sangrokjung

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics.

Automatically detects project build environments and executes appropriate build and test commands across multiple languages and frameworks.

Use when adding new error messages to React, or seeing "unknown error code" warnings.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag).

Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing.

Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`).

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when…

Orchestrates and automates the lifecycle of verification skills by detecting coverage gaps and keeping project rules in sync with code…

Orchestrates multi-agent AI teams to distribute tasks, manage file ownership, and aggregate results for complex development projects.