Analytics & Monitoring Agent Skills for Claude Desktop

Advanced prompt optimization and composition system for all prompt types (system prompts, task-specific, creative, technical, agentic).

Use when implementing a complete AI feature in a BRICKS app end-to-end, after generator and model choice.

Performs evidence-driven reverse engineering of AI product architectures, user journeys, and agent contracts to produce interactive…

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio.

Generate an interactive AIEO monitoring dashboard for any brand from existing monitoring reports.

Evaluates and benchmarks LLM prompt variations using three-column comparison across weak prompts, portable templates, and live skill…

Architects and governs robust AI agent runtimes, multi-agent orchestration, context compression, memory strategies, and domain-enhanced…

Use OpenAQ and AirNow source-backed recipes for air-quality snapshots, nearby monitors, sensor history, point comparison, and AirNow AQI…

Printing Press CLI for Airbyte Admin. Inspect Airbyte workspaces, sources, destinations, connections, jobs, connector definitions, users…

Use this skill for AIRR-seq (Adaptive Immune Receptor Repertoire / VDJ-seq) data analysis with immunarch + immundata in R, including…

Monitor and interact with Akasha's Nidra consolidation engine — the subsystem that automatically consolidates episodic memories into…

Cross-functional organizational health check combining signals from all C-suite roles.

Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations.

Browse, slice, and analyze the curated American Reindustrialization directory — with diffs, geo clusters, sector...

Domain tips and workflow guidance for building AMI computation graphs via MCP tools.

Analyse the session that is running right now.

Assess whether structured data, query results, dashboards, or analytical evidence are trustworthy enough to use.

Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis, occupancy…

Analyses customer and user feedback in Dcipher - reviews, support tickets, survey responses, call transcripts, chat logs, community posts…

Pull and interpret production experiment query-performance data from the staff-only `/api/debug_ch_queries` endpoints backing the…