thermo-nuclear-code-quality-review

Reviews branch diffs for structural regressions, file-size growth, and spaghetti-condition complexity.

2|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/nseng-ai/ns --skill thermo-nuclear-code-quality-review-nseng-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: thermo-nuclear-code-quality-review
Source: https://github.com/nseng-ai/ns/tree/main/.agents/skills/thermo-nuclear-code-quality-review
Command: npx skills add https://github.com/nseng-ai/ns --skill thermo-nuclear-code-quality-review-nseng-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often rubber-stamp working implementations that quietly degrade maintainability: files balloon past 1000 lines, ad-hoc conditionals tangle existing flows, and thin wrappers add indirection without clarity. This Skill enforces an unusually strict, structure-focused review that pushes for dramatic simplification rather than cosmetic cleanup. ## Core Features & Use Cases - Structural regression detection: Flags files crossing the 1000-line threshold, scattered special-case branching, feature logic leaking into shared paths, and unnecessary casts, optionality, or wrapper abstractions. - Code-judo restructuring suggestions: Actively searches for reframings that delete whole layers of complexity instead of merely rearranging them, with a prioritized list of preferred remedies. - Adversarial findings challenge: Runs a self-critique pass (via subagent when available) that keeps, downgrades, or drops each draft finding so only high-conviction issues survive. - Use Case: Before merging a large feature branch, run this review to catch a diff that pushes a module past 1k lines and bolts new conditionals onto an unrelated flow, then get concrete restructuring proposals that keep behavior identical. ## Quick Start Ask the agent to run a thermo-nuclear code quality review on the current branch's changes before merging.

Frequently Asked Questions about thermo-nuclear-code-quality-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a strict code quality review on a branch diff?

Invoke this review on the current branch's changes and it audits the merged diff for structural regressions, file-size explosions, and branching complexity. It outputs prioritized findings with concrete restructuring remedies rather than style nits.

What does a thermo-nuclear code review flag as blockers?

It treats files crossing 1000 lines, ad-hoc conditionals bolted onto unrelated flows, feature logic leaking into shared modules, unnecessary wrappers or casts, and duplicated canonical helpers as presumptive blockers requiring author justification.

Does this review cover commit organization and PR hygiene?

No. Commit organization, stack shape, and PR description quality are explicitly out of scope and rated LOW at most. The review judges only the implementation as it would land: code structure, abstractions, and codebase health.

How does the adversarial findings challenge work?

Draft findings are passed to a challenger subagent (or an inline pass if subagents are unavailable) that marks each KEEP, DOWNGRADE, or DROP. Findings survive as HIGH only if the remedy deletes real complexity, prevents a plausible bug, or repairs a boundary violation.

When should I not use this strict review?

Avoid it for trivial changes, prototypes, or when you only need a correctness check. The review demands ambitious restructuring and will push back on working code that leaves the codebase messier, which can be excessive for low-stakes diffs.