replica-recon is the first step of the Replica skill set. It scopes which app, platform and slice to study, lists the public sources, and writes a recon map and a feature matrix that every later step reads.
It studies functionality and UX patterns, clean-room style. It uses public pages and your own account only, and does not read the app’s source, private APIs or anything behind another person’s login.
What You Get
replica/recon.mdfrom a template, with sources, core loop, screens, flows, components and data modelreplica/features.csvwith feature, area, priority, original, clone and notes columns- A
replica/screens/folder of reference screenshots that are never shipped - A list of skip rows for licensed content, networks, partner deals, hardware and regulated licences
- A five-line summary with the core loop, counts, three hardest parts and next step
Common Use Cases
- Mapping the screens and flows of a SaaS app before planning your own version
- Producing a feature matrix with must, should and could priorities
- Sizing a clone project as a weekend, a few weeks, a quarter or a rescope
What Makes It Unique
It sets legal and ethical limits before any work starts. Sources are public pages and your own account, pages are read at human speed, and the app’s JavaScript bundles, network calls and private APIs are left alone. It also writes down what cannot be cloned, and marks inferred data model fields with evidence and a confidence level.
Under The Hood
The skill is instructions plus two templates, a recon map and a feature CSV, with no scripts. The agent reads public web pages such as help centres, pricing pages, changelogs and store listings, may drive a connected browser on your own account with you present, and writes the recon files and screenshots into your project. It does not run commands.