Index of every page on this site: llms.txt
All skills
rshankras avatar

/originality-check

@f958982
Run it yourself

Guideline-4.3 anti-spam / originality gate — score whether an app (and each portfolio addition) is meaningfully distinct in function, content, and metadata before you invest or submit. Use at validation/new-app time and again before submission. Protects the whole developer account from 4.3 (spam/duplicate) rejections. NOT rejection-handler (that works an existing rejection) and NOT competitive-analysis (that positions in the market).

Use this Skill: https://skilld.dev/gh/rshankras/claude-code-apple-skills/originality-check

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈115 tokens for metadata: the name and description. ≈876 when used: this file.

Description uses 5.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈457 characters, or 5.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Originality Check

Decide, with evidence, whether an app is distinct enough to exist — before you build it or submit it.

At portfolio scale, shipping many similar small apps risks Guideline 4.3 (spam / duplicate) — this is the go/no-go distinctness gate that keeps that from happening.

Where it fits (read the seams)

  • Not rejection-handler. That works a rejection you already have. This is upstream — it prevents the 4.3 by catching sameness before you ship.
  • Not competitive-analysis / market-research. Those size demand and position you in the market. This judges distinctness (function + content + metadata) vs your own portfolio and vs near-identical competitors — a spam risk, not a demand question.
  • Two moments to run it: at validate / new-app (don't build a dup) and before submit (don't trip 4.3). Also periodically across the portfolio (internal cannibalization / template-sameness).

Prerequisites

  • The app idea or a shipped app to evaluate (name, one-line function, target metadata).
  • Optional: .planning/VALIDATION.md (competitor + market data). If missing/stale, gather fresh via WebSearch or the product/competitive-analysis skill.
  • Optional ASC access to read the developer's existing portfolio (list_apps / get_metadata).

Flow

  1. Internal check (your own portfolio). list_apps → for each shipped app read its positioning (get_metadata). Does the candidate overlap one you already ship in function, code template, or metadata? Two apps that differ only in theme/reskin = 4.3 risk.

  2. External check (the market). Read VALIDATION.md if present; otherwise WebSearch for close look-alikes. Judge: is the core function a thin reskin of an existing app, or a genuine wedge?

  3. Distinctness scorecard. Score each dimension meaningful difference vs cosmetic, and flag any that is only skin-deep:

    Dimension Distinct if…
    Function it does something materially different, not a template swap
    Content / data unique data or content, not a generic wrapper
    Metadata name / keywords / screenshots not near-identical to siblings or competitors
    UX / value a real reason a user picks this one
  4. Verdict + remedy.

    • Distinct → proceed.
    • Borderline → give concrete ways to differentiate (merge sibling apps into one configurable app, add the unique wedge, or drop it); if approved, name the specific wedge that MUST be built to clear 4.3.
    • Duplicate → recommend not shipping; consolidate any existing thin apps into one strong app instead.
  5. Record. Write the verdict + reasoning to .planning/ (VALIDATION or STATE). For a borderline-approved app, record the wedge as a build requirement so plan/build deliver it.

Done

  • A written verdict (distinct / borderline+wedge / duplicate) with per-dimension reasoning, and — if borderline — the specific differentiation that must ship before submission.

Caveats

  • Cosmetic theming ≠ differentiation — Apple judges function + metadata similarity, not intent.
  • Protect the account. When in doubt between "borderline ship" and "consolidate," prefer one strong app over several thin ones.
  • Guideline numbers/text drift — confirm current 4.3 wording at the App Review Guidelines (captured 2026-07).

Source: SKILL.md on GitHub

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.

No alerts3mo3 checks · Risk SAFE
  • Gen Agent Trust Hub3mo

    The skill is safe. It is designed to help developers ensure their applications are distinct enough to avoid App Store rejections for spam or duplication. It retrieves application metadata and performs market research via web search to provide an originality assessment.

  • Socket3mo

    No alerts

  • Snyk3mo

    Risk: LOW · No issues

Signed by skilld at f958982. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 4 months ago
What it can do
Reads files Edits files Network
MCP servers
asc-metadata
last_verified
2026-07-16
review_by
2027-06-22
All 8 allowed tools
ReadWriteWebSearchGlobGrepAskUserQuestionmcp__asc-metadata__list_appsmcp__asc-metadata__get_metadata

README badge

README badge for rshankras/claude-code-apple-skills/originality-check