← Search

Replica Recon , reverse-engineer any app into a recon map from public sources
Development 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit 77c9436
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: none , works from public web sources and your own…

Replica Recon , reverse-engineer any app into a recon map from public sources

First step of the Replica pack: turn any app into a recon map (screen inventory, user flows, components, inferred data model, feature matrix) from public pages, screenshots, app store listings, help docs and your own account

Version:

@

Quick answer

Replica Recon is the first step of the Replica pack, by Jakeschincariol: it reverse-engineers an app into a recon map you can build from, using only public sources and your own account. Screen inventory with states, user flows traced click by click, repeated components, an inferred data model with confidence levels, and a scored feature matrix.

At a glance

What it isA clean-room research skill: it studies a target app from the outside and writes the map that every later Replica step — build, test — works from.
Who it's forDevelopers who want to rebuild an app's experience (or study a competitor's structure honestly) and need the full picture before writing code.
What you give itThe target app to study, through public pages, screenshots, app store listings, help docs and your own account. No prerequisites — it works from public web sources and your own accounts.
What you getA recon map: every screen with its states, user flows, a component list, an inferred data model with evidence and confidence levels, a feature matrix — plus an honest size estimate and an upfront list of what cannot be cloned.
Works withMuse, installed from this page with the copy-paste install prompt. Strictly clean-room: no scraping, no source code, no private APIs.
CostFree
TimeA few minutes to install. The recon itself scales with the app — a small app is one working session; a large one takes proportionally longer, and the skill says so in its size estimate.

Example — mapping a notes app before rebuilding it

An example of the pass the documentation describes, on a hypothetical target app:

  • You point the skill at the app and feed it what is public: the store listing, the help docs, screenshots, and a walkthrough from your own account.
  • It inventories the screens and their states — empty, loading, editing, error — traces the main flows click by click, and lists the components that repeat from screen to screen.
  • It closes with the inferred data model, each inference carrying its evidence and a confidence level, a scored feature matrix, and an honest sizing: a weekend, a few weeks, a quarter — or a recommendation to rescope.
⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 77c9436

Prerequisites: none , works from public web sources and your own accounts. Install "Replica Recon , reverse-engineer any app into a recon map from public sources" for me. It gives my agent @Jakeschincariol's recon workflow, the first step of the Replica pack: scope the app slice, gather sources, build a screen inventory, trace user flows, list components, infer the data model with evidence, score a feature matrix, list what cannot be cloned, and size the project. Repository: https://raw.githubusercontent.com/Jakeschincariol/replica-skill/77c9436fb3d18c3d58169efb8caf4fe906b0dc51/replica-recon/SKILL.md Pinned version: install the code at commit 77c9436fb3d18c3d58169efb8caf4fe906b0dc51 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files, including the recon-map and features.csv templates) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "replica-recon". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. pick the app and the slice to map; the skill will ask before starting). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🧪 Example
You ask
Reverse-engineer this app for me: I want to rebuild the pages, blocks and sharing features of a notes app like Notion. Web only, for my own small team.
You get
Done — written to your project: • replica/recon.md — the recon map (screens, flows, components, inferred data model) • replica/features.csv — the feature matrix Summary: the core loop is create a page → nest blocks → share it with the team. Hardest parts: block drag-and-drop, live sharing, permissions. Out of scope: the mobile apps and the template gallery. Next step: /replica-architect.
Illustrative example based on this skill’s own documentation — not a real user’s result.
🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 77c9436 · 2026-10-13
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : no network contact
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
77c9436 · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

\u2318

The Replica series

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.