跳到正文
cccskills
免费在 GitHub 公开

plan-react-native-port

Inspect a declared React Native or Expo feature slice and produce a read-only SwiftUI behavioral parity contract before any implementation.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md3.5 KB
  • agents/openai.yaml320 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Plan a React Native Port

Turn one explicitly declared React Native or Expo feature into a reviewable SwiftUI parity contract. This is a planning skill, not a transpiler and not permission to edit.

Safety contract

  • Do not edit files.
  • Do not create, edit, delete, rename, format, generate, install, build, or commit files.
  • Do not run commands that write caches, lockfiles, build products, or derived data.
  • Inspect only the declared feature files and the smallest set of directly imported files needed to understand that feature. Do not crawl the whole repository.
  • Treat the source as a behavioral reference. Do not copy source, assets, submodules, private links, credentials, generated artifacts, or customer data into any output.
  • When available, use the bundled scripts/native-port.mjs plan guardrail for declared files. Its expected result is readOnly: true and writesPerformed: false; do not proceed if it reports ambiguity.

Required declaration

Before inspecting, require all of:

  • an exact source boundary: files, route, component, or directory plus its allowed direct imports;
  • the intended SwiftUI target directory and target module;
  • the backend contract for this slice, including request/response shapes, auth assumptions, persistence, errors, and offline behavior;
  • source, asset, font, and dependency licensing/provenance;
  • the parity expectations and any approved native adaptations.

If source scope, target module, backend contract, licensing, or parity expectations are missing or ambiguous, stop. Return a short missing-input list and no implementation advice that assumes an answer.

Inspection method

  1. Inventory the declared screens, components, state holders, hooks, navigation entry points, platform APIs, and directly used dependencies.
  2. Trace observable user journeys, state transitions, validation, loading/empty/error states, persistence, network calls, permissions, and analytics only within the declared scope.
  3. Separate behavior from implementation details. Record what a user or backend can observe; do not preserve incidental JavaScript structure.
  4. Identify dependencies that should remain, be replaced by native APIs, or be deferred. State the reason and the parity impact.
  5. Identify pure domain rules that can live in Swift without importing SwiftUI or UIKit.
  6. Propose deterministic checks for each material invariant, including seeded randomness, fixed clocks, fixture data, or stable serialization where needed.
  7. Record accessibility expectations: labels, hints, traits, focus order, Dynamic Type, contrast, reduced motion, and deterministic UI identifiers for the approved path.

Contract output

Return a compact contract with:

  • declared scope and excluded scope;
  • target directory/module and allowed write boundary for a later port;
  • user journeys and state-transition table;
  • backend, persistence, permissions, and error contract;
  • parity requirements and intentional native adaptations;
  • pure-Swift domain candidates versus SwiftUI/UIKit adapters;
  • deterministic check matrix and available platform gates;
  • accessibility acceptance criteria;
  • licensing/provenance findings;
  • unresolved questions, explicit deferrals, and a go/no-go recommendation.

End by asking for explicit approval of exactly one feature slice, the contract, and the target directory/module before $port-react-native-slice may write anything.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Analyze reviewed Grafana log evidence for event patterns, error-rate changes, and enrolled security markers. Use when a user needs bounded log analytics for an incident window, error-log comparison, anomaly triage, operational debugging, or a cautious check of approved security signals.

中文简介正在准备中。当前显示原文说明。

openai/community-plugins152026年10月20日 更新

Run a read-only App Store-readiness preflight for a declared iOS target without claiming approval or submitting anything.

中文简介正在准备中。当前显示原文说明。

openai/community-plugins152026年10月20日 更新

Audit whether a declared local review evaluation can support fair quality claims. Use only when the user explicitly asks to audit review-eval validity or use the bundled synthetic fixture.

中文简介正在准备中。当前显示原文说明。

openai/community-plugins152026年10月20日 更新

Deterministically score comparable imported review-run lanes with root-cause metrics and uncertainty. Use only when the user explicitly asks to benchmark normalized local review runs or use the bundled synthetic fixture.

中文简介正在准备中。当前显示原文说明。

openai/community-plugins152026年10月20日 更新

Stage and verify Fusion exports, drawing PDFs, flat-pattern DXF, viewport images and local renders. Use for engineering deliverables, not automatic publication or release.

中文简介正在准备中。当前显示原文说明。

openai/community-plugins152026年10月20日 更新

Prepare, execute and verify authorized Fusion CAD changes using resolved entities, explicit units and state-bound plans. Use for reviewed parameter, sketch, feature, assembly or configuration operations.

中文简介正在准备中。当前显示原文说明。

openai/community-plugins152026年10月20日 更新

查看 openai 的全部技能

报告此技能的问题