcripts as HTML or Markdown.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via…

Run one neutral prompt independently across every discovered model from selected CLI providers, then compare all answers and failures.

Diagnose and fix Single Step Instrumentation (SSI) issues on Linux hosts — SSI automatically instruments applications for APM without code…

Diagnoses dbt Cloud/platform job failures by analyzing run logs, querying the Admin API, reviewing git history, and investigating data…