thermo-nuclear-code-quality-review — Claude Code skill: review
Runs a strict maintainability audit of code changes, abstractions, large files, and branching complexity. Use it when a routine review needs deeper structural scrutiny.
npx skills add cursor/plugins --skill thermo-nuclear-code-quality-review -a claude-codeWhat thermo-nuclear-code-quality-review does
This skill audits changes in the current branch and looks for ways to simplify the implementation without changing behavior. It asks the reviewer to rethink abstractions, reduce branching, split overloaded modules, and remove layers that do not clarify the code.
The review checks large files, ad hoc conditionals, thin wrappers, unclear type boundaries, and feature logic leaking across layers. It also questions reuse of canonical helpers, avoidable sequential orchestration, and updates that can leave state partly applied.
A file crossing 1000 lines is treated as a reason to consider extracting a module or helper. Automatic invocation is disabled, so the review must be requested explicitly.
What it helps with
- audit the current branch for maintainability issues
- break up files that grow past a healthy size
- replace ad hoc conditionals with clearer structure
- check type and module boundaries for hidden assumptions
- remove wrappers that add indirection without clarity
Example prompts for the agent
- Run a strict maintainability audit of the current branch and suggest structural changes that preserve behavior.
- Check whether the changed file crosses 1000 lines and look for ad hoc branches in unrelated code paths.
- Review the abstractions, type boundaries, and module ownership in this change, then identify ways to simplify it.
How to install thermo-nuclear-code-quality-review
1Skills CLI (Vercel)
npx skills add cursor/plugins --skill thermo-nuclear-code-quality-review -a claude-code2Manually: put the files in place
~/.claude/skills/thermo-nuclear-code-quality-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/thermo-nuclear-code-quality-review/
1Skills CLI (Vercel)
npx skills add cursor/plugins --skill thermo-nuclear-code-quality-review -a codex2Manually: put the files in place
.agents/skills/thermo-nuclear-code-quality-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add cursor/plugins --skill thermo-nuclear-code-quality-review -a cursor2Manually: put the files in place
.cursor/skills/thermo-nuclear-code-quality-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install cursor/plugins thermo-nuclear-code-quality-review2Manually: put the files in place
.github/skills/thermo-nuclear-code-quality-review/SKILL.md1Skills CLI (Vercel)
npx skills add cursor/plugins --skill thermo-nuclear-code-quality-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/cursor/plugins --path cursor-team-kit/skills/thermo-nuclear-code-quality-reviewManually: put the files in place
.devin/skills/thermo-nuclear-code-quality-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add cursor/plugins --skill thermo-nuclear-code-quality-review -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set3
The whole set →Similar
Questions about thermo-nuclear-code-quality-review
How do I install thermo-nuclear-code-quality-review in Claude Code?
Run npx skills add cursor/plugins --skill thermo-nuclear-code-quality-review -a claude-code, then run npx skills add cursor/plugins --skill thermo-nuclear-code-quality-review -a claude-code again. Verify ~/.claude/skills/thermo-nuclear-code-quality-review/SKILL.md afterward.
What does thermo-nuclear-code-quality-review do?
It performs a strict maintainability review and challenges implementations that work but leave the structure harder to understand. It focuses on abstractions, large files, branching complexity, type boundaries, and logic placed in the wrong layer.
Which platforms support this skill?
It is intended for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. Automatic invocation is disabled, so you need to request the review explicitly.