Analytics & Monitoring Agent Skills for Claude Desktop

Diagnose unit profitability, CAC payback, defensible LTV, and break-even metrics across recurring, transactional, and service business…

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete…

This skill should be used when the user asks "why does adding servers not help", "why did throughput drop when we scaled out", "how far…

US stocks analysis by an adversarial investment committee.

Design, execute, audit, or synthesize evidence-led user-demand research with the SURE protocol.

User segmentation and persona creation from mixed data sources — analytics, CRM, support tickets, reviews, or any combination.

Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM.

Validate and explain GeoParquet 2.0 vector files by checking local

This skill enables Claude to validate the ethical implications and fairness of AI/ML models and datasets.

Use after creating or modifying ANY Honeydew object (metric, attribute, entity, domain).

When the user has to prove, measure or defend what a customer actually got for their money — the impact hypothesis, the baseline, the…

Screen US stocks for high-quality dividend opportunities combining value characteristics (P/E ratio under 20, P/B ratio under 2)…

Decompose financial variances into drivers with narrative explanations and waterfall analysis.

FP&A-style period-over-period variance analysis and trending reports.

Optimize Vast.ai GPU instance selection, startup time, and training

Use when you need to populate the Meta-Vault with machine-generated notes derived from session-orchestrator JSONL records.

Identify and classify duplicate TCR records across all VDJdb chunks at three resolution levels (beta-only, paired, and same-epitope…

When to activate: vector database, Pinecone, Weaviate, Qdrant, Chroma, HNSW, similarity search, metadata filtering, hybrid search…

Implement vector similarity search with embedding generation, index selection, and hybrid retrieval strategies.