domains / families / software-engineering / sharp-coder

sharp-coder

authentic

Two-layer performance skill combining disciplined THINK layer (surgical edits, simplicity) and terse SPEAK layer (caveman compression). Triggers on requests for brevity, token efficiency, or disciplined coding.

When to use

• Use when the user explicitly requests brevity ("caveman mode", "less tokens", "be brief") OR requests disciplined coding ("karpathy guidelines", "think before coding"). This skill combines extreme token efficiency in prose with rigorous en…

When not to use

• Over-compression may lead to ambiguity. Use full mode if the context is lost.

Skill page

Source