Nicholas Previtali

Implements tasks following TDD. Use proactively when a plan task needs implementation. Builds features methodically: asks questions → implements with tests → self-reviews → commits. Always externalizes decisions to files. Use for any discrete coding task.

Senior holistic reviewer for pre-merge assessment. Reviews entire git diff against the original plan for architecture alignment, design quality, and production readiness. Run ONCE after ALL tasks complete, not per-task. Reports merge readiness with reasoning.

Creates detailed implementation plans with bite-sized tasks. Breaks work into 2-5 minute tasks with exact file paths, complete code, and verification commands. Use when requirements are clear and need systematic task breakdown.

Assesses code quality after spec compliance passes. Checks HOW code was built: patterns, error handling, type safety, test coverage, security, maintainability. Reports issues categorized as Critical/Important/Minor with file:line references.

Deep codebase exploration and context gathering. Use proactively when understanding existing code, finding patterns, investigating architecture, or gathering context before planning. Fast, read-only, runs in background by default.

Verifies implementations match their specifications. Use proactively after builder completes a task. Reads actual code — does NOT trust builder reports. Checks for missing requirements, unneeded extra work, and misunderstandings. Reports pass/fail with file:line references.

Generate or update a semantic domain map (ATLAS.md) for the project. Maps where to look, entry points, module purposes, key symbols, and integration points. Complements codemap's structural index with the domain knowledge layer.

Use when starting creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements through Socratic dialogue before any implementation.

Use when you have an implementation plan ready to execute. Dispatches builder agents per task with automated spec and quality review chains. Supports single-track (subagents) and multi-track (Agent Teams) parallel execution.

Use when encountering any bug, test failure, or unexpected behavior. Enforces systematic root-cause investigation before proposing fixes. Prevents guess-and-check debugging.

Use when you have stories or clear requirements that need to become an implementation plan with bite-sized tasks, exact file paths, complete code, and verification commands.

Use before merging to verify completed work meets requirements and quality standards. Dispatches code-reviewer for holistic assessment of the full git diff against the original plan.

Run once after installing turbocharge. Audits global config for conflicts — duplicate agents, competing skills, stale rules — and offers to fix them. Also validates turbocharge plugin health.

Use when implementation and review are complete and you need to integrate the work. Verifies tests, presents structured options for merge, PR, keep, or discard, and handles cleanup.

Use when you have requirements, PRDs, or feature descriptions that need to become implementable work. Transforms requirements into INVEST-compliant user stories with testable acceptance criteria.

Use when ending a session, taking a break, or context is getting full. Captures session state, decisions, and generates a resume prompt for the next session. Critical for multi-session continuity.