New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Thermonuclear Code Quality Review

by bangle-io in bangle-io/bangle-io

Perform an unusually strict code-quality audit focused on structural simplification, maintainability, abstraction quality, file growth, branching complexity, type boundaries, architectural…

AGPL-3.0Auto-check passedDevelopment

Install Thermonuclear Code Quality Review

skills CLI
$ npx skills add bangle-io/bangle-io --skill thermonuclear-code-quality-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bangle-io/bangle-io thermonuclear-code-quality-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bangle-io/bangle-io.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/thermonuclear-code-quality-review .claude/skills/thermonuclear-code-quality-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
thermonuclear-code-quality-review
GitHub stars
1.2k
Token cost
~1.4k tokens
SKILL.md length
689 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Perform an unusually strict code-quality audit focused on structural simplification, maintainability, abstraction quality, file growth, branching complexity, type boundaries, architectural…

  • Works in 5 steps: Read the repository instructions and run… → Inspect the working tree, branch, merge… → Identify the owning packages and read… → …
  • Thermonuclear reviews
  • SKILL.md covers Establish the review scope, Apply the approval bar, Search for code-judo… and Inspect aggressively, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Thermonuclear Code Quality Review is an agent skill from bangle-io/bangle-io. Perform an unusually strict code-quality audit focused on structural simplification, maintainability, abstraction quality, file growth, branching complexity, type boundaries, architectural ownership, and test quality. Use for thermonuclear reviews, deep maintainability audits, harsh code-quality reviews, or reviews that should seek ambitious behavior-preserving restructuring rather than local cleanup.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Code quality. The repository describes itself as: A web only WYSIWYG note taking app that saves notes locally in markdown format. v2: https://app.bangle.io/. The licence is AGPL-3.0.

When your agent uses it

  • Thermonuclear reviews
  • Deep maintainability audits
  • Harsh code-quality reviews
  • Reviews that should seek ambitious behavior-preserving restructuring rather than local cleanup

Example prompts

  • “/thermonuclear-code-quality-review”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read the repository instructions and run commands from the repository root.
  2. Inspect the working tree, branch, merge base, diff statistics, and complete diff. Include staged and unstaged changes.
  3. Identify the owning packages and read enough surrounding code to understand canonical helpers, dependency boundaries, and existing state…
  4. Measure changed file sizes before accepting file growth.
  5. Run relevant validation when practical. Never hide failures; distinguish introduced failures from existing ones.

What it can do on your machine

Read from SKILL.md and the folder at commit c3310c5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Thermonuclear Code Quality Review loads about 1.4k tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 689 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~110
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from bangle-io/bangle-io at commit c3310c5, republished under its AGPL-3.0 licence (© bangle-io). 689 words, ~1,366 tokens.

Download SKILL.mdSave it as .claude/skills/thermonuclear-code-quality-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
thermonuclear-code-quality-review
description
Perform an unusually strict code-quality audit focused on structural simplification, maintainability, abstraction quality, file growth, branching complexity, type boundaries, architectural ownership, and test quality. Use for thermonuclear reviews, deep maintainability audits, harsh code-quality reviews, or reviews that should seek ambitious behavior-preserving restructuring rather than local cleanup.

Thermonuclear Code Quality Review

Audit the current branch's changes with an approval bar substantially higher than “works and passes tests.” Seek behavior-preserving restructurings that make the implementation smaller, more direct, and easier to reason about.

Establish the review scope

  1. Read the repository instructions and run commands from the repository root.
  2. Inspect the working tree, branch, merge base, diff statistics, and complete diff. Include staged and unstaged changes.
  3. Identify the owning packages and read enough surrounding code to understand canonical helpers, dependency boundaries, and existing state models.
  4. Measure changed file sizes before accepting file growth.
  5. Run relevant validation when practical. Never hide failures; distinguish introduced failures from existing ones.

Do not modify code unless the user explicitly asks for implementation. A review request authorizes inspection and validation, not fixes.

Apply the approval bar

Block approval when any of these conditions has no compelling justification:

  • The change preserves incidental complexity that a plausible restructuring could delete.
  • A file crosses from below 1,000 lines to above 1,000 lines.
  • Feature checks or ad-hoc conditionals are scattered through unrelated flows.
  • Feature logic leaks into a shared path or the wrong architectural layer.
  • A wrapper, generic mechanism, cast-heavy contract, or optional parameter adds indirection without clarifying an invariant.
  • The change duplicates a canonical helper, state transition, lifecycle, or orchestration flow.
  • Related updates can leave partial state, or independent work is needlessly serialized.
  • Tests pass while the implementation makes the surrounding code harder to maintain.

Do not approve merely because behavior appears correct.

Search for code-judo simplifications

For every meaningful change, ask:

  • Can the model be reframed so entire branches, flags, modes, helpers, or layers disappear?
  • Can ownership move to the layer that already owns the concept?
  • Can two parallel workflows become one parameterized lifecycle or typed state transition?
  • Can a special case become part of the default flow?
  • Can an abstraction be deleted in favor of direct code?
  • Can duplicated business rules move to the lowest valid shared package?
  • Can explicit types remove casts, silent fallbacks, or unnecessary optionality?
  • Can orchestration become atomic or parallel while remaining clearer?

Prefer simplifications that reduce the number of concepts a reader must hold. Moving the same complexity into more files is not a successful refactor.

Show full SKILL.md (318 more words)Show less

Inspect aggressively

Prioritize these review categories:

  1. Structural regressions and missed dramatic simplifications.
  2. Spaghetti growth: new flags, nullable modes, special-case branches, and incidental control flow.
  3. State ownership, atomicity, lifecycle cleanup, async ordering, and failure behavior.
  4. Architectural boundaries, canonical helpers, and package placement.
  5. Type and API boundary cleanliness.
  6. File-size growth and decomposition.
  7. Test quality, especially whether regression tests prove user-visible behavior and failure paths.
  8. Legibility issues that materially increase maintenance cost.

Treat these patterns as strong smells:

  • Multiple components independently managing the same draft, commit, dismiss, focus, or persistence lifecycle.
  • UI observers redefining core commands to fit a local state model.
  • Shared atoms or registries without explicit per-owner identity and cleanup.
  • Copy-pasted condition chains with small variations.
  • Broad unknown, any, assertions, or silent fallback masking an unclear contract.
  • Generic “magic” handling that hides a simple known data shape.
  • Thin pass-through wrappers that do not reduce caller complexity.
  • Tests that delete failure coverage after a refactor or only verify the happy path.
  • Unrelated fixes added to compensate for a side effect introduced elsewhere.

Validate findings

Trace each suspected issue through callers, state transitions, and tests. Prefer a smaller number of high-confidence findings over speculative or cosmetic comments.

For each finding:

  • State the concrete failure or maintainability cost.
  • Explain why the current structure causes it.
  • Identify the smallest coherent structural remedy.
  • Cite a tight file and line range.
  • Assign severity based on impact, not rhetorical force.

If a restructuring is only a preference and does not materially improve maintainability, omit it.

Report the review

Lead with findings ordered by severity. Use inline code comments when supported. Keep summaries brief and include:

  • Whether the change meets the thermonuclear approval bar.
  • Validation commands run and their exact outcomes.
  • Any important testing gaps or assumptions.
  • An explicit statement when no high-confidence findings remain.

Do not flood the review with naming or formatting nits while structural issues remain.

© bangle-io, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .codex/skills/thermonuclear-code-quality-review of bangle-io/bangle-io.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit c3310c5

Compare with similar skills

Thermonuclear Code Quality Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Thermonuclear Code Quality Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Thermonuclear Code Quality Review this skillbangle-io/bangle-io1.2k—~1.4kAutomated safety check: PassAGPL-3.0
WooCommerce Code Reviewwoocommerce/woocommerce11k3 repos~1.1kAutomated safety check: PassCustom licence
Systematic Code Refactoringluongnv89/claude-howto42k—~3kAutomated safety check: PassMIT
Install Anti-Slop Oxlint Rulesdmmulroy/anti-slop5.3k—~2.2kAutomated safety check: PassMIT
Constraint-Driven Developmentaddyosmani/agent-skills103k2 repos~5.2kAutomated safety check: PassMIT
Skill Doli Code ReviewDolibarr/dolibarr7.7k1 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Systematic Code Refactoring

    luongnv89/claude-howto

    Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.

    42k GitHub stars~3k tokensUpdated 9 days ago
    DevelopmentAuto-check passed

  • Install Anti-Slop Oxlint Rules

    dmmulroy/anti-slop

    Installs, updates or migrates the vendored anti-slop Oxlint plugin in a repository, keeping local rule changes and the plugin's license and provenance files.

    5.3k GitHub stars~2.2k tokensUpdated 28 days ago
    DevelopmentAuto-check passed

  • Constraint-Driven Development

    addyosmani/agent-skills

    Records a project's quality bar in CONSTRAINTS.md and watches diffs for signs an agent quietly weakened it, such as suppressions, skipped tests or lowered thresholds.

    103k GitHub starsUsed in 2 repos~5.2k tokens
    DevelopmentAuto-check passed

  • Skill Doli Code Review

    Dolibarr/dolibarr

    Reviews Dolibarr PHP code for compliance with coding standards and security best practices, and fixes identified issues.

    7.7k GitHub starsUsed in 1 repo~1.1k tokens
    DevelopmentAuto-check passed

  • Ponytail Lazy Developer Mode

    DietrichGebert/ponytail

    Makes the agent pick the laziest solution that works: skip unneeded work, reuse what exists, prefer the standard library and platform features, and keep diffs small.

    159k GitHub stars~873 tokensUpdated today
    DevelopmentAuto-check passed

More from bangle-io/bangle-io

  • Bangle Project Operator

    bangle-io/bangle-io

    Keep the Bangle 2 GitHub Project aligned with the bangle-io repository.

    1.2k GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check passed

  • Wordgard

    bangle-io/bangle-io

    Write idiomatic Wordgard editor code (schema elements, extensions, commands, decorations, markdown specs) for the editor-w stack.

    1.2k GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed

  • Bangle Desktop Release

    bangle-io/bangle-io

    Build, test, package, and release the Bangle.io Electron desktop app.

    1.2k GitHub stars~297 tokensUpdated 3 days ago
    Auto-check passed

  • Bangle Followup Operator

    bangle-io/bangle-io

    Operate recurring Bangle.io agent follow-ups after a thread has already started.

    1.2k GitHub stars~991 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Thermonuclear Code Quality Review

What does Thermonuclear Code Quality Review do?

Perform an unusually strict code-quality audit focused on structural simplification, maintainability, abstraction quality, file growth, branching complexity, type boundaries, architectural…. Thermonuclear Code Quality Review is an agent skill from bangle-io/bangle-io. Perform an unusually strict code-quality audit focused on structural simplification, maintainability, abstraction quality, file growth, branching complexity, type boundaries, architectural ownership, and test quality.

When should I use Thermonuclear Code Quality Review?

Thermonuclear Code Quality Review fits situations like: thermonuclear reviews; deep maintainability audits; harsh code-quality reviews; reviews that should seek ambitious behavior-preserving restructuring rather than local cleanup.

How do I install Thermonuclear Code Quality Review in Claude Code?

Run `npx skills add bangle-io/bangle-io --skill thermonuclear-code-quality-review -a claude-code`. Or copy the skill folder (.codex/skills/thermonuclear-code-quality-review in bangle-io/bangle-io) into .claude/skills/thermonuclear-code-quality-review in your project. Claude Code loads it when a task matches its description.

How do I install Thermonuclear Code Quality Review in Codex?

Run `npx skills add bangle-io/bangle-io --skill thermonuclear-code-quality-review -a codex`. Or copy the skill folder (.codex/skills/thermonuclear-code-quality-review in bangle-io/bangle-io) into .agents/skills/thermonuclear-code-quality-review in your project. Codex loads it when a task matches its description.

Can I use Thermonuclear Code Quality Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bangle-io/bangle-io --skill thermonuclear-code-quality-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/thermonuclear-code-quality-review, .gemini/skills/thermonuclear-code-quality-review, .github/skills/thermonuclear-code-quality-review and .opencode/skills/thermonuclear-code-quality-review in your project.

What does Thermonuclear Code Quality Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Thermonuclear Code Quality Review is instructions for the agent only.

Does Thermonuclear Code Quality Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Thermonuclear Code Quality Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Thermonuclear Code Quality Review use?

Thermonuclear Code Quality Review is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Thermonuclear Code Quality Review use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Thermonuclear Code Quality Review?

Skills that share tags, products or a category with Thermonuclear Code Quality Review: WooCommerce Code Review (woocommerce/woocommerce, 11k stars), Systematic Code Refactoring (luongnv89/claude-howto, 42k stars), Install Anti-Slop Oxlint Rules (dmmulroy/anti-slop, 5.3k stars) and Constraint-Driven Development (addyosmani/agent-skills, 103k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Thermonuclear Code Quality Review?

bangle-io (a GitHub organization) maintains it in bangle-io/bangle-io, which has 1,234 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 5, 2026.

Source: bangle-io/bangle-io on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.