Testing & QA · For developers

Validate that commands documented in skill files actually work.

microsoft/vstest

Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network…

mitsuhiko/agent-stuff

browser-based page capture and text extraction for public-opinion research.

123321kk/opinion-agent-ultimate

Replay recorded agent conversations as Playwright tests against the real chat panel and canvas.

Comfy-Org/ComfyUI_frontend

Project workflow for invoking the local review sub-agents Thomas, Helen, Beck, Jonas, The Reaper, and Heckler during LibreQoS coding sessions.

LibreQoE/LibreQoS

Start, selectively modernize, fully migrate, or update Python projects using simple-modern-uv practices: uv, ruff, BasedPyright, pytest, GitHub Actions CI, and tag-driven PyPI publishing.

jlevy/simple-modern-uv

Audit, plan, write, and verify unit tests for Python projects using pytest.

areed1192/finance-news-aggregator

Build, launch, and drive this worktree's Hive app over CDP to verify a change end-to-end with playwright-cli

morapelker/hive

Guide and audit Node.js CLI application development against 41 established best practices covering UX, distribution, interoperability, accessibility, testing, error handling, development setup…

lirantal/nodejs-cli-apps-best-practices

Adds a release eval scorecard to a GAIA hub agent by writing a harness adapter, running a real eval, and wiring the result into the agent's README and release gate.

amd/gaia

Drives and tests terminal apps, especially the Cline CLI TUI, through named background PTY sessions that an agent can read, wait on, snapshot and type into.

cline/cline

Generate working code that routes HTTP requests through Bright Data proxy networks (Datacenter, ISP, Residential, Mobile) and help users decide which network and IP pool type to use (shared pool…

brightdata/skills

Analyze retained NemoClaw CI timings for slow CLI tests, runner queues, or base-image publication.

NVIDIA/NemoClaw

Offload bulk judgment calls to Jev (TypeSafe's fast System One model) so Claude doesn't read, and pay for, content it only needs a verdict on.

UditAkhourii/quicksilver

Guide for diagnosing GitHub Actions test failures, extracting failed tests from runs, and creating or updating failing-test issues.

microsoft/aspire

Reviews a candidate pull request's diff and tests against its linked issue, with an optional live comparison against a previously captured baseline, without editing, merging or pushing.

stickerdaniel/linkedin-mcp-server

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts.

einverne/dotfiles

Record real OpenAI/Anthropic HTTP back-and-forth (requests + responses, including streaming text/event-stream) and print paste-ready Swift fixtures for SwiftAgent unit tests (ReplayHTTPClient) using…

SwiftedMind/SwiftAgent

Write correct and complete RSpec tests for Doorkeeper. An agent skill from doorkeeper-gem/doorkeeper.

doorkeeper-gem/doorkeeper

Drives a multi-turn conversation with a LiveKit agent running locally to see what it does.

livekit-examples/agent-starter-python

Debug Playwright E2E test failures from GitHub Actions CI runs.

quay/quay

使用隔离的 Chrome DevTools MCP 从博客、新闻、公众号等网页提取正文，返回结构化内容，或保存 Markdown 和远程图片。用户要求提取文章、抓取网页正文、保存为 Markdown、下载文章图片或排查正文选择器时调用。

dongbeixiaohuo/writing-agent

A skill your agent uses when adding support for a new model to VeOmni.

ByteDance-Seed/VeOmni

Verified, actionable gotchas for oh-my-posh. An agent skill from JanDeDobbeleer/oh-my-posh.

JanDeDobbeleer/oh-my-posh

Take a change from working tree to a merge-ready pull request, then keep iterating until the CI checks and AI reviewers (CodeRabbit, cubic) all pass.

noh-rs/nohrs

Cut a sim-use release end-to-end. An agent skill from lycorp-jp/sim-use.

lycorp-jp/sim-use

Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing.

openclaw/openclaw

A skill your agent uses when writing, editing, reviewing, or running Helm chart tests for the Astronomer APC repository.

astronomer/astronomer

Performs manual hands-on testing of a web application using playwright-cli.

ktnyt/cclsp

Look at Kiln's UI in a real browser, and run its end-to-end tests.

Kiln-AI/Kiln

Triage failing GitHub PR checks: list failures with gh, fetch capped Actions logs, skip non-Actions checks, and summarize root cause.

Mentra-Community/MentraOS

This skill should be used when the user asks to "dev-impl", "タスクを実装", "テストファースト実装", "implement task", "実装を開始", "クイック修正", "quick fix", "dev-impl auth 001".

classmethod/tsumiki

Version and release c15t packages with Changesets. An agent skill from c15t/c15t.

c15t/c15t

Write, fix, or review NeoServer functional tests that start from the network handler and run against the real server stack.

OpenCoreMMO/OpenCoreMMO

Verify frontend changes end to end after editing a web app, instead of manually clicking through pages.

ucsandman/marketing-studio

Runs a staged pull request or diff review using selected reviewer personas, checking the change against its stated intent and project standards before producing findings.

EveryInc/compound-engineering-plugin

Verify reader features end-to-end by importing a synthetic volume through the real upload modal and driving the reader with Playwright.

Gnathonic/mokuro-reader

Write idiomatic Effect v4 TypeScript following official best practices from effect-solutions and the Effect source.

mattiacerutti/supernova

Reproduces change-data-capture bugs in the source-mssql Airbyte connector by enabling CDC on a local SQL Server backend and replaying per-bug SQL fixtures.

airbytehq/airbyte

Guides an agent through probing an unfamiliar project's test setup, then choosing a red-light-first testing strategy matched to the task type.

huiliyi37/Tianshu-harness

Reproduce a Vaadin web component bug from a GitHub issue in vaadin/web-components.

vaadin/web-components

Guidelines and conventions for writing unit tests for linters in the r-lib/lintr package using testthat.

r-lib/lintr

Step-by-step runbook for creating, extending, and verifying integration tests in the GCSFuse repository.

GoogleCloudPlatform/gcsfuse

Capture headless-Chrome screenshots of the tingly-box frontend (running locally in mock mode) so frontend changes can be visually verified in environments without a real browser.

tingly-dev/tingly-box

Reviews a diff by anchoring on agreements between two sides of a boundary, forcing a concrete violating execution, and refuting each finding before reporting it.

phuryn/pm-skills

Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system.

microsoft/testfx

Picks the right save file and script for a KenshiCoop debugging or validation session, and protects version-controlled fixtures from being overwritten.

nhoral/KenshiCoop

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria.

shinpr/claude-code-workflows