NeVibeCode · collection · 30

Code review skills

Ordered by install count from the source, then by repository stars on GitHub. Only cards with a checked description are included.

1

improve-codebase-architecture

This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review.

skill · Matt Pocock · MIT

1,163,035installs
2

tdd

Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details.

skill · Matt Pocock · MIT

1,141,062installs
3

triage

This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue.

skill · Matt Pocock · MIT

990,453installs
4

codebase-design

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.

skill · Matt Pocock · MIT

850,344installs
5

code-review

Reviews changes from a chosen reference point against repository standards and the originating spec. Use it for a branch, PR, or work in progress.

skill · Matt Pocock · MIT

789,521installs
6

implement

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.

skill · Matt Pocock · MIT

774,700installs
7

migrate-to-shoehorn

Replaces as type assertions in tests with helpers from @total-typescript/shoehorn. Use it when tests need partial objects or deliberately invalid data.

skill · Matt Pocock · MIT

475,388installs
8

vercel-composition-patterns

A rule set that pushes your agent away from boolean props and toward compound components, shared context and state lifted into providers.

skill · vercel · MIT

416,700installs
9

caveman-review

Generates terse, single-line code review comments with exact line numbers, problems, and fixes. Eliminates conversational filler in pull request reviews.

skill · JuliusBrussee · Apache-2.0

410,700installs
10

emil-design-eng

This skill guides UI polish, component details, and animation choices. Use it when an interface works but its states and transitions need closer review.

skill · emilkowalski · MIT

385,500installs
11

cavecrew

cavecrew delegates code searches, small edits, and diff reviews to three subagents. Use it when keeping the main agent's context lean matters.

skill · JuliusBrussee · Apache-2.0

357,900installs
12

analyze-project

Reads a deep learning repository and maps its structure, entrypoints and suspicious spots. Changes nothing, runs no heavy jobs.

skill · lllllllama · MIT

335,500installs
13

systematic-debugging

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.

skill · Jesse Vincent · MIT

306,118installs
14

retro

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.

skill · Matt Pocock · MIT

276,027installs
15

requesting-code-review

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.

skill · Jesse Vincent · MIT

262,135installs
16

test-driven-development

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.

skill · Jesse Vincent · MIT

259,292installs
17

review-animations

Reviews UI animation and motion code against Emil Kowalski's design standards. Flags slow easings, non-GPU properties, and unnecessary transitions.

skill · emilkowalski · MIT

254,100installs
18

verification-before-completion

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.

skill · Jesse Vincent · MIT

251,313installs
19

executing-plans

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.

skill · Jesse Vincent · MIT

242,988installs
20

subagent-driven-development

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.

skill · Jesse Vincent · MIT

237,746installs
21

improve-animations

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.

skill · emilkowalski · MIT

222,000installs
22

receiving-code-review

Reviews code review feedback before changes: it clarifies unclear points, checks the repository, and supports reasoned pushback. Use it before acting on review comments.

skill · Jesse Vincent · MIT

221,216installs
23

find-animation-opportunities

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.

skill · emilkowalski · MIT

206,800installs
24

firebase-security-rules-auditor

Audits Firebase rules for data leaks, privilege escalation, and validation gaps. Use it when reviewing Firestore or Cloud Storage access.

skill · Google LLC · Apache-2.0

138,200installs
25

workers-best-practices

Guides coding agents on production Cloudflare Workers standards, Wrangler typing, observability setup, and runtime anti-pattern checks.

skill · cloudflare · Apache-2.0

124,900installs
26

write-swift

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.

skill · emilkowalski · MIT

117,500installs
27

durable-objects

This skill helps build, debug, and review Cloudflare Durable Objects for state, coordination, and persistent connections.

skill · cloudflare · Apache-2.0

109,700installs
28

caveman-explore

A read-only skill locates relevant files and line ranges in a repository. Use it for cold-start orientation or broad searches.

skill · JuliusBrussee · Apache-2.0

106,500installs
29

caveman-learn

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.

skill · JuliusBrussee · Apache-2.0

105,700installs
30

safe-refactor

Restructures code while preserving existing behavior, enforcing verification boundaries before structural edits.

skill · JuliusBrussee · Apache-2.0

105,500installs

Code review skills

Other collections