All skills
jakeschincariol avatar

/replica-recon

@77c9436

Reverse-engineers any app into a recon map: screen inventory, user flows, component list, inferred data model and a feature matrix, from public pages, screenshots, app store listings, help docs and the user's own account. The first step of the Replica pack. Use when the user says "clone this app", "reverse engineer X", "how does X work", "map out X", "what screens does X have", "I want to build my own version of X", "copy this app", or pastes an app's URL or App Store link and wants to rebuild it.

Use this Skill: https://skilld.dev/gh/jakeschincariol/replica-skill/replica-recon

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

recon-map.md

≈312 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Recon map: {{app}} ({{platform}})

Scope: {{the slice being cloned}} For: {{who the clone is for}} Date: {{YYYY-MM-DD}}

Sources

# source URL notes
1 help center

Core loop

{{one sentence: the thing users pay for}}

Screens

ID screen route / how to reach purpose key components states seen
S01 empty, filled, error

Flows

F01 {{goal}}
    S01 -> S02 -> S03
    happy path clicks: {{n}}
    edge: {{cases}}

Components

component variants states used on
Button primary, secondary, ghost, danger default, hover, focus, disabled, loading all

Inferred data model

{{Entity}}  {{fields}}
            evidence: {{screen IDs, help articles}}
            confidence: high | medium | guess

Relationships: {{User 1-n EventType, EventType 1-n Booking, ...}}

Feature matrix

See features.csv. Must: {{n}}, should: {{n}}, could: {{n}}, skip: {{n}}.

Out of scope (cannot or should not be cloned)

  • {{licensed content, the network, partner deals, ...}}

Size

Screens {{n}}, flows {{n}}, entities {{n}}. Hard parts: {{list}}. Size: {{S|M|L|XL}}.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning4d3 checks · Risk SAFE
  • Gen Agent Trust Hub4d

    The skill provides a clean-room approach for mapping application features from public sources and user-owned data. It includes strong safety instructions against unauthorized access, scraping, and intellectual property theft.

  • Socket4d

    No alerts

  • Snyk4d

    Risk: MEDIUM · 1 issue

Signed by skilld at 77c9436. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 hours ago.

Activeupdated 5 days ago

README badge

README badge for jakeschincariol/replica-skill/replica-recon