AGENT SKILL

thermo-nuclear-code-quality-review

Run an opt-in strict maintainability review for giant files, spaghetti growth, misplaced logic, weak boundaries, unnecessary abstractions, and missed structural simplifications. Use for a thermonuclear review, harsh code-quality audit, code-judo review, or a file approaching 1000 lines. Do not use as an automatic rewrite mandate or for cosmetic cleanup.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 1
Forks
0

01 前言 Front Matter

name
thermo-nuclear-code-quality-review
description
Run an opt-in strict maintainability review for giant files, spaghetti growth, misplaced logic, weak boundaries, unnecessary abstractions, and missed structural simplifications. Use for a thermonuclear review, harsh code-quality audit, code-judo review, or a file approaching 1000 lines. Do not use as an automatic rewrite mandate or for cosmetic cleanup.
disable-model-invocation
true

03 SKILL.md 正文

Strict Code Quality Review

This is an unusually demanding review mode, not an instruction to rewrite code by taste. Inspect the current diff and surrounding architecture, then report only high-conviction findings grounded in a contract, reachable behavior, or a material maintainability risk.

Review Bar

Ask:

  • Can a simpler ownership boundary remove whole branches or concepts?
  • Did the diff add ad-hoc flags, special cases, or feature logic to a shared path instead of using the canonical layer?
  • Did a cohesive module become more coupled or cross a meaningful shape limit?
  • Are wrappers, casts, optionality, and sequential orchestration earning their complexity?
  • Does a proposed decomposition reduce what a reader must hold in mind, rather than merely move the same complexity into more files?

A file crossing roughly 1000 lines is a strong signal to inspect decomposition, not an automatic failure. Apply the project's actual shape policy and explain why a split would improve ownership. Do not manufacture a rewrite when the current structure is coherent and the change is small.

Output

Report findings in this order:

  1. structural regressions;
  2. missing simplifications with a concrete alternative;
  3. spaghetti or branching growth;
  4. boundary and type-contract problems;
  5. file shape and decomposition;
  6. lower-severity readability issues.

For each finding include file/line, contract or evidence, user/operator impact, and a concrete remedy. Separate BLOCKER, ADVISORY, and ACCEPTED decisions. If no finding survives reachability, materiality, and evidence screening, say so.

Independence and scope

Use a fresh reviewer for non-trivial changes. This review does not replace focused tests, security proof, or proof-verify; it evaluates maintainability and architecture. It must not silently edit production code or turn an advisory concern into a rewrite.

Gotchas

  • Ambition without a contract becomes over-engineering. Keep the selection gate: a sufficient implementation is a reason to stop expanding.
  • A line count is a probe, not a universal design law.
  • Moving code across files without reducing coupling is not a successful decomposition.
  • Passing tests do not erase a material architecture regression, but a style preference without impact is not a blocker.

Troubleshooting

Symptom Likely cause Action
Review proposes a rewrite for a tiny diff Scope or trigger was too broad Limit the review to changed behavior and material risks
Many low-value nits No severity/materiality screen Keep only findings with evidence and an actionable remedy
File is large but coherent Threshold treated as a verdict Record ACCEPTED with rationale and keep the stable boundary
Suggested split adds more indirection Complexity moved, not removed Reject it and compare the reader's concepts before/after

Source

Adapted from Cursor Team Kit's MIT-licensed thermo-nuclear-code-quality-review: https://github.com/cursor/plugins/tree/main/cursor-team-kit/skills/thermo-nuclear-code-quality-review

04 同仓库更多 Skills

hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

owner-voice

暂无简介

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

humanize-russian

Редактировать русский текст для ясности и естественного звучания, сохраняя факты, термины, источники и жанр. Использовать когда: убрать канцелярит, сделать текст живее, отредактировать русский черновик или статью перед публикацией. Не определяет авторство и не обещает обход детекторов. Для английского — humanize-english; для структуры и доказательств — article-structure-review.

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

humanize-english

Edit English drafts for clear, natural language while preserving facts, uncertainty, technical meaning, citations and genre. Use when: humanize this text, remove AI-style filler, improve English prose, or edit an English article before publication. Not an authorship detector or a promise to bypass one. For Russian use humanize-russian; for thesis/evidence and structure use article-structure-review.

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

caveman

Ultra-compressed reply mode. Cuts output tokens ~65-75% by answering in terse "caveman" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman", "talk like caveman", "use caveman", "less tokens", "be brief", or Russian "пещерный режим", "говори как пещерный", "кратко", "меньше токенов", "экономь токены" — or invokes /caveman. Preserves the user's language (Russian in → Russian caveman out). Off only: "stop caveman" / "normal mode" / "обычный режим". Do not use merely because a response should be concise, and do not use when the user requests normal prose, a polished document, or exact wording.

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

article-structure-review

Проверить структуру технической статьи после черновика: задача читателя, жанр, опора значимых утверждений на доказательства и честные ограничения. Use after the first draft, before publication. Исправлять структуру, когда это входит в запрос; не создавать обязательный конвейер из других навыков. Для локальной языковой редактуры — humanize-english или humanize-russian.

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

video-post-production

Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standards, and platform-specific export configs. Do NOT use to generate or animate the video frames/scenes in code (use remotion-production-guide), to write the script (use video-narrative-arc), or to evaluate script quality (use script-evaluator); this is the finishing stage applied to an already-rendered video.

★ 1