NeVibeCode · collection · 30

Testing skills

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

1

agent-browser

A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website.

skill · vercel-labs · Apache-2.0

1,200,000installs
2

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
3

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
4

prototype

Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase.

skill · Matt Pocock · MIT

986,201installs
5

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
6

diagnosing-bugs

This skill guides agents through reproducing hard bugs and performance regressions with a focused feedback loop. Use it when code fails, behaves incorrectly, or runs slowly.

skill · Matt Pocock · MIT

834,802installs
7

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
8

to-spec

Turns the current conversation and repository context into a spec, then publishes it to the project issue tracker. Use it when a feature discussion is ready to hand off to an agent.

skill · Matt Pocock · MIT

715,388installs
9

design-taste-frontend

This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished.

skill · Leonxlnx · MIT

673,100installs
10

google-agents-cli-eval official

Guides testing, dataset setup, and scoring for AI agents via agents-cli. Useful for inspecting failures and running prompt optimization under the Gemini methodology.

skill · Google · Apache-2.0

510,000installs
11

google-agents-cli-workflow official

This skill guides ADK agent work from scaffolding through deployment and observability. Use it when an agent must be run, tested, published, or debugged.

skill · Google · Apache-2.0

510,000installs
12

remotion-to-hyperframes

Imports Remotion animations or video footage into HyperFrames and verifies visual matching frame by frame against the original.

skill · heygen-com · Apache-2.0

504,900installs
13

setup-pre-commit

This skill configures pre-commit checks for a JavaScript repository, running Prettier, type checking, and tests before each commit.

skill · Matt Pocock · MIT

489,289installs
14

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
15

minimal-run-and-audit

Captures and normalizes execution evidence from deep learning smoke tests and inference commands into standardized repro_outputs/ files.

skill · lllllllama · MIT

474,400installs
16

skill-creator official

Creates and refines skills, then tests them with prompts, evaluations, and performance checks.

skill · anthropics · Apache-2.0

414,180installs
17

ai-research-reproduction

This skill guides a repository-grounded reproduction run from its README to an evidence bundle. Use it to test a documented model run without quietly changing the experiment.

skill · lllllllama · MIT

335,300installs
18

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
19

implement-spec

Implements a prepared spec from its ticket graph on one integration branch, using parallel subagents. Use it when tickets have blocking dependencies.

skill · Matt Pocock · MIT

283,700installs
20

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
21

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
22

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
23

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
24

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
25

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
26

dispatching-parallel-agents

Dispatches independent tasks to separate subagents so they can investigate them in parallel. Use it for unrelated test failures and separate broken subsystems.

skill · Jesse Vincent · MIT

218,235installs
27

writing-skills

Applies a TDD workflow to authoring and checking agent skills: observe failure first, then write instructions that address it. Use it when creating or editing SKILL.md files.

skill · Jesse Vincent · MIT

217,894installs
28

using-git-worktrees

Prepares an isolated workspace before feature work or plan execution. It checks the repository first, then uses native worktree support or Git.

skill · Jesse Vincent · MIT

217,153installs
29

finishing-a-development-branch

This skill checks the test suite and guides branch completion: merge locally, open a Pull Request, or leave the work in place.

skill · Jesse Vincent · MIT

214,439installs
30

webapp-testing official

This skill tests local web apps with Playwright, helping agents debug UI behavior, capture screenshots, and inspect browser logs.

skill · anthropics · Apache-2.0

186,758installs

Testing skills ranked by repository stars and install counts, verified descriptions only. Check which runner a skill uses (pytest, Jest, Vitest, Playwright) and whether it runs the tests itself. Skip any skill that rewrites a failing test without looking for the cause. It is a plus when a skill can rerun a single failing test instead of the whole suite. To make sure tests always run, pair the skill with a hook: Claude Code hooks.

Testing skills

google-agents-cli-eval official

google-agents-cli-workflow official

skill-creator official

webapp-testing official

Other collections