Developer Productivity

Design stable APIs and module interfaces: contract first, one error format, consistent naming, validation at the boundary, additive changes, plus REST resource and pagination patterns and TypeScript interface patterns.

Give an AI coding agent a CONSTRAINTS.md of mechanical checks it cannot talk its way around: a non-negotiable floor, numeric limits, a ratchet for what exists today, and a diff review that catches weakened tests and suppressions.

Turns code review into one line per finding: location, problem and fix, with an optional severity tag.

Makes your coding agent answer first and drop the filler, while keeping code, commands, paths and error messages exactly as they are.

Shrinks memory files such as CLAUDE.md so they cost fewer input tokens, with validation and a backup of the original.

Add a relevant Claude Academy learning resource to answers about using Claude, only when there is a strong match.

Guides you from an idea to a finished Agent Skill: intent capture, a SKILL.md draft, test prompts, optional eval runs and description tuning.

Writes terse Conventional Commits messages that explain why, not what.