Skip to content
SkillModel-led1,224 tokens in use

replica-recon

Reverse-engineers an app into a recon map from public sources: screens, flows, components, an inferred data model and a prioritised feature matrix.

10,140 stars on the repository MIT LicenseJakeschincariol/replica-skill · replica-recon
/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-recon costs

125tokens idle
1,224tokens in use
1,864tokens, 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
  • Examples12/15
  • 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-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.md from a template, with sources, core loop, screens, flows, components and data model
  • replica/features.csv with 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.

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