Skip to main content
NeVibeCode · 439 items

Code review and refactoring: skills, plugins, subagents, slash commands and mcp servers

Code review and refactoring for Claude Code, Codex and Cursor: skills, plugins, subagents, slash commands and mcp servers, from popular to niche.

439 items
improve-codebase-architecture Matt Pocock skill This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs tdd Matt Pocock skill Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs triage Matt Pocock skill This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. Claude Code 990,453installs codebase-design Matt Pocock skill This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write. Claude Code 850,344installs code-review Matt Pocock skill Reviews changes from a chosen reference point against repository standards and the originating spec. Use it for a branch, PR, or work in progress. Claude Code 789,521installs implement Matt Pocock skill Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine. Claude Code 774,700installs migrate-to-shoehorn Matt Pocock skill Replaces as type assertions in tests with helpers from @total-typescript/shoehorn. Use it when tests need partial objects or deliberately invalid data. Claude Code 475,388installs systematic-debugging Jesse Vincent skill Makes the agent investigate the cause of a failure before it suggests a patch. Use it for failing tests, build errors, and behaviour that does not match expectations. Claude Code CX Codex 306,118installs requesting-code-review Jesse Vincent skill Sends completed work to a reviewer subagent after a task, major feature, or before merging to main. It keeps the review focused on the change and its requirements. Claude Code CX Codex 262,135installs test-driven-development Jesse Vincent skill This skill guides an agent through test-first development: verify a test fails, write the smallest passing change, then refactor. It covers features, bug fixes, and behavior changes. Claude Code CX Codex 259,292installs verification-before-completion Jesse Vincent skill This skill blocks completion claims until the agent runs a fresh check and reads the result. Use it before commits or PRs when an agent report is not enough. Claude Code CX Codex 251,313installs executing-plans Jesse Vincent skill Runs an implementation plan in the current session instead of assigning each task to a subagent. Use it for inline work with TDD, a decision ledger, and a final branch review. Claude Code CX Codex 242,988installs subagent-driven-development Jesse Vincent skill This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. Claude Code CX Codex 237,746installs receiving-code-review Jesse Vincent skill Reviews code review feedback before changes: it clarifies unclear points, checks the repository, and supports reasoned pushback. Use it before acting on review comments. Claude Code CX Codex 221,216installs retro Matt Pocock skill Reviews a coding session and suggests changes to the agent environment for later runs. Use it after mistakes, slow repository navigation, or costly tool calls. Claude Code 276,027installs caveman-review JuliusBrussee skill Generates terse, single-line code review comments with exact line numbers, problems, and fixes. Eliminates conversational filler in pull request reviews. Claude Code CX Codex Cursor +1 410,700installs cavecrew JuliusBrussee skill cavecrew delegates code searches, small edits, and diff reviews to three subagents. Use it when keeping the main agent's context lean matters. Claude Code CX Codex Cursor +1 357,900installs karpathy-guidelines multica-ai skill Guidelines that cut typical LLM coding mistakes: less overcomplication, surgical edits, verifiable outcomes. Claude Code CX Codex Cursor +1 42,500installs vercel-composition-patterns vercel skill A rule set that pushes your agent away from boolean props and toward compound components, shared context and state lifted into providers. Claude Code CX Codex Cursor +1 416,700installs ponytail DietrichGebert skill ponytail puts an agent into a senior-dev mode focused on the smallest complete change. Use it when you want clear replies and less code added to a project. Claude Code CX Codex Cursor +1 105,000installs emil-design-eng emilkowalski skill This skill guides UI polish, component details, and animation choices. Use it when an interface works but its states and transitions need closer review. Claude Code CX Codex Cursor +1 385,500installs review-animations emilkowalski skill Reviews UI animation and motion code against Emil Kowalski's design standards. Flags slow easings, non-GPU properties, and unnecessary transitions. Claude Code CX Codex Cursor +1 254,100installs ponytail-review DietrichGebert skill ponytail-review reviews a change beyond the diff, checking connected code, bugs, risks, load, tests, speed, and unnecessary code. Use it for PRs and commits. Claude Code CX Codex Cursor +1 56,300installs improve-animations emilkowalski skill Surveys motion and animation code across your project, then generates self-contained fix plans. It spots janky keyframes and poor easing without altering source files. Claude Code CX Codex Cursor +1 222,000installs find-animation-opportunities emilkowalski skill Scans a codebase or UI for motion that would clarify states and interactions, while rejecting decoration that gets in the way. It is read-only. Claude Code CX Codex Cursor +1 206,800installs caveman-explore JuliusBrussee skill A read-only skill locates relevant files and line ranges in a repository. Use it for cold-start orientation or broad searches. Claude Code CX Codex Cursor +1 106,500installs caveman-learn JuliusBrussee skill This skill reads Caveman learn reports, proposes token-cost reductions, and asks for consent before each edit. Use it for heavy CLAUDE.md files or repeated context. Claude Code CX Codex Cursor +1 105,700installs safe-refactor JuliusBrussee skill Restructures code while preserving existing behavior, enforcing verification boundaries before structural edits. Claude Code CX Codex Cursor +1 105,500installs caveman-optimize JuliusBrussee skill This skill turns a Caveman report observation into an operator-selected candidate and a paired baseline evaluation. Approval is required before code changes. Claude Code CX Codex Cursor +1 104,800installs ponytail-audit DietrichGebert skill It audits a repository and ranks bugs, risks, and redundant code in a one-shot report. Use it when you need a review without code changes. Claude Code CX Codex Cursor +1 44,800installs investigate-first JuliusBrussee skill The skill keeps the agent in diagnosis mode: gather evidence, rank hypotheses, name the cause. Only then does it touch code. Claude Code CX Codex Cursor +1 104,400installs surgical-patch JuliusBrussee skill The skill constrains AI coding agents to the narrowest layer responsible for a bug. It prevents unwanted refactoring and demands focused regression checks. Claude Code CX Codex Cursor +1 103,800installs lean-build JuliusBrussee skill Prevents overbuilding when adding new features or integrations. It sets strict acceptance bounds, cuts speculative abstractions, and stops immediately once proof passes. Claude Code CX Codex Cursor +1 103,500installs caveman-evidence-review JuliusBrussee skill A read-only skill reviews Caveman Cloud evidence on LLM spend, traces, and routing. Use it to see where a project’s model budget goes. Claude Code CX Codex Cursor +1 103,500installs ponytail-debt DietrichGebert skill Turns every deliberate ponytail shortcut into one debt ledger: file, line, the ceiling the comment names, and the trigger for revisiting it. Claude Code CX Codex Cursor +1 42,200installs ponytail-gain DietrichGebert skill Displays measured benchmark savings across code volume, token spend, and execution time for Ponytail. Useful when evaluating the toolset. Claude Code CX Codex Cursor +1 40,300installs migrate-radix-to-base shadcn-ui skill Migrates React components and full projects from Radix UI to Base UI (@base-ui/react). Useful when switching the underlying primitives in shadcn/ui projects. Claude Code CX Codex Cursor +1 30,100installs security-audit cloudflare skill Reviews codebases and APIs for vulnerabilities using safe sandboxing. Fits pre-release security reviews, pen-test triage, and architecture checks. Claude Code CX Codex Cursor +1 52,200installs write-swift emilkowalski skill This skill guides Swift coding, reviews, and migrations using the language’s current practices. Use it to investigate concurrency errors, hangs, data races, or retain cycles. Claude Code CX Codex Cursor +1 117,500installs code-review-and-quality addyosmani skill Five review axes and a limit on diff size, so an agent checks a change before merge instead of after. Claude Code CX Codex Cursor +1 72,500installs

1–40 of 439

Code review and refactoring: the agent reads a diff, hunts for bugs, duplication and needless complexity, and suggests simplifications. Subagents shine here, since a reviewer with its own context does not carry the edit history and reads the code fresh. When choosing, check what the skill does with its findings: write a report or edit files straight away. The second is convenient and risky in a shared repository.

More in NeVibeCode

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor