Skip to content
Agentmart
Submit a tool

maintainability-review

Run an unusually strict maintainability review for structural simplification, abstraction quality, file growth, branching, types, boundaries, and codebase…

Skill by paulorsv01

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/paulorsv01-maintainability-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Run an unusually strict maintainability review for structural simplification, abstraction quality, file growth, branching, types, boundaries, and codebase health.

Use cases: marketing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/maintainability-review

What's inside

Skill name
maintainability-review
Description
Run an unusually strict maintainability review for structural simplification, abstraction quality, file growth, branching, types, boundaries, and codebase health.
License
MIT
Instructions
21 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • openai.yaml · agents/
  • code-quality-review.md · references/

SKILL.md (first lines)

# Thermo-Nuclear Code Quality Review

Review only the added or modified code and its demonstrated structural effects. Remain read-only unless the user separately asks for fixes.

Read the [canonical code-quality rubric](references/code-quality-review.md) in full before reviewing. Apply its code-judo, file-size, branching, boundary, type, canonical-layer, atomicity, and approval-bar rules.

## Workflow

1. Resolve the intended change and the smallest correct diff.
2. Read surrounding modules only as needed to judge ownership, reuse, and structural effects.
3. Search for an implementation shape that deletes concepts, branches, wrappers, or state.
4. Test every candidate finding against intended behavior and repository conventions.
5. Return a small set of high-conviction findings instead of cosmetic volume.

## Output

Order findings by structural regression, missed simplification, branching growth, boundary or type problems, file growth, then smaller maintainability concerns.

Each finding names `file:line`, the concrete maintenance cost, and the cleaner structural direction. If the implementation meets the rubric, approve it directly and name the strongest checks performed.

From paulorsv01/agents, MIT.

More from paulorsv01/agents

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 24, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from paulorsv01

Cite this page

maintainability-review skill. Agent Mart. https://agentmart.dev/skills/paulorsv01-maintainability-review (last updated 2026-10-24)