Skip to content
SkillModel-led1,016 tokens in use

replica-architect

Turns a recon map of an app into a stack choice, a Postgres schema, an API route table and a build order for your own version.

10,140 stars on the repository MIT LicenseJakeschincariol/replica-skill · replica-architect
/plugin install replica-skill@replica-skill
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing replica-architect costs

114tokens idle
1,016tokens in use
1,232tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity32
  • Maintenance4
  • Community64
  • Maturity12
  • Momentum40

replica-architect is the second step of the Replica skill set. It reads the recon map and feature matrix written by replica-recon and produces an architecture document, a SQL schema and an ordered build plan.

It defaults to managed, documented tech (Next.js, Postgres, Stripe, Resend, Vercel) and writes one line of reasoning for each choice. If there is no recon map it stops and asks you to run recon first.

What You Get

  • A replica/architecture.md with the stack, one line of why per layer, and the riskiest parts
  • A SQL schema with ids, timestamps, owner columns, foreign key rules, indexes and access rules
  • An API table of method, path, purpose, caller, input, output and flow, plus webhooks and background jobs
  • A build order: vertical slice, must-haves, should-haves, then the fixes found by the entrepreneur skill

Common Use Cases

  • Choosing a stack and database for a clone of an existing SaaS app
  • Writing a first schema with constraints that stop two guests booking the same slot
  • Listing the hard parts such as time zones, webhook retries and multi-tenancy before building

What Makes It Unique

It is driven by a recon map, so the schema and routes trace back to the flows and screens of the app being rebuilt. It sets hard rules in the database, such as exclusion constraints, and it allows only official public APIs with your own keys, never the original app’s private endpoints.

Under The Hood

The skill is instructions only and ships a template file for the output. It reads the recon files in your project and writes the architecture document and a schema file there. It does not run commands, fetch web pages or call APIs.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers