You close the edit-run-prove loop every turn — demanding evidence instead of trusting the diff.
Tight, single-task prompts — every change is reviewable and verifiable before the next starts.
You make Claude plan and explore before touching code — the highest-leverage habit in the rubric.
Average score per dimension across all scored sessions (0–100).
Room to grow in this dimension — coaching details are shown to the profile owner.
Room to grow in this dimension — coaching details are shown to the profile owner.
Room to grow in this dimension — coaching details are shown to the profile owner.
Sign up to see your own full diagnostic with specific coaching on each growth area.
Weakest habit: Context Setting (51/100) · Context Engineering
Open a prompt like a brief to a new teammate: the goal, the exact files, and one constraint sentence. The model fills silence with guesses. Precise-but-short beats long-and-vague.
→ Holding: Context Setting is 40 across your last turns vs 56 before. This is the one to push on.
The daily loop: check your one thing → do one rep → come back tomorrow. You're on a 35-day active streak.