Intel

Privacy Terms Submit Map API for Agents

Human PR review plus automated skill checks — Intel — VibeLeaderboard

← All Intel

Clip / Other

Human PR review plus automated skill checks

From Benchmarking Coding Agents on New vs Legacy Codebases — Denys Linkov, Wisedocs · ≈16:36

“So, our PR reviews were all all human PR reviews during that refactor.”

“PRs were really good way for us to build context uh for that repo as we only had a few developers working on it, and we wanted to make sure people understood what had gone into the refactor.”

What’s in it

Explains why PR reviews stayed human-only during a major refactor
Shows how local 'skills' checks are supplementing human code review
Argues PRs double as team context-building, not just quality gates

Watch this moment ↗

Clip transcript

So, our PR reviews were all all human PR reviews during that refactor. Uh we did some local checks where we ran skills to say, "Hey, review this code. Make sure that it's good." And they're continuing to get more autonomous as time goes on. But, at that point, PRs were really good way for us to build context uh for that repo as we only had a few developers working on it, and we wanted to make sure people understood what had gone into the refactor.