跳到正文
cccskills
免费在 GitHub 公开

audit-ios-readiness

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。

查看安装方法

包含的文件(2)

  • SKILL.md3.1 KB
  • agents/openai.yaml276 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Audit iOS Readiness

Perform a bounded, read-only preflight for one declared iOS target after a port. This is an evidence-backed readiness report, not App Store approval.

Required scope

Require the explicit target directory/module, bundle target or scheme when present, approved parity contract, backend/data-collection contract, and licensing/provenance record. Stop if the target, backend contract, licensing, or release expectations are ambiguous.

Safety contract

  • Do not edit metadata, entitlements, privacy manifests, assets, source, signing, provisioning, or App Store Connect records.
  • Do not archive, upload, submit, notarize, create credentials, install tools, download runtimes, or accept Apple licenses.
  • Do not request or expose certificates, profiles, tokens, customer data, private URLs, or production credentials.
  • Inspect only the declared target and approved supporting files. Keep any optional logs under an explicitly approved disposable directory.
  • Never state or imply guaranteed App Store approval.

Preflight checks

Review what can be established locally:

  • bundle identifier, version/build values, deployment target, supported devices, orientations, and required capabilities;
  • Info.plist usage descriptions, privacy manifest declarations, tracking/data-collection claims, and backend/data-flow consistency;
  • entitlements, background modes, networking/ATS choices, permissions, deep links, notifications, and account/deletion behavior when relevant;
  • app icon, launch treatment, asset provenance, fonts, third-party SDK inventory, dependency licenses, and attribution;
  • accessibility evidence for labels, traits, focus order, Dynamic Type, contrast, reduced motion, and assistive-technology reachability;
  • release configuration, debug flags, logging, test hooks, crash paths, localization, and user-facing error/empty/offline states;
  • available deterministic checks and any existing build, Simulator, or XCUITest evidence.

Consult current Apple documentation when a rule may have changed, and label an inference as such. Local checks cannot replace archive validation, App Store Connect metadata, TestFlight, legal review, or human App Review.

When available, use the bundled scripts/native-port.mjs audit guardrail for the bounded static pass. Treat its preflightOnly: true and guaranteedApproval: false fields as invariants, not as a substitute for the human release review below.

Report format

Return:

  1. scope and evidence inspected;
  2. a table of PASS, WARN, FAIL, BLOCKED, or NEEDS HUMAN findings with evidence and the smallest next action;
  3. privacy, permissions, accessibility, licensing, and backend-contract summaries;
  4. platform gates already evidenced versus unavailable;
  5. a release-owner checklist for human decisions;
  6. an explicit conclusion: preflight ready, preflight blocked, or not ready.

Use preflight ready only when there are no local failures or blocked required gates; still say that it is not guaranteed App Store approval.

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13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13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13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13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13日 更新

Prepare a traceable local Fusion engineering review draft with source identities, artifacts and unresolved assurance gates. Not for sending, publication or release approval.

中文简介正在准备中。当前显示原文说明。

openai/community-plugins152026年10月13日 更新

查看 openai 的全部技能

报告此技能的问题