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 deciding whether a request needs an analiz task before implementation - the conditions that require the architect's analysis versus going straight to implementation
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。
Some work can go straight to implementation tasks; some needs the architect to investigate first. Guessing wrong is costly: skipping a needed analiz produces bounced tasks, and forcing analiz on trivial work wastes a cycle.
Core principle: Analiz when the approach is unknown; skip it when the work is clear and small.
get_design_system returns nothing) and its screens still need slicing — open the design-system task yourself with request_design_system (implementation-task-spec) so it runs alongside the analysis, and carry the design brief and its key in the analiz description; the architect makes the UI tasks wait for it.When unsure between a direct task and analiz, take analiz — hidden complexity only grows once implementation starts.
Assign the analiz task to system-architect and move it to todo (investigation is always safe to start — no stakeholder approval needed). The analysis itself returns through the human analiz_review gate before any implementation task is created. Never assign analiz to yourself or a developer.
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。