Agentic AI-guided evaluation system for comparing LLMs with multi-judge jury scoring
Skill Claude CodeCodex ✓ vendor
Use when the user asks to create, update, or render an AWS architecture diagram (or a cloud/infrastructure diagram using AWS service icons) — e.g. "diagram our AWS setup", "architecture diagram with CloudFront/S3/EKS/RDS", "update docs/image.png", "make an AWS infra diagram". Produces a clean, poster-style diagram…
Skill Claude CodeCodex ✓ vendor
Port an existing third-party benchmark or eval into this repo as an Inspect AI task, faithfully. Use this whenever the task is "add benchmark X", "port this eval", "can we run here", or adapting any external eval harness (aiewf-eval, lm-evaluation-harness, a paper's repo, a colleague's script). Enforces the one rule…
Skill Claude CodeCodex ✓ vendor
Ship work in the llm-evaluation-system repo end-to-end — commit with conventional-commit messages, push to a feature branch (never directly to main), open a PR with the proper title format, and after merge either run make release to publish to PyPI or just clean up branches. Use this skill whenever the user says…