pitcany

Review Production ML — AI skill for Claude Code

AI community

Pre-deployment and in-production ML review — training/serving skew, drift, delayed labels, versioning of model/features/calibrator, shadow and canary rollout, rollback criteria, monitoring, retraining.

How to install Review Production ML

Installs to ~/.claude/skills/pitcany-statistical-agent-skills-review-production-ml/SKILL.md

Terminal

mkdir -p ~/.claude/skills/pitcany-statistical-agent-skills-review-production-ml && curl -fsSL https://raw.githubusercontent.com/pitcany/statistical-agent-skills/HEAD/commands/review-production-ml.md -o ~/.claude/skills/pitcany-statistical-agent-skills-review-production-ml/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Review Production ML does

description: Pre-deployment and in-production ML review — training/serving skew, drift, delayed labels, versioning of model/features/calibrator, shadow and canary rollout, rollback criteria, monitoring, retraining triggers.

Production ML review

Target: $ARGUMENTS

What to do

Invoke the production-ml-review skill.
Run the pre-deployment gate checklist and report each item as pass / fail / unverifiable. Do not summarize the gate as "mostly ready" — report the items.
T

Alternatives in AI

Inference Serving — ai-research-skills vLLM, SGLang, TensorRT-LLM, llama.cpp 5.4k ★
ML Deployment Pack — Machine learning model deployment skills 1.6k ★
Aiwg — Cognitive architecture for AI-augmented software development 204 ★