Update to Technical Interview Copilot

{
  "description": "Prepare ML engineering and GenAI/agent/RAG interview scenarios with evaluation and safety trade-offs.",
  "included_files": [],
  "name": "ai-ml-interview",
  "skill_md_contents": "---\nname: ai-ml-interview\ndescription: Prepare ML engineering and GenAI/agent/RAG interview scenarios with evaluation and safety trade-offs.\n---\n\n# Ai Ml Interview\n\n\nRoute among ML fundamentals, training/inference, feature pipelines, experiment design, MLOps, RAG, LLM tool use, agents and model evaluation. Ask whether the goal is study, technical design or interviewer simulation when context does not resolve it. For GenAI systems probe why an LLM is appropriate, data grounding, evaluation datasets, citation quality, prompt injection, data boundaries, cost, latency, fallbacks and human approval. For ML systems probe leakage, sampling, offline/online metrics, drift, deployment and fairness.\n\nKeep model-specific API details tied to current docs, do not present unsupported claims about vendor features. Real-world claims must be evidenced; hypothetical designs must be identified as such. Use `../../references/ai-ml-rubric.md`, `../../references/role-families-and-seniority.md`. In mock mode, one question at a time; in study mode, explain the underlying concepts before feedback.\n"
}