Analytics & Monitoring Agent Skills for Gemini CLI

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model.

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms.

Design statistically rigorous A/B tests and interpret experiment results.

Documents the results of a completed experiment or A/B test with statistical analysis, learnings, and recommendations.

This skill enables Claude to provide interpretability and explainability for machine learning models.

Explicit Identity Across Boundaries

Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces.

Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts…

Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and…

Extract TCR:pMHC specificity data from raw source files (papers, supplementary tables, XLS, PDF, 10X output, AIRR-format) and produce a…

Facebook's library for efficient similarity search and clustering of dense vectors.

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for…

Manages OrchestKit feedback system. Use when providing feedback or viewing usage analytics.

Identify, measure, and exclude bot / crawler / AI-agent traffic in PostHog web and product analytics using the traffic classification…

Standardizes financial data collection and performs dual-source cross-validation across US, HK, and A-share markets.

Turn financial model outputs into a clear written narrative.

Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap", "quarterly review", "year…

Financial reconnaissance — audit current P&L, burn rate, runway, unit economics, and financial health to understand where the constraint is.

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag…

Guides a user from "I want to watch recordings but don't know which ones" to a short, high-signal list of sessions worth watching.

Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model.