Skip to content
Skills Library
Programming · Analysis

replica-diff

/replica-diff

Compares an app clone against the original: a feature parity score from the feature matrix (weighted by must, should, could) with the missing list in build order, plus a screenshot layout diff that ignores colour so a rebrand does not count against you. Two standard-library Python tools. Use when the user says "how close is my clone", "compare it to the original", "what''s missing", "parity check", "diff the screens", "is it ready", or after the replica-test skill.

Licence
MIT
Last repository change
30.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 30.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Compares an app clone against the original: a feature parity score from the feature matrix (weighted by must, should, could) with the missing list in build order, plus a screenshot layout diff that ignores colour so a rebrand does not count against you. Two standard-library Python tools. Use when the user says "how close is my clone", "compare it to the original", "what''s missing", "parity check", "diff the screens", "is it ready", or after the replica-test skill.

Triggers from the description

how close is my clonecompare it to the originalwhats missingparity checkdiff the screensis it ready
Original author description

Compares an app clone against the original: a feature parity score from the feature matrix (weighted by must, should, could) with the missing list in build order, plus a screenshot layout diff that ignores colour so a rebrand does not count against you. Two standard-library Python tools. Use when the user says "how close is my clone", "compare it to the original", "what''s missing", "parity check", "diff the screens", "is it ready", or after the replica-test skill.

How it works

  1. On this computer
  2. What parity means here
  3. Step 1: feature parity
  4. Step 2: layout diff
  5. Step 3: behaviour diff
  6. Step 4: the report
  7. Output
Original SKILL.md headings · 101 lines, 693 words
SKILL.md preview
---
name: replica-diff
description: 'Compares an app clone against the original: a feature parity score from the feature matrix (weighted by must, should, could) with the missing list in build order, plus a screenshot layout diff that ignores colour so a rebrand does not count against you. Two standard-library Python tools. Use when the user says "how close is my clone", "compare it to the original", "what''s missing", "parity check", "diff the screens", "is it ready", or after the replica-test skill.'
---

# replica-diff

## On this computer

Run the scoring tools on this computer. They do not change source files. Write
the report and diff images into the project you are scoring.

If `replica/features.csv` and the screenshots live in the user's repository,
clone that repository read-only, or use a checkout you already have, and run
the tools there. Do not commit from this computer.

Screenshots of the original come from public pages or the desktop browser on
the user's own account. The user signs in. Never type a password, a card, or
a live key.

Code changes that close gaps go to a Cursor cloud coding agent as a
self-contained task: the missing list, plus the rules from the replica-build
skill. Do not edit the repository yourself. Clone screenshots can come back
from that task, or you can take them from a preview URL in the desktop browser.

Two shared tools, both standard-library Python, no installs:

```bash
python3 "${REPLICA_HOME:-/home/box/replica-skill}/tools/parity.py" replica/features.csv                         # feature parity + missing list
python3 "${REPLICA_HOME:-/home/box/replica-skill}/tools/imgdiff.py" replica/screens/S07.png replica/clone-screens/S07.png --out diff-S07.png
python3 "${REPLICA_HOME:-/home/box/replica-skill}/tools/imgdiff.py" a.png b.png --json > replica/diffs/S07.json # for parity.py --visual
python3 "${REPLICA_HOME:-/home/box/replica-skill}/tools/parity.py" replica/features.csv --visual replica/diffs/*.json --markdown > replica/parity.md
```

## What parity means here

**Parity means it does the same job, not that it looks the same.** The
feature score is the number that matters: can a user do everything they could
do in the original. The layout score checks structure (is the information in
the same places, in the same hierarchy), because that is what makes a switcher
feel at home. It deliberately ignores colour, because replica-brand changes
every colour on purpose. Do not chase pixel parity with the original. Its
exact look is its trade dress, and it changes before launch.

## Step 1: feature parity

Make sure `replica/features.csv` is current: every row's `clone` column is
`yes`, `partial` (with a note), `no`, or `skip` (with a reason). Then:

```bash
python3 "${REPLICA_HOME:-/home/box/replica-skill}/tools/parity.py" replica/features.csv
```

It weights must 3, should 2, could 1, counts partial as half, leaves out
`skip` rows and rows you added that the original does not have, and prints:
the score, must-haves done of total, each area weakest first, and the missing
list in build order. Must-haves not done means not shippable, and it says so.

## Step 2: layout diff

For each key screen, take two screenshots at the **same viewport** (1440x900
desktop, 390x844 mobile) in the **same state** (same data shape, same tab
open, logged in the same way). The original's come from public pages or the
user's own account, saved in `replica/screens/`. The clone's go in
`replica/clone-screens/`.

```bash
python3 "${REPLICA_HOME:-/home/box/replica-skill}/tools/imgdiff.py" replica/screens/S07.png replica/clone-screens/S07.png --out replica/diffs/S07.png
```

Layout mode (default) turns both into edge maps, cuts them into a grid, and
compares where things are, scoring only cells with something in them. It
reports the score (matches 90+, close 75+, partly 50+, different), the
regions that differ (in the original's pixel coordinates, biggest first), and
a height difference if the clone's page is much longer or shorter. Retina and
non-retina screenshots compare fine: both are scaled to the same width.

`--mode pixel` is exact comparison. Use it for your own regressions (clone
today against clone last week), not against the original.

## Step 3: behaviour diff

Walk each flow in both apps and compare what the scores cannot see: clicks to
finish the core flow, what happens on errors, what is remembered between
visits, what emails arrive. Fewer clicks than the original is a win. Write
each difference as: flow, original does, clone does, fix or keep.

## Step 4: the report

`replica/parity.md`: overall score, feature score, layout score per screen,
missing features in build order, behaviour differences, and a verdict:

- **not shippable**: any must-have missing, or any open S1 bug
- **shippable**: all must-haves done, feature score 80+, no open S1 or S2
- **better than the original**: shippable, plus fixes from
  replica-entrepreneur. This is the goal. A straight copy has no reason to exist.

Give honest numbers. A clone at 62% is at 62%.

## Output

`replica/parity.md`, the diff images, and the top five things to build next.
Then the replica-build skill for the gaps, or the replica-entrepreneur skill if parity is
there.

Versions

RepositoryScoreLicence
This page · letmefind/replica-skill-cursor-grok100MIT
lucasouzadev/agent-kit-skill100MIT
letmefind/replica-skill-cursor-grok100MIT
jakeschincariol/replica-skill100MIT
dmminga1983/minga-replica95MIT

Database snapshot: 13.11.2026 · package version fbecf7ff5224 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100recreate-diff
    Compares an app clone against the original: a feature parity score from the feature matrix (weighted by must, should, could) with the missing list in build order, plus a screenshot layout diff that ignores colour so a rebrand does not count against you. Two standard-library…
  • 100fxreplica-diff
    Compares an app clone against the original: a feature parity score from the feature matrix (weighted by must, should, could) with the missing list in build order, plus a screenshot layout diff that ignores colour so a rebrand does not count against you. Two standard-library…
  • 100replica
    Runs the Replica pack in order: recon, architect, design, build, backend, test, diff, entrepreneur, brand, launch, deploy. Use when the user wants to clone an app, asks where to start, or asks which step is next. Each step reads what the previous one wrote under replica/.
  • 100replica
    Runs the Replica pack in order: recon, architect, design, build, backend, test, diff, entrepreneur, brand, launch, deploy. Use when the user wants to clone an app, asks where to start, or asks which step is next. Each step reads what the previous one wrote under replica/.
  • 100check-parity
    [Orbit 2.6.8 Quality checks] Parity with a reference: feature-matrix score, screen diff, parallel run for legacy. Use when: «насколько совпадает», «паритет со старой системой», «сравни со старой версией»; parity check, feature parity, compare with the old system.
  • 100replica-recon
    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…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.