- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add rshankras/claude-code-apple-skills --skill originality-check -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add rshankras/claude-code-apple-skills --skill originality-check -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add rshankras/claude-code-apple-skills --skill originality-check -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add rshankras/claude-code-apple-skills --skill originality-check -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/rshankras/claude-code-apple-skills/tree/HEAD/skills/app-store/originality-check來自發布者
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.
rejection-handler. That works a rejection you already have. This is upstream — it
prevents the 4.3 by catching sameness before you ship.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.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)..planning/VALIDATION.md (competitor + market data). If missing/stale, gather fresh
via WebSearch or the product/competitive-analysis skill.list_apps / get_metadata).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.
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?
Distinctness scorecard. Score each dimension meaningful difference vs cosmetic, and flag any that is only skin-deep:
Verdict + remedy.
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.
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 validati
---name: originality-checkdescription: Guideline-4.3 anti-spam / originality gate — score whether an app (and each portfolio addition) is…---# skills/app-store/originality-check/SKILL.md總覽
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).
常見問題
從發布者下載 skills/app-store/originality-check/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/rshankras/claude-code-apple-skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。