essentials

Produce a rich, self-contained HTML explainer for a code change — deep background, core intuition with diagrams, a guided code walkthrough, and an interactive quiz. Use whenever the user asks to explain or deeply understand a diff, PR, branch, or commit — "explain this PR", "walk me through this change", "what does this diff actually do", "make an explainer for this branch" — or wants a shareable document that teaches someone else what changed and why. Output is an HTML file opened in the browser, not a chat reply.

Compact the current conversation into a handoff document for another agent to pick up. Use when the user says "hand this off", "wrap up", "save context", "continue later", "pass this to another session", "I need to stop here", "pick this up later", or when a session is ending with unfinished work. Also use when context is getting long and the user wants to start fresh without losing progress.

Build a throwaway prototype to answer a design question before committing to real implementation. Generates either a runnable terminal app (for state machines, data models, business logic) or several radically different UI variations on one route (for visual/layout decisions). Use when the user wants to prototype, spike, POC, sanity-check a data model, mock up a UI, explore design options, or says "prototype this", "spike this out", "let me play with it", "try a few designs", "sketch this in code", "I want to try something before building it for real", "quick and dirty version", or "validate this approach" — even if they don't use the word "prototype."

Socratic tutor that drills the user until they deeply understand a change — the problem, the solution, the design decisions, the edge cases, and what it impacts. Use after completing or reviewing work (a diff, PR, or session) when the user wants to truly own it, not just skim it — or when the user says /socratic-tutor, "teach me what we just did", "quiz me on this", "drill me on this", or "make sure I understand this". Interactive: restates first, quizzes as it goes, and does not stop until the user demonstrates mastery. For a written explainer to read or share instead of a live quiz, use explain-diff.

Review the current branch with six specialist lenses (security, correctness, conventions, tests, architecture, duplication), then put every finding through an adversarial verifier that tries to refute it — so what reaches you has already survived a skeptic. Use when the user asks for a thorough, deep, or paranoid review, a review before merging or shipping, a "real" review, or wants to know what a review would catch that a quick pass misses. Costs 12 agents; for a fast single-pass read, use the built-in code-review skill instead.

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use when the user explicitly asks for a thermo-nuclear review, thermonuclear review, deep code quality audit, or an especially harsh maintainability review. Not for ordinary review requests — those belong to the built-in code-review skill. This file is also the canonical rubric loaded by the thermo-nuclear-code-quality-review agent.