uniapp-test：把 uni-app 页面测试写成可执行工作流
uniapp-test 是 SkillHub 社区 Skill（@user_3141f90e/uniapp-test，v1.0.0），面向 uni-app / uni-app x：分析 .vue/.uvue 与 pages/ 页面，生成或完善 *.test.js，并通过 npm run test:web 及 app-android、app-ios、app-harmony、mp-weixin 等脚本在多端运行与修复失败用例。无需 API Key。安装需 skillhub CLI，并用 --dir 指向 Cursor 等环境的 skills 目录。适合已有 uni 自动化基建、希望用 Agent 串联写测、跑测、改测的开发者。
Read More购物场景 Agent 体验质量评估：自动化脚本与评估报告
SkillHub 社区 Skill「购物场景Agent体验质量评估」（@user_d9b3e84b/shopping-agent-evaluation，v1.1.0）面向线上购物 Agent 的体验质量评估：调用后自动执行评估脚本并生成报告。标签 requires_api_key=true，需配置 API Key。本文说明定位、核心能力、skillhub install 安装路径（Cursor/Claude/Codex）及典型调用边界，并给出官方页面与安装文档链接。
Read Moredsh-testhud：在待测应用上方显示自动化测试进度
dsh-testhud 是 DeepSeek Harness 的 macOS 客户端插件，在被测应用上方显示置顶、可穿透点击的测试进度面板，并通过 test_hud 工具与 testhud CLI 上报标题、步骤期望/实际结果及是否可收回键鼠。支持 GitHub、本地 link 与 npm 0.1.1 安装，可选 topInset 与锚点配置。适合 GUI 自动化与长时验证；插件以 dsh 进程权限运行，安装前请核对源码与 MIT 许可证。
Read MoreDeepSeek Harness (DSH) Test Plugin：在对话中完成测试规划与执行
DSH Test Plugin 是 DeepSeek Harness 的原生测试插件，旨在解决脚本编写与对话流程割裂的问题。它允许开发者通过自然语言直接完成测试规划、执行与结果交付，支持网页 UI、接口及参数化测试。 该插件具备自然语言规划、执行进度监控、实时画面录像、证据收集及静态 HTML 报告生成等核心功能。使用 `/test` 等命令即可快速上手。安装需满足 Node.js 22.19+ 及 DSH 特定版本要求，支持串行执行与离线报告保存。
Read MoreTouchstone: DeepSeek Harness 代理驱动的自动化测试平台
DeepSeek Harness (DSH) 的插件 Touchstone 将其从单次命令行工具升级为长期运行的自动化测试工作流平台。该插件提供 Markdown 案例库、Bug 报告生成、可视化的开发板视图及统一串行队列，支持探索、回归、压力测试及修复验证等全生命周期管理。Touchstone 专为本地运行设计，旨在解决 AI 测试中的上下文管理与协作难题。
Read MoreDeepSeek Harness 插件：zseven-w/dsh-qa
zseven-w/dsh-qa 是 DeepSeek Harness (DSH) 的一个 QA 协调器插件，旨在通过 Agent 驱动的探索模式，让智能体以真实用户方式操作应用并捕获证据，最终将验证过的操作转化为可复现的回放场景。该插件支持 Web、桌面及移动端多平台测试，提供从观察到回放的完整工作流，允许将场景导出为声明式 JSON 文件。开发者需自行安装对应驱动包并配置入口，安装后可运行示例脚本验证。使用时需注意证据导向、无权限升级限制以及移动端和 macOS 计算机辅助的特殊要求。
Read More小程序云测：在 AI Agent 里对接微信 MiniTest 云测
SkillHub 社区 Skill「小程序云测」（@user_05b87ff0/minitest，v1.0.0）面向微信小程序 MiniTest 云测外部服务，用于提交与查询测试任务、管理测试计划与用例及质量检测。Skill 标注 requires_api_key=true，依赖 minitest.weixin.qq.com。本文说明定位、能力与 skillhub install 安装方式（需 --dir 指向 Agent skills 目录），并指向微信官方 MiniTest 文档作接口与配额参考。
Read Morecypress-skill: Writing E2E and Component Tests in Agents Following Cypress Production Standards
cypress-skill, maintained by TestMu AI for e2e testing, generates Cypress E2E and component tests in JavaScript or TypeScript within an Agent. It distinguishes between local `npx cypress` execution and TestMu AI cloud execution, standardizes the `cypress/e2e` and component directories, emphasizes command chaining, `data-cy` selectors, and using `intercept` instead of hard waits, and provides examples of `cy.session`, custom commands, and `lambdatest-cypress` cloud configuration. It is suitable for standardizing Cypress test styles in tools such as Cursor.
Read Moredsh-shipcheck: An Evidence-Driven Frontend Release Checker
`dsh-shipcheck` is a frontend release-checking plugin for DeepSeek Harness (DSH), designed to replace subjective judgment with evidence-first deterministic checks. The plugin uses a real browser to generate screenshots, named baselines, and JSON reports, covering accessibility, structure, content quality, and runtime error checks. It provides tools such as `shipcheck_run` and `shipcheck_matrix` for URL checks, structural regression comparisons, and user journey simulation. Acting as a release gate, it provides reproducible failure evidence and supports quality control before manual review, though it should be noted that it is structure-based rather than pixel-level.
Read Moredsh-mp-automator: A WeChat Mini Program Automated Testing Plugin
The `dsh-mp-automator` plugin released by DeepSeek Harness (DSH) aims to address key challenges in agent-driven WeChat Mini Program testing: environment changes have a significant impact, and pure text models struggle to infer screen state. By introducing “discipline layer” designs—including selector addressing, build freshness gates, and fail-closed mechanisms—it ensures the accuracy and reliability of test actions. It provides eight tools, including session management, element querying, action execution, and screenshots, and supports geometric assertions and camera-free QR code scanning, offering the necessary components for agents to test Mini Programs securely and reliably.
Read Moredsh-test-runner: Structured test runner plugin for DSH
dsh-test-runner is an MIT-licensed plugin within the DSH ecosystem. The core tool, `test_run`, is designed to optimize the agent's test execution workflow. By automatically detecting testing frameworks such as vitest, jest, pytest, and node:test, executing tests, and structurally parsing failure summaries, it prevents the model from having to read lengthy raw terminal outputs, thereby reducing the costs associated with multi-round fixes. The plugin supports filtering test targets by file or case mode, provides a `last_failed` feature to rerun only failed cases, and allows overriding the default execution command via the `command` parameter. The default timeout is set to 120 seconds, and it strictly adheres to session-level sandbox security policies. Installation requires adding the command via a local directory, followed by restarting the DSH Web process to take effect. Applicable scenarios are frequent execution...
Read MoreLet Agent fix itself until all tests pass with grinding-until-pass
### 介绍 This article introduces `grinding-until-pass` from spencerpauly/awesome-cursor-skills: It enables the Agent to independently fix issues until tests, builds, or lint checks pass via the `fix→run→check` loop. We verify that the steps follow the official SKILL.md rules, including iterating within 10 times, fixing one thing at a time, and prohibiting deleting tests or suppressing errors. We also explain the installation methods using `npx skills` or copying the skill to `.cursor/skills`, along with target command examples and advanced usage of Cursor Hooks. This skill is suitable for scenarios such as large-scale refactoring, dependency upgrades, and clearing failed builds after merging branches; manual intervention is required for slow tests or when design changes are needed.
Read More