菜单
Analyze a feature a developer is building from a QA perspective — edge cases, negative flows, abuses, unobvious scenarios — and write acceptance criteria. Use when asked "what could go wrong?", "what am I missing?", "review this as QA", or for acceptance criteria before tests exist.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate a QA Sprint Progress Summary Report from Testomat.io TMS data. Use when the user wants to produce a structured end-of-sprint report covering test design coverage, execution results, defect trends, and quality signals. The skill reads data via Testomat.io MCP tools, maps it to the report sections, and outputs an `.html` file by default (or `.md` if explicitly requested).
Detect redundant tests, duplicated test logic, semantic overlaps, and parameterization opportunities across the entire test suite. Present recommendations and request user approval before refactoring.
Map test cases — manual (markdown) and automated e2e (Playwright, Cypress, WebdriverIO, CodeceptJS, Puppeteer, Appium) — to source code files and produce a `coverage.tests.yml` mapping consumed by `@testomatio/reporter --filter "coverage:..."`. Use this skill when the user wants to run only the tests affected by a code change, generate a coverage file (manual, e2e, or both), build a traceability matrix between tests and source code, or set up change-aware regression.
Orchestrate the complete test case lifecycle from requirements to uploading to TMS (Test Management System). Generate test cases, improve existing ones, analyze test coverage, add test reporter, upload to TMS, write new autotests, fix/heal autotests. Use this skill when you need to manage the entire testing workflow including generation, improvement, coverage, and sync with Testomat.io or do one of these tasks. This is the tactical/execution layer triggered by concrete task verbs — for strategic intent ("where do I start", "improve our QA process", "review our quality", "QA maturity review") use the `qa-lead-strategy-advisor` skill instead.
This skill converts manual test cases into production-ready automated test scripts. It analyzes the existing automation framework, interprets manual test steps, and generates maintainable tests following automation best practices. Use this skill whenever the user wants to automate manual test cases, expand test coverage, or create end-to-end automated flows from existing test documentation.
Diagnose and fix failing automated tests. Analyzes failures, inspects DOM, identifies root causes, and applies targeted fixes using framework tools and MCP/CLI debug modes. Use when tests fail, are flaky, or behave inconsistently (e.g., pass locally but fail in CI).
| name | qa-thinking |
| description | Analyze a feature a developer is building from a QA perspective — edge cases, negative flows, abuses, unobvious scenarios — and write acceptance criteria. Use when asked "what could go wrong?", "what am I missing?", "review this as QA", or for acceptance criteria before tests exist. |
Look at the feature in development and think about it like a senior QA engineer. The user can explain the idea, or you can take it from the current branch or current PR.
Think:
Output:
Outcomes:
action → expected result).qa-write-test-cases skill.