evaluation

Use proactively whenever academic literature could improve answer quality, even when the user does not mention papers or research.

Optimize AI-consumed code and data for token efficiency — reduce token usage while preserving semantic fidelity.

Design the runtime environment around AI agents — constraints, guardrails, verification, sandboxing, feedback loops, and recovery mechanisms that make agents…

Audit the codebase for violations of the project's core principles — detect unintended system-imposed constraints that contradict the project's stated goals.

Document public code surfaces and API behavior using the project's native documentation conventions while avoiding redundant comments and private…

Enforce the full delivery cycle for every implementation task.

Detect project context and automatically select, apply, and propose skills.

Detect and enforce layered architecture boundaries.

Define contracts before implementations.

Implement Retrieval-Augmented Generation pipelines — ingestion, chunking, embedding, retrieval, and generation.

Coordinate multiple agents — routing, delegation, parallelism, state sharing, and result aggregation.

Analyze test coverage and drive it to 80%+ by writing missing tests.