菜单
Request second-opinion analyses from other installed AI CLIs (Claude, Codex, Gemini) and synthesize the result. Use when decisions are high impact, architecture tradeoffs are unclear, or you want external challenge before implementation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Algorithmic engineering theory, language-agnostic: complexity analysis (time/space, amortized), data-structure selection, algorithm families (divide & conquer, dynamic programming, greedy, graph, string), correctness reasoning with invariants, and space-time/approximation tradeoffs. Use when choosing a data structure, analyzing or reducing complexity, solving an algorithmic problem, reviewing code with non-trivial loops/recursion, or reasoning about scalability limits of an approach.
Local, searchable Apple developer documentation via the apple-docs CLI and MCP server (DocC, Human Interface Guidelines, App Store Review Guidelines, Swift Evolution, Swift Book, WWDC sessions, sample code, SF Symbols). Use whenever an answer depends on exact Apple API behavior, availability, HIG/review-guideline wording, or WWDC content — before trusting training memory. Also use to set up the tooling: detect whether the MCP server or CLI is available and propose installation if not.
Apple platform API adoption for the iOS 26 / macOS 26 SDK generation: Liquid Glass (SwiftUI, UIKit, AppKit, WidgetKit), Swift 6.2 features (InlineArray, Span, concurrency updates), Foundation Models (on-device LLM), Visual Intelligence, AppIntents, StoreKit, SwiftData inheritance, AlarmKit, 3D Charts, MapKit GeoToolbox, AttributedString, visionOS widgets. Use when adopting, migrating to, or asking about these platform APIs. For SDK 27 SwiftUI changes use swiftui-whats-new-27; for general SwiftUI use swiftui.
Secure coding and security review for Apple platforms: threat modeling (STRIDE, attacker profiles), Keychain and Secure Enclave storage, CryptoKit cryptography, network security (ATS, certificate pinning, TLS), input validation (deep links, URL schemes, WebView hardening), jailbreak/integrity checks, and security code-review methodology. Use when writing or reviewing security-sensitive code (auth, storage, crypto, network handlers, deep links). For Xcode build-setting hardening (Enhanced Security, bounds safety) use audit-xcode-security-settings.
Guide for the C -fbounds-safety language extension. Covers the language model, pointer annotations, adopting bounds-safety in existing C code, compiler build settings and modes, and runtime debugging of bounds violations.
Perform rigorous, team-calibrated code reviews for iOS (Swift/SwiftUI) and Android (Kotlin/Compose) projects. Automatically detects platform from file extensions and applies platform-specific review rules. Covers correctness, architecture, type safety, naming, testing, simplification, UI patterns, and PR process. Also integrates a simplification-first philosophy to strip unnecessary complexity. Use when reviewing code, PRs, or code snippets for any iOS or Android project. Triggers on "code review", "PR review", "review my PR", "strict review", "senior review", "thorough review". Not for pure refactoring requests without review context.
| name | cross-cli-opinion-broker |
| description | Request second-opinion analyses from other installed AI CLIs (Claude, Codex, Gemini) and synthesize the result. Use when decisions are high impact, architecture tradeoffs are unclear, or you want external challenge before implementation. |
Gather independent opinions from peer AI CLIs and return a consolidated recommendation.
scripts/request_opinions.py --prompt "<your prompt>"
Use this template for consistent peer review quality:
Task: <what needs to be decided>
Context: <constraints and relevant files>
Current approach: <planned solution>
Ask: Identify critical risks, better alternatives, and missing validation steps.
When reporting back:
claude, codex, gemini).references/prompting-template.md