Thermo Nuclear Code Quality Review
Run an exceptionally strict maintainability and abstraction review on branch changes before merge or release.
Overview
thermo-nuclear-code-quality-review is an agent skill most often used in Ship (also Build) that runs an extremely strict maintainability and abstraction audit on branch changes.
Install
npx skills add https://github.com/cursor/plugins --skill thermo-nuclear-code-quality-reviewWhat is this skill?
- Thermo-nuclear baseline: deep audit of branch changes with behavior-preserving restructuring
- Explicit push for code judo—simpler, smaller, more direct implementations
- Non-negotiable extra standards on abstraction quality, giant files, and spaghetti-condition growth
- disable-model-invocation: true—meant as a dedicated reviewer stance, not casual chat
- Measure twice, cut once: thorough, ambitious modularity and legibility targets
- Includes explicit non-negotiable additional review standards beyond the core deep-audit prompt
Adoption & trust: 2.6k installs on skills.sh; 1.9k GitHub stars.
What problem does it solve?
Your diff passes CI but still hides giant files, weak abstractions, and spaghetti that will slow every future solo-builder iteration.
Who is it for?
Solo builders shipping non-trivial refactors who want a deliberately harsh second opinion on structure and modularity.
Skip if: Quick syntax checks, dependency CVE sweeps, or teams that only need a lightweight PR skim.
When should I use this skill?
User asks for thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
What do I get? / Deliverables
You get a rigorous review agenda focused on restructuring wins and concrete maintainability fixes to implement before merge—without treating “looks fine” as sufficient.
- Structured maintainability findings
- Restructuring and code-judo recommendations
- Giant-file and spaghetti-risk callouts
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Ship/review because the skill is invoked as a formal quality gate on diffs, yet the same rigor applies while iterating during Build. It is a reviewer playbook (not tests or security scanning)—optimized for code review depth, restructuring ambition, and spaghetti-risk calls.
Where it fits
After a large feature lands locally, run the skill to decide whether to split modules before opening a PR.
Pre-merge on a refactor branch to force ambitious restructuring recommendations.
When tests pass but readability regressed, use findings to plan a behavior-preserving cleanup sprint.
During hotfix follow-up, audit whether the patch introduced spaghetti that will compound ops debt.
How it compares
Use instead of a casual “review my PR” chat when you need an aggressive maintainability standard, not a substitute for automated test suites.
Common Questions / FAQ
Who is thermo-nuclear-code-quality-review for?
Indie developers and small teams using Cursor who want a strict, ambition-forward code quality review focused on abstractions, file size, and spaghetti risk.
When should I use thermo-nuclear-code-quality-review?
Use it in Ship (review) before merging large or messy branches; also mid-Build when restructuring a module and you want the thermo-nuclear maintainability bar, not a friendly pass.
Is thermo-nuclear-code-quality-review safe to install?
It is a review prompt skill with model invocation disabled for automatic runs—check the Security Audits panel on this page and ensure review output stays inside your repo policy.
SKILL.md
READMESKILL.md - Thermo Nuclear Code Quality Review
# Thermo-Nuclear Code Quality Review Use this skill for an unusually strict review focused on implementation quality, maintainability, abstraction quality, and codebase health. Above all, this skill should push the reviewer to be **ambitious** about code structure. Do not merely identify local cleanup opportunities. Actively search for "code judo" moves: restructurings that preserve behavior while making the implementation dramatically simpler, smaller, more direct, and more elegant. ## Core Prompt Start from this baseline: > Perform a deep code quality audit of the current branch's changes. > Rethink how to structure / implement the changes to meaningfully improve code quality without impacting behavior. > Work to improve abstractions, modularity, reduce Spaghetti code, improve succinctness and legibility. > Be ambitious, if there is a clear path to improving the implementation that involves restructuring some of the codebase, go for it. > Be extremely thorough and rigorous. Measure twice, cut once. ## Non-Negotiable Additional Standards Apply the baseline prompt above, plus these explicit review rules: 0. **Be ambitious about structural simplification.** - Do not stop at "this could be a bit cleaner." - Look for opportunities to reframe the change so that whole branches, helpers, modes, conditionals, or layers disappear entirely. - Prefer the solution that makes the code feel inevitable in hindsight. - Assume there is often a "code judo" move available: a re-organization that uses the existing architecture more effectively and makes the change dramatically simpler and more elegant. - If you see a path to delete complexity rather than rearrange it, push hard for that path. 1. **Do not let a PR push a file from under 1k lines to over 1k lines without a very strong reason.** - Treat this as a strong code-quality smell by default. - Prefer extracting helpers, subcomponents, modules, or local abstractions instead of letting a file sprawl past 1000 lines. - If the diff crosses that threshold, explicitly ask whether the code should be decomposed first. - Only waive this if there is a compelling structural reason and the resulting file is still clearly organized. 2. **Do not allow random spaghetti growth in existing code.** - Be highly suspicious of new ad-hoc conditionals, scattered special cases, or one-off branches inserted into unrelated flows. - If a change adds "weird if statements in random places", treat that as a design problem, not a stylistic nit. - Prefer pushing the logic into a dedicated abstraction, helper, state machine, policy object, or separate module instead of tangling an existing path. - Call out changes that make the surrounding code harder to reason about, even if they technically work. 3. **Bias toward cleaning the design, not just accepting working code.** - If behavior can stay the same while the structure becomes meaningfully cleaner, push for the cleaner version. - Do not rubber-stamp "it works" implementations that leave the codebase messier. - Strongly prefer simplifications that remove moving pieces altogether over refactors that merely spread the same complexity around. 4. **Prefer direct, boring, maintainable code over hacky or magical code.** - Treat brittle, ad-hoc, or "magic" behavior as a code-quality problem. - Be skeptical of generic mechanisms that hide simple data-shape assumptions. - Flag thin abstractions, identity wrappers, or pass-through helpers that add indirection without buying clarity. 5. **Push hard on type and boundary cleanliness when they affect maintainability.** -