Agent-Era Skill Gym

Deliberate practice to keep your code-review instincts sharp

Problem

As AI writes more code, judging whether its output is correct gets harder. Stop writing by hand for a while and review skill, systems intuition, and debugging instincts visibly decay — but there's no training ground aimed at non-LOC skills.

Solution

A deliberate-practice gym focused on review and judgment, not output volume: a few short daily exercises — spot the race condition in a snippet, find the root cause in messy logs, estimate an algorithm's complexity — with instant scoring and explanations, plus long-run skill curves.

Users

Developers leaning on AI but worried about skill rot, engineers prepping for interviews, tech leads who want to stay hands-on

MVP

Two tracks: technical fluency and systems intuition; 3-5 short exercises per day; instant grading and explanations; per-dimension skill curves; no login, local progress storage

Revenue

Free daily set + subscription for the full library and AI follow-up explanations; team plan gives engineering orgs a skill radar

Why now

Debate over agent-driven skill atrophy is heating up and practitioners are actively looking for anti-rot tools; this needs no model training, so an indie can iterate fast