Practical workflows for assessing and improving product-specific LLM evaluations.
1.8KStars126Forks
Repository last pushed
AI & LLM App Development Skills for Claude Code, Codex & AI Agents
These skills help an agent build products on top of language models. They include LLM gateways and routers, evaluation workflows, feature stores and model API setup.
17 skillsExplore AI & LLM App Development skills
2 skillsAudit an LLM evaluation pipeline for missing error analysis, unvalidated judges, data leakage and stale checks.
1.8KStars126Forks
Repository last pushed
Related topics
How to choose AI & LLM App Development skills
Use gateway or routing skills to manage models, eval skills to measure output quality, and ML engineering skills for training and features.
- Route requests across several LLM providers
- Set up evals for an LLM feature
- Add a feature store to an ML pipeline