agentleFS
Davidengstrom01Davidengstrom01/claude-skills/skills/thermo-nuclear-code-quality-review/SKILL.md

thermo-nuclear-code-quality-review

Skill0 starsChanged 41 days agoMITView on GitHub

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

68 other projects use a version of this, 63 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use thermo-nuclear-review, verify-this and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • gandolhSkill

    thermo-nuclear-review

    Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.

    Also in 7 projects that use this

  • learnerLjSkill

    verify-this

    Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.

    Also in 6 projects that use this

  • rockcookiesSkill

    thermos

    Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.

    Also in 3 projects that use this

  • ElyzeSolutionsSkill

    control-cli

    Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.

    Also in 4 projects that use this

  • dorian-akhsSkill

    handoff-implement

    Creates or executes an implementation-grade handoff brief for a less capable model agent, including a measured context budget and a binding sub-agent orchestration plan. Activated explicitly via /handoff-implement.

    Also in 3 projects that use this

  • ElyzeSolutionsSkill

    control-ui

    Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs.

    Also in 4 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

47 rules. 41 are common, 5 are distinctive, and 1 is very specific to this project.

  • 41

    Common

    Most of the 67 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never post comments on a PR unless told so - keep it in chat as default

    line 8
  2. Common:

    Use this skill for an unusually strict review focused on implementation quality, maintainability, abstraction quality, and codebase health.

    line 10
  3. Distinctive:

    Only raise a finding if it satisfies at least one of these:

    line 18
  4. Distinctive:

    If a finding satisfies none of these, drop it.

    line 24
  5. Distinctive:

    When nothing clears the bar, say so plainly.

    line 30
  6. Common:

    Start from this baseline:

    line 34
  7. Common:

    Do not stop at "this could be a bit cleaner."

    line 47
  8. Common:

    Look for opportunities to reframe the change so that whole branches, helpers, modes, conditionals, or layers disappear entirely.

    line 48
  9. Common:

    Prefer the solution that makes the code feel inevitable in hindsight.

    line 49
  10. Common:

    If you see a path to delete complexity rather than rearrange it, push hard for that path.

    line 51
  11. Common:

    Treat this as a strong code-quality smell by default.

    line 54
  12. Common:

    Prefer extracting helpers, subcomponents, modules, or local abstractions instead of letting a file sprawl past 1000 lines.

    line 55
  13. Common:

    If the diff crosses that threshold, explicitly ask whether the code should be decomposed first.

    line 56
  14. Common:

    Only waive this if there is a compelling structural reason and the resulting file is still clearly organized.

    line 57
  15. Common:

    If a change adds "weird if statements in random places", treat that as a design problem, not a stylistic nit.

    line 61
  16. Common:

    Prefer pushing the logic into a dedicated abstraction, helper, state machine, policy object, or separate module instead of tangling an …

    line 62
  17. Common:

    Call out changes that make the surrounding code harder to reason about, even if they technically work.

    line 63
  18. Common:

    If behavior can stay the same while the structure becomes meaningfully cleaner, push for the cleaner version.

    line 66
  19. Common:

    Do not rubber-stamp "it works" implementations that leave the codebase messier.

    line 67
  20. Common:

    Treat brittle, ad-hoc, or "magic" behavior as a code-quality problem.

    line 71
  21. Common:

    Prefer explicit typed models or shared contracts over loosely-shaped ad-hoc objects.

    line 77
  22. Common:

    If a branch relies on silent fallback to paper over an unclear invariant, ask whether the boundary should be made explicit instead.

    line 78
  23. Common:

    Call out feature logic leaking into shared paths or implementation details leaking through APIs.

    line 81
  24. Common:

    Prefer existing canonical utilities/helpers over bespoke one-offs.

    line 82
  25. Common:

    If independent work is serialized for no good reason, ask whether the flow should run in parallel instead.

    line 86
  26. Common:

    If related updates can leave state half-applied, push for a more atomic structure.

    line 87
  27. Common:

    Do not over-index on micro-optimizations, but do flag avoidable orchestration complexity that makes the implementation more brittle.

    line 88
  28. Common:

    When you identify a code-quality problem, prefer suggestions like:

    line 134
  29. Common:

    Delete a whole layer of indirection rather than polishing it.

    line 136
  30. Common:

    Delete wrappers that do not meaningfully clarify the API.

    line 146
  31. Common:

    Do not be satisfied with "maybe rename this" feedback when the real issue is structural.

    line 153
  32. Common:

    Do not be satisfied with a merely cleaner version of the same messy idea if there is a plausible path to a much simpler idea.

    line 154
  33. Common:

    Do not be rude, but do not soften major maintainability issues into mild suggestions.

    line 159
  34. Common:

    If the code is making the codebase messier, say so clearly.

    line 160
  35. Common:

    If the implementation missed an opportunity for a dramatic simplification, say that clearly too.

    line 161
  36. Distinctive:

    Do not flood the review with low-value nits — not below the real findings, and not as an appendix either.

    line 189
  37. Common:

    Do not approve merely because behavior seems correct.

    line 193
  38. Common:

    no clear structural regression

    line 196
  39. Common:

    no obvious missed opportunity to make the implementation dramatically simpler when such a path is visible

    line 197
  40. Common:

    no unjustified file-size explosion

    line 198
  41. Common:

    no obvious spaghetti-growth from special-case branching

    line 199
  42. Common:

    no obviously hacky or magical abstraction that makes the code harder to reason about

    line 200
  43. Very specific:

    no unnecessary wrapper/cast/optionality churn obscuring the real design

    line 201
  44. Common:

    no clear architecture-boundary leak or avoidable canonical-helper duplication

    line 202
  45. Common:

    no missed opportunity for an obvious decomposition that would materially improve maintainability

    line 203
  46. Common:

    Treat these as presumptive blockers unless the author can justify them clearly:

    line 205
  47. Common:

    If those conditions are not met, leave explicit, actionable feedback and push for a cleaner decomposition.

    line 214

“Common” is measured: kept by at least 6 in 10 of the 67 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Thermo-Nuclear Code Quality Review

Never post comments on a PR unless told so - keep it in chat as default

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.

The Bar for Raising a Finding

Strict does not mean noisy. A review that raises twenty findings of which three matter is worse than one that raises three, because the author now has to do the filtering that was your job.

Only raise a finding if it satisfies at least one of these:

  1. It identifies an actual bug, correctness issue, security issue, or meaningful risk.
  2. It reduces unnecessary code or duplication.
  3. It significantly reduces complexity, or makes the code substantially easier to maintain.

If a finding satisfies none of these, drop it. Do not soften it into a "minor nit" or a "just a thought" — discard it silently. Every finding you keep should be one you would defend if the author pushed back.

Things that do not clear the bar, however strict the review: naming preferences that read the same either way, stylistic rearrangement, restructurings that relocate complexity rather than remove it, abstractions proposed for a second use case that does not exist yet, and "this is fine, but here's how I'd have written it."

The standards below describe what to look for. This gate decides whether it gets reported. When the two seem to conflict, the gate wins — a smell that produces no bug, no deletion, and no real maintainability gain is not a finding.

When nothing clears the bar, say so plainly. "No findings that meet the bar" is a legitimate outcome of a harsh review, not a failure to review hard enough.

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:

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.
  6. Push hard on type and boundary cleanliness when they affect maintainability.
    • Question unnecessary optionality, unknown, any, or cast-heavy code when a clearer type boundary could exist.
    • Prefer explicit typed models or shared contracts over loosely-shaped ad-hoc objects.
    • If a branch relies on silent fallback to paper over an unclear invariant, ask whether the boundary should be made explicit instead.
  7. Keep logic in the canonical layer and reuse existing helpers.
    • Call out feature logic leaking into shared paths or implementation details leaking through APIs.
    • Prefer existing canonical utilities/helpers over bespoke one-offs.
    • Push code toward the right package, service, or module instead of normalizing architectural drift.
  8. Treat unnecessary sequential orchestration and non-atomic updates as design smells when the cleaner structure is obvious.
    • If independent work is serialized for no good reason, ask whether the flow should run in parallel instead.
    • If related updates can leave state half-applied, push for a more atomic structure.
    • Do not over-index on micro-optimizations, but do flag avoidable orchestration complexity that makes the implementation more brittle.

Primary Review Questions

For every meaningful change, ask:

  • Is there a "code judo" move that would make this dramatically simpler?
  • Can this change be reframed so fewer concepts, branches, or helper layers are needed?
  • Does this improve or worsen the local architecture?
  • Did the diff add branching complexity where a better abstraction should exist?
  • Did a previously cohesive module become more coupled, more stateful, or harder to scan?
  • Is this logic living in the right file and layer?
  • Did this change enlarge a file or component past a healthy size boundary?
  • Are there repeated conditionals that signal a missing model or missing helper?
  • Is the implementation direct and legible, or does it rely on special cases and incidental control flow?
  • Is this abstraction actually earning its keep, or is it just a wrapper?
  • Did the diff introduce casts, optionality, or ad-hoc object shapes that obscure the real invariant?
  • Is this logic living in the canonical layer, or did the diff leak details across a boundary?
  • Is this orchestration more sequential or less atomic than it needs to be?

These questions generate candidates. Run every candidate through the bar above before it becomes a finding.

What to Flag Aggressively

Escalate findings when you see:

  • A complicated implementation where a cleaner reframing could delete whole categories of complexity.
  • Refactors that move code around but fail to reduce the number of concepts a reader must hold in their head.
  • A file crossing 1000 lines due to the PR, especially if the new code could be split out.
  • New conditionals bolted onto unrelated code paths.
  • One-off booleans, nullable modes, or flags that complicate existing control flow.
  • Feature-specific logic leaking into general-purpose modules.
  • Generic "magic" handling that hides simple structure and makes the code harder to reason about.
  • Thin wrappers or identity abstractions that add indirection without simplifying anything.
  • Unnecessary casts, any, unknown, or optional params that muddy the real contract.
  • Copy-pasted logic instead of extracted helpers.
  • Narrow edge-case handling implemented in the middle of an already busy function.
  • Refactors that technically pass tests but make the code less modular or less readable.
  • "Temporary" branching that is likely to become permanent debt.
  • Bespoke helpers where the codebase already has a canonical utility for the job.
  • Logic added in the wrong layer/package when it should live somewhere more central.
  • Sequential async flow where obviously independent work could stay simpler and clearer with parallel execution.
  • Partial-update logic that leaves state less atomic than necessary.

Preferred Remedies

When you identify a code-quality problem, prefer suggestions like:

  • Delete a whole layer of indirection rather than polishing it.
  • Reframe the state model so conditionals disappear instead of getting centralized.
  • Change the ownership boundary so the feature becomes a natural extension of an existing abstraction.
  • Turn special-case logic into a simpler default flow with fewer exceptions.
  • Extract a helper or pure function.
  • Split a large file into smaller focused modules.
  • Move feature-specific logic behind a dedicated abstraction.
  • Replace condition chains with a typed model or explicit dispatcher.
  • Separate orchestration from business logic.
  • Collapse duplicate branches into a single clearer flow.
  • Delete wrappers that do not meaningfully clarify the API.
  • Reuse the existing canonical helper instead of introducing a near-duplicate.
  • Make type boundaries more explicit so the control flow gets simpler.
  • Move the logic to the package/module/layer that already owns the concept.
  • Parallelize independent work when that also simplifies the orchestration.
  • Restructure related updates into a more atomic flow when partial state would be harder to reason about.

Do not be satisfied with "maybe rename this" feedback when the real issue is structural. Do not be satisfied with a merely cleaner version of the same messy idea if there is a plausible path to a much simpler idea.

Review Tone

Be direct, serious, and demanding about quality. Do not be rude, but do not soften major maintainability issues into mild suggestions. If the code is making the codebase messier, say so clearly. If the implementation missed an opportunity for a dramatic simplification, say that clearly too.

Good phrases:

  • this pushes the file past 1k lines. can we decompose this first?
  • this adds another special-case branch into an already busy flow. can we move this behind its own abstraction?
  • this works, but it makes the surrounding code more spaghetti. let's keep the behavior and restructure the implementation.
  • this feels like feature logic leaking into a shared path. can we isolate it?
  • this abstraction seems unnecessary. can we just keep the direct flow?
  • why does this need a cast / optional here? can we make the boundary more explicit instead?
  • this looks like a bespoke helper for something we already have elsewhere. can we reuse the canonical one?
  • i think there's a code-judo move here that makes this much simpler. can we reframe this so these branches disappear?
  • this refactor moves complexity around, but doesn't really delete it. is there a way to make the model itself simpler?

Output Expectations

Every reported finding must clear the bar in "The Bar for Raising a Finding". Make the payoff visible — the bug or risk it identifies, the code or duplication it deletes, or the complexity it removes — so the author can see why it is worth their time. If you cannot state that in a sentence, the finding is not ready to report.

Among the findings that clear the bar, prioritize in this order:

  1. Structural code-quality regressions
  2. Missed opportunities for dramatic simplification / code-judo restructuring
  3. Spaghetti / branching complexity increases
  4. Boundary / abstraction / type-contract problems that make the code harder to reason about
  5. File-size and decomposition concerns
  6. Modularity and abstraction issues
  7. Legibility and maintainability concerns

Do not flood the review with low-value nits — not below the real findings, and not as an appendix either. Prefer a smaller number of high-conviction comments over a long list of cosmetic notes.

Approval Bar

Do not approve merely because behavior seems correct. The bar for approval is:

  • no clear structural regression
  • no obvious missed opportunity to make the implementation dramatically simpler when such a path is visible
  • no unjustified file-size explosion
  • no obvious spaghetti-growth from special-case branching
  • no obviously hacky or magical abstraction that makes the code harder to reason about
  • no unnecessary wrapper/cast/optionality churn obscuring the real design
  • no clear architecture-boundary leak or avoidable canonical-helper duplication
  • no missed opportunity for an obvious decomposition that would materially improve maintainability

Treat these as presumptive blockers unless the author can justify them clearly:

  • the PR preserves a lot of incidental complexity when there is a plausible code-judo move that would delete it
  • the PR pushes a file from below 1000 lines to above 1000 lines
  • the PR adds ad-hoc branching that makes an existing flow more tangled
  • the PR solves a local problem by scattering feature checks across shared code
  • the PR adds an unnecessary abstraction, wrapper, or cast-heavy contract that makes the design more indirect
  • the PR duplicates an existing helper or puts logic in the wrong layer when there is a clear canonical home

If those conditions are not met, leave explicit, actionable feedback and push for a cleaner decomposition.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.