Testing & QA · For frontend developers

Find failing PR checks, inspect logs or external check links, and apply focused fixes

cursor/plugins

Best practices for writing new MSTest 3.x/4.x unit tests and implementing concrete fixes in existing MSTest code.

runceel/ReactiveProperty

Installs Reticle's dev-only SDK in a running web app and verifies user-facing changes by driving a real flow, returning a verdict with the file and line to fix.

reticlehq/reticle

[omh] AI agent progress for managers: help managers inspect AI-agent progress, blockers, quality gates, and throughput levers.

rlaope/oh-my-hermes

Run mutation testing to validate test quality beyond code coverage.

jmagly/aiwg

Send feedback or a bug report to the WOZCODE team. An agent skill from WithWoz/wozcode-plugin.

WithWoz/wozcode-plugin

Creates backend e2e tests for new or existing endpoints. An agent skill from letehaha/moneymatter.

letehaha/moneymatter

Runs the frontendchecklist CLI against local files or a deployed URL to check code against 380+ accessibility, performance, SEO and security rules, with fixable, cited findings.

thedaviddias/Front-End-Checklist

Coverage-improvement workflow for Raven tests through cleanup.

marinasundstrom/raven

Run a Meticulous session simulation against a live URL and analyze the visual output — either by inspecting screenshots directly (quick-check mode) or by comparing pixel and HTML diffs against a…

FlintSH/Flare

A skill your agent uses when the user wants to write, run, or troubleshoot automated regression tests for Protheus routines with ADVPR (Advanced Protheus Robot) -- covering FWTestHelper API…

thalysjuvenal/advpl-specialist

Analyze the blast radius of a proposed change before any code is written.

danielvm-git/bigpowers

Guides development workflow, design system, scripts, and component inventory for @ant-design/agentic-ui.

antdigital-ai/agentic-ui

Invoke whenever writing, changing, reviewing, or sweeping tests.

simstudioai/sim

Review work against user requirements, enumerate tasks, and verify completion with tests and formatting

tonghuikang/nemotron

This skill should be used after spec-compliance-review and before visual-diff-fix.

Jason904/ui-skill-lab

A skill your agent uses when maintaining candidate scoring, ranking, feasibility assessment, and promotion decisions.

meamaturinlove221/TuringResearch_plus

Generate failing acceptance tests using TDD cycle. An agent skill from chenjackle45/SayIt.

chenjackle45/SayIt

Add explicitly requested web renderer tests or update existing ones for implementation changes.

remotion-dev/remotion

Run automated post-deploy UI verification with a browser automation MCP (claude-in-chrome, Playwright, or Puppeteer): console-error and Core Web Vitals smoke checks, form and auth-flow interaction…

affaan-m/ECC

Independent power-user audit of a big new-feature PR. An agent skill from pydantic/pydantic-ai.

pydantic/pydantic-ai

Gate quantitative Mira conclusions by requiring reproducible data, formulas, calculation ledgers, or explicit downgrades when numbers drive judgment.

byteseek/Mira

A skill your agent uses when building features with Cursor in any codebase and the work should go through a disciplined build → review → test → fix loop.

BuildGreatProducts/builder-os

Verifies mobile app behavior end to end on the iOS simulator against a local API and relay, with strict evidence rules and an edge-case pass before anything counts as tested.

superset-sh/superset

Verify the id/key contract between backend producers and frontend consumers before implementing any change that joins, selects, persists, or attributes entities keyed by backend-produced ids (GPUs…

shm11C3/HardwareVisualizer

Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence

nyldn/claude-octopus

Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them.

Elite588/AUTOGPT

Implement an accepted NemoClaw issue or repair a classified PR finding, with focused validation.

NVIDIA/NemoClaw

Reproduce stale NemoClaw bug reports on the reported and newest releases, then propose evidence-backed triage.

NVIDIA/NemoClaw

Report a Dex bug to the Dex team with zero homework — Dex investigates locally, builds a privacy-safe report, shows it to you (or auto-sends if you've chosen that), and tracks the ticket until it's…

davekilleen/Dex

Ask Google's Antigravity CLI (agy staffer, fast Gemini) a cheap one-shot question - the fast zero-tool mode and the post-install smoke test.

keli-wen/agy-staff

File a LeetCode problem into the cheatsheets under doc/cheatsheet/ the way the existing sections are written — find the sheet whose Scope line owns the topic, file it under the pattern it belongs to…

yennanliu/CS_basics

在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发，确保单元测试、集成测试和端到端测试的覆盖率超过80%。

affaan-m/ECC

Give your AI agents something more useful than a prompt. An agent skill from DataDog/datadog-agent.

DataDog/datadog-agent

Handle a CI failure that is reliably attributed to the current PR's own code changes.

DataDog/datadog-agent

Statically review KeeForge changes since a shipped release for behavior risks, documentation inconsistencies, i18n gaps, and missing test coverage.

KeeForge/KeeForge

Unified conventions for writing Go unit/integration tests (TR-F022).

talkincode/toughradius

Investigate Mentra App bug reports and feedback from a reports Slack link or rep report ID.

Mentra-Community/MentraOS

Generate end to end automated tests for existing features. An agent skill from delorenj/mcp-server-trello.

delorenj/mcp-server-trello

Compares a generated UI screenshot with reference images and returns a strict JSON verdict with a score, differences and suggested edits to drive the next iteration.

Yeachan-Heo/oh-my-claudecode

Analyze failed Revyl test, workflow, and device-session reports via CLI to classify real bugs, flaky tests, infra issues, setup failures, or test-design improvements.

RevylAI/revyl-cli

Add or change a named Pallas/Mosaic kernel, including its reference implementation, correctness tests, wrapper, or requested tuning.

marin-community/marin

运行视觉回归测试验证代码更改是否正确，支持 basic/pastissue/complete 套件及基线更新. An agent skill from open-guji/luatex-cn.

open-guji/luatex-cn

Use this skill before answering or editing whenever an MSTest v1/v2 project is being upgraded or repaired for v3.

dotnet/skills

UVM-based functional verification — testbench architecture, test planning, directed and constrained-random stimulus, functional and code coverage closure, formal assist, and regression sign-off.

hdl-tools/digital-chip-design-agents

Run tests scoped to the current patch vs origin/main, fix any failures found in those packages (this patch's own regressions or genuinely pre-existing ones alike), then fix genuine coverage gaps on…

cloudposse/atmos

Prepare and cut one signed NemoClaw semver release tag, then follow release workflows and draft the Announcement.

NVIDIA/NemoClaw

Author, change, review, delete, or audit Happier tests through observable contracts, canonical testkits, risk-selected validation, and safe subsystem cleanup.

happier-dev/happier