让 AI 像资深测试工程师一样工作：面向 AI Agent 的测试工程 Skill 框架——10 Skills + 共享知识库 + 类型决策矩阵（Claude Code / dsh 等 Agent 可用）
Skill Claude CodeCodex
API testing checks a software service directly through its endpoints, using OpenAPI or Swagger documentation or automated test cases. It can produce and run scripts that test requests and responses.
Skill Claude CodeCodex
A workflow for turning manual web-app test cases into Playwright end-to-end tests and running them. End-to-end tests check a complete user flow through the website.
Skill Claude CodeCodex
A method for investigating confirmed software bugs by tracing their cause in code and assessing their effects. It also records repair and regression-testing recommendations in a test report.
Skill Claude CodeCodex
A shared reference library for a collection of software-testing skills. It contains common guidance on evidence, risk, test cases, coverage, failure triage, and reports, but does not define a user-facing workflow.
Skill Claude CodeCodex
A method for exploratory testing, where a tester learns an unfamiliar system while looking for risks instead of following only predefined test cases. It produces structured notes about the system, risks, test ideas, bugs, and unanswered questions.
Skill Claude CodeCodex
A complete software-testing workflow that moves from understanding a requirement through strategy, test cases, review, execution, bug analysis, regression testing, and a report.
Skill Claude CodeCodex
A workflow for deciding which existing tests should run after a code change. Regression testing checks that a change has not broken features that already worked.
Skill Claude CodeCodex
A structured method for figuring out what a software requirement really means from documents, bugs, issues, and code. It records goals, scope, users, rules, exceptions, dependencies, and unanswered questions.
Skill Claude CodeCodex
A review process for checking whether existing software test cases cover the right requirements and can actually be run. TDD, or test-driven development, is different: it writes tests as part of developing the code.
Skill Claude CodeCodex
A method for turning requirements, API documents, bug reports, or source code into executable manual test cases, plus a machine-readable test schema. A markmap is a Markdown-based mind-map format; the method uses the code first when a repository is available.
Skill Claude CodeCodex
A method for deciding how a feature should be tested by turning risks into testing scope, depth, and priorities. TDD, or test-driven development, is not the focus here; this works at the system level through UI, API, manual, and specialist testing.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: