Analytics & Monitoring Agent Skills

PostHog API for product analytics. Use when user mentions "PostHog",

PostHog error tracking for Python

PostHog error tracking for Web (JavaScript)

PostHog feature flags for Java applications

PostHog integration for any Python application using the Python SDK

PostHog integration for Ruby on Rails applications

PostHog logs for Next.js

PostHog logs for Node.js

Post-market safety surveillance and recall/adverse-event RETRIEVAL across the full spectrum of FDA-regulated products that are NOT covered…

Audits an existing prompt (system prompt, CLAUDE.md, SKILL.md, sub-agent prompt, or a prompt embedded in a Claude API call) against…

Formal theorem proving with research, testing, and verification phases

Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for…

Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage…

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property…

Guides Qdrant monitoring and observability setup.

When the user wants to improve product quality, implement quality control systems, reduce defects, or analyze quality data.

Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8.

Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE /…

Use when adding polymorphic activity timelines with live Turbo Stream updates to any Rails model.

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement.