Testing & QA · pnpm

Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

bytedance/deer-flow

Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.

different-ai/openwork

Runs and debugs evaluations of how Chatbox models answer questions about large attached files, using synthetic and real long-document fixtures.

chatboxai/chatbox

Prepares the current DevSpace checkout or worktree for isolated local manual QA, covering QA state seeding, UI asset builds and snapshot resets.

Waishnav/devspace

Minimal starter runbook for cloud agents to install dependencies, run packages, execute tests, and troubleshoot the Scalar monorepo quickly.

scalar/scalar

A skill your agent uses when starting or verifying Hermes Agent CN Desktop with the latest Hermes-CN-Desktop and Hermes-CN-Core branches — dev smoke test (pnpm tauri:dev), packaged beta/release…

Eynzof/Hermes-CN-Desktop

Workflow for WooCommerce development: run PHP and JavaScript tests, lint and fix code style on the current branch, and follow guides for i18n and markdown.

woocommerce/woocommerce

Run this repository's local CI parity commands and pnpm run ci:local jobs.

module-federation/core

Launch and drive Yep Anywhere — an isolated dev server plus real browser interaction — and run the repository's check suite.

kzahel/yepanywhere

Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.

different-ai/openwork

Testing CKEditor 5 plugins in the Trilium monorepo. An agent skill from TriliumNext/Trilium.

TriliumNext/Trilium

Figures out which rebuild and test suites actually cover a change in the verdaccio monorepo, instead of a scoped run that passes untested.

verdaccio/verdaccio

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

Comfy-Org/ComfyUI_frontend

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

tmux for AI agents. An agent skill from remorses/tuistory.

remorses/tuistory

Run tests and add Next.js version coverage for the cache handler.

trieb-work/nextjs-turbo-redis-cache

A skill your agent uses when manually verifying a Chorus frontend change in a real browser — finding local login credentials, driving the running dev server with the Playwright MCP, logging in…

Chorus-AIDLC/Chorus

Run, write, and debug Playwright E2E tests for this project.

Asvarox/allkaraoke

Run a local pnpm monorepo CI loop, fix failures, and stop only when the full sequence is green.

gronxb/hot-updater

Home Assistant frontend testing and validation workflow. An agent skill from home-assistant/frontend.

home-assistant/frontend

Run the full OpenPlayerJS verification gauntlet before committing, opening a PR, or preparing a release.

openplayerjs/openplayerjs

Launches a standalone Chrome or Chromium in a Daytona sandbox and drives it over CDP for web sign-in, OAuth and other flows that should bypass the Electron app.

Devin-AXIS/iPolloWork

Multi-platform browser login and video upload via Playwright Test only (headed Chromium).

szhshp/panda-video-generator

Verify PR readiness before requesting review or merging. An agent skill from Azure/LogicAppsUX.

Azure/LogicAppsUX

This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only…

tzachbon/smart-ralph

Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate.

ZenUml/web-sequence

Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.

openclaw/openclaw

使用 Bun 1.4 内置的 Bun.WebView 无头浏览器对前端页面（Vue/Vite 等）做端到端冒烟与交互测试。当需要加载页面、真实点击、读取 DOM/应用状态、做断言、截图归档，或对本地开发服务器/静态站点做零依赖的浏览器级验证、可视化巡检、交互回归测试时，应使用本技能。

pa001024/dna-builder

Reproduce and fix bugs using TDD. An agent skill from stacklok/toolhive-studio.

stacklok/toolhive-studio

Testing workflow for the Rstest monorepo. An agent skill from web-infra-dev/rstest.

web-infra-dev/rstest

Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the teste2edeployrelease.yml GitHub Actions workflow.

vercel/next.js

A skill your agent uses when asked to run, boot, start, dev-serve, smoke-test, or drive the SEO Office app, or to confirm a change works end-to-end in the real running app (UI → orchestrator → brain…

AgriciDaniel/seo-os

A skill your agent uses when running Playwright tests in this repo (luna.mbt) and either the test fails to discover specs ("did not expect test.describe()" / "two different versions of…

mizchi/luna.mbt

Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.

openclaw/openclaw

Test a change in Open Data Capture. An agent skill from DouglasNeuroInformatics/OpenDataCapture.

DouglasNeuroInformatics/OpenDataCapture

Find and safely apply ONE worthwhile code optimization (reuse, simplification, efficiency, or a dead-weight cleanup) somewhere in packages//src, with new regression tests proving behavior is…

openplayerjs/openplayerjs

Runs one unattended iteration of a QA loop: tend any open QA pull request, then build one queued qa issue as tests or test tooling only and open a PR.

breaking-brake/cc-wf-studio

Commit changes following project quality gates and best practices.

hyperlane-xyz/hyperlane-explorer

Structured coding workflow: read, plan, implement, test, verify

spytensor/openmozi

Testing commands and strategy for the kouchou-ai repo, including unit/integration tests and Playwright E2E rules.

digitaldemocracy2030/kouchou-ai

Investigate pnpm test memory growth, Vitest worker OOMs, and suspicious RSS increases in OpenClaw using the scripts/test-parallel.mjs heap snapshot tooling.

SafeAI-Lab-X/ClawKeeper

Inspect, select, author, modify, or review NiceEval E2E and Unit test owners.

NiceEval/NiceEval

Drive the ConvoForm web app in a real browser to capture screenshots or walk product flows.

growupanand/ConvoForm

Diagnose AgentDeck Stream Deck/PTY option synchronization, cursor state, hook ingestion, and bridge state-machine issues.

puritysb/AgentDeck

Moves logic out of Astro frontmatter into tested helper modules under shared/lib, with rules for naming, typing, deterministic demo data and sibling test files.

tabler/tabler

Runs OpenWork's agent-first test specs one at a time, locally or on Daytona, and records exact results, skips and runtime mismatches instead of reporting a loose pass.

different-ai/openwork

运行并解读 lint、类型检查、测试等质量门时使用。它不只是执行命令，还要根据变更范围选择最小充分检查、分析失败原因，并给出是否允许继续提交或发布的判断。用户提到 lint、typecheck、tests、quality gate、验证改动时都应触发。

CaoMeiYouRen/caomei-auth

Walks the agent through a fixed loop for failing tests and build errors: reproduce, isolate, hypothesize, instrument, fix, verify, then add a regression test.

Totoro-jam/battle-tested-patterns