DSH Test AutoFix：给 agent 的 run_tests 与结构化失败修复循环
DSH Test AutoFix（dsh-test-autofix）为 DeepSeek Harness agent 提供 run_tests 工具：自动识别 pytest、jest、vitest、cargo、go、npm 等框架并执行测试，将失败压缩为带文件、行号与断言信息的 JSON，支持 Windows 中文断言编码处理与同失败重复时的循环防护。本文介绍其定位、安装命令、典型调用与配置，并说明与 dsh-test-runner 的区别及使用时的权限与安全注意。
Read More千流-aitest：让 Agent 对接千流 AI 测试效能平台
千流-aitest 是 SkillHub 社区 Skill（@user_6c0ab08d/qianliu-aitest，v1.0.0），用于千流 TP 测试平台集成：配置 ~/.qianliu/config.json 与任务 YAML 后，可执行测试、查询测试床与执行主机、监控状态并获取报告。本文基于官方 SKILL.md 与 SkillHub 安装说明，说明 skillhub 安装路径、Cursor/Claude 等 skills 目录及 API 端点，并提示 requires_api_key 与 PowerShell 脚本环境注意点。
Read Morecicd-pipeline-skill: Generating Cross-Platform CI/CD Pipeline Configurations for Test Automation
cicd-pipeline-skill is a DevOps Agent Skill (MIT License, v1.0) provided by TestMu AI in the agent-skills repository. It generates GitHub Actions, Jenkins, GitLab CI, and Azure DevOps pipeline configurations for test automation and includes integration examples for local Playwright and TestMu AI cloud testing. After installing it with npx agentskillsforall, you can describe CI/CD requirements in natural language in assistants such as Cursor to align with the official Core Patterns. The article covers multi-platform configuration files and secret locations, representative YAML snippets, and usage considerations.
Read Moredsh-playwright-cli: Integrating Playwright CLI into DSH's Agent Loop
dsh-playwright-cli is a Host-only plugin for DSH agents designed to encapsulate common Playwright CLI operations as tools callable by the agent, thereby implementing automated testing workflows. The plugin provides four core functionalities: `playwright_version` probes the local CLI status; `playwright_install` automatically installs browsers and missing test dependencies; `playwright_test` runs test suites, supporting various parameter configurations; and `playwright_show_report` generates and returns the route or file path to the HTML report. The plugin runs based on DSH's shell executor, inheriting its sandbox strategy, timeout control, and environment variable configuration.
Read MoreAdding E2E Tests: Building Playwright End-to-End Tests from Scratch with Agent Skill
### 正式翻译： # Adding E2E Tests from awesome-cursor-skills: Teach AI Agents to Build Playwright E2E Testing from Scratch This tutorial covers end-to-end setup with Playwright: installing dependencies, configuring `playwright.config.ts`, writing smoke tests and Page Objects, supplementing npm scripts and `.gitignore`, integrating GitHub Actions CI, and emphasizes best practices for `data-testid` and Playwright Codegen. It explains the positioning of this skill, its differences from webapp-testing, installation methods for Cursor/Claude Code, and a seven-step implementation workflow, making it suitable for frontend and full-stack projects that have not yet adopted E2E testing.
Read More