Use when writing acceptance criteria for a task - express each as an observable Given/When/Then that QA can execute, including negative cases
中文简介正在准备中。当前显示原文说明。
Use after the targeted cases pass - choosing the adjacent behaviour this change can break from the PR's files and the component's links, and the per-repository smoke set
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
After the targeted scenarios pass, run a quick regression sweep of adjacent behaviour. Choose what to sweep from:
list_links — who else calls this component; a change to a shared API or schema can break every caller.Keep it in project memory (search_memory "regression smoke") so it accumulates across rounds instead of being reinvented each time: app boots, login works, primary navigation works, the main create/read flow works, the landing page renders with no console errors (Lighthouse errors-in-console or a manual console check). When a regression escapes to UAT, extend the set with save_memory so the next round catches it.
One screenshot at 360 and 1440 of the one or two most-used unchanged screens that share the changed component or design tokens — a token/layout change can break a screen nobody touched in this task.
Record swept cases as category: regression.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when writing acceptance criteria for a task - express each as an observable Given/When/Then that QA can execute, including negative cases
中文简介正在准备中。当前显示原文说明。
Use when the diff adds or changes an endpoint, resolver, RPC, job or query that takes an object id, a role check, a request binding or a tenant filter - BOLA/IDOR, function-level authorization, mass assignment and tenant scoping
中文简介正在准备中。当前显示原文说明。
Use on every UI change - semantic HTML, labels for controls, keyboard-navigable dialogs/menus, visible focus, and never color as the only signal
中文简介正在准备中。当前显示原文说明。
Use when a task changes any screen, form, dialog, menu or control - Lighthouse/axe scan of the changed screens, a keyboard walk, and the thresholds that fail a task
中文简介正在准备中。当前显示原文说明。
How to work a task returned with review, QA or UAT findings. Use when a task is in need_revision or PR review comments are in your context.
中文简介正在准备中。当前显示原文说明。
Use when the repository keeps its alerting in code, or a person asks for alerts outside TaskTrooper - PrometheusRule YAML, a Cloud Monitoring alert policy in Terraform, a Datadog monitor, each routed to TaskTrooper's alert ingest URL so it opens an incident here
中文简介正在准备中。当前显示原文说明。