Implement an app screen by screen from research and design documents, starting with its core workflow. Write fresh code and interface text, cover loading and error states, and track progress with a feature matrix and screenshots.
中文简介正在准备中。当前显示英语简介。
Rebuilds an app screen by screen from the recon map: app shell first, then the core flow as a vertical slice, then every screen with all its states, ticking off the feature matrix as it goes. Writes every line fresh, never the original's code, assets or copy. Use when the user says "build the clone", "build screen S07", "start building", "rebuild this screen", "implement the booking page", or after /replica-design.
安装前可以查看交给 AI 代理的指令内容。
Reads replica/recon.md, replica/architecture.md, replica/design/.
Updates replica/features.csv (the clone column) and keeps
replica/build-log.md.
Routing for every screen in the inventory (stub pages are fine), the layout (nav, header, sidebar), tokens wired in, the primitives from replica-design, and seed data so screens have something real to show. Commit.
The core loop from the recon map, end to end, before anything else. For a booking app: create an event type, open the public page, book a slot, see it on the dashboard. Ugly is fine. Working is the point. If replica-backend has not run yet, use the seed data and a fake data layer with the same function signatures, so swapping in the real one changes no screen code.
Work in the order of architecture.md. For each screen:
features.csv to yes or partial (with a note).replica/clone-screens/S07.png for replica-diff.build: S07 booking page.replica/build-log.md, one line per screen: ID, date, done or partial, what
is missing, what was harder than expected. When a feature is bigger than it
looked, say so in the log and in the chat. Do not quietly ship half of it.
Go back to the original as a user: read its help article, watch its public walkthrough, use the user's own account. Do not dig into its code or network calls. Then build your own version of the behaviour.
Screens built, the feature matrix updated, screenshots saved, and a summary:
screens done of total, must-haves done of total, what is next. Then
/replica-backend if the data layer is still fake, else /replica-test.
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。
Turn research about an existing app into a technical plan for a new implementation. Choose technologies, define database tables and access rules, map API routes, and order development around a small, complete core workflow.
中文简介正在准备中。当前显示英语简介。
Build the backend for an app modeled on an existing service, including login, database access rules, Stripe test payments, email, and integrations through official APIs. Track implementation and security checks in a dedicated checklist.
中文简介正在准备中。当前显示英语简介。
Develop an app’s own identity through name candidates, a distinct color palette, a logo brief, and writing guidance. Track name screening checks and scan project files for leftover names, domains, and colors from the original app.
中文简介正在准备中。当前显示英语简介。
Prepare and publish an app built from an existing reference, covering release checks, production services, domain and email records, payments, sign-in, monitoring, and mobile distribution. It records results and requires user approval before going live.
中文简介正在准备中。当前显示英语简介。
Rebuild an app’s visual system as reusable design values and component specifications. It covers typography, spacing, component states, implementation, and contrast checks while replacing the original app’s branded assets with independent alternatives.
中文简介正在准备中。当前显示英语简介。
Compare a recreated app with its reference using weighted feature coverage, screenshot layout differences that ignore color, and workflow reviews. Generate a report showing missing functionality, release readiness, and the next five implementation priorities.
中文简介正在准备中。当前显示英语简介。