agentleFS
dmminga1983dmminga1983/minga-replica/skills/replica-build/SKILL.md

replica-build

Skill1 starsChanged 18 days agoMITView on GitHub

Rebuild an app clone screen by screen from the recon map: the shell first, then the core flow as a vertical slice, then every screen with all its states, ticking off the feature matrix, every line written fresh. Use for 'build the clone', 'build screen S07', 'start building', 'implement this page'; RU: собери клон, сверстай экран, начинай разработку, сделай этот экран.

2 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Clean room: Every line is written here from the recon map and the specs.

    line 13
  2. Distinctive:

    Your words: Every label, button, empty state and email written fresh.

    line 16
  3. Distinctive:

    Tokens only: No raw hex or pixel values in components.

    line 19
  4. Distinctive:

    When a feature is bigger than it looked, say so in the log and in the chat.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

replica-build

Reads replica/recon.md, replica/architecture.md, replica/design/. Updates the clone column of replica/features.csv and keeps replica/build-log.md.

The rules

  • Clean room. Every line is written here from the recon map and the specs. Never paste the original's HTML, CSS, JavaScript, SVGs or images, never load anything from its domain or CDN, never "view source and adapt".
  • Your words. Every label, button, empty state and email written fresh. Matching what a button does is parity; matching its sentence is copying. Russian interface text written by a native speaker's standard, not translated word for word.
  • Tokens only. No raw hex or pixel values in components.

Step 1: the shell

Routing for every screen (stubs are fine), the layout, tokens wired in, the primitives, seed data with realistic fake records (no real people). Commit.

Step 2: the vertical slice

The core loop end to end before anything else. Ugly is fine, working is the point. If the backend is not there yet, a fake data layer with the same function signatures, so swapping it changes no screen code.

Step 3: screen by screen

For each screen in the order of architecture.md: read its recon row; look at the reference for layout and hierarchy, not pixels; build it with the primitives; every state (empty, loading, filled, error, no permission, a 60-character name, 390px wide); semantic HTML, labels, keyboard, visible focus, alt text; update features.csv; screenshot at the reference viewport into replica/clone-screens/S07.png; one commit per screen.

Definition of done, per screen

  • every state from the recon map, plus empty, error, loading
  • works at 390px and 1440px
  • the flow completes with the keyboard only
  • no console errors
  • no copy borrowed from the original
  • features.csv updated, screenshot saved

When a feature is bigger than it looked, say so in the log and in the chat. Never quietly ship half of it. Stuck on behaviour: use the original as a user (help article, walkthrough, the user's own account), never its code or network calls.

Next: /replica-backend if the data is still fake, else /replica-test.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.