← 返回 Skills 市场
anderskev

Swift Code Review

作者 Kevin Anderson · GitHub ↗ · v1.2.1 · MIT-0
cross-platform ✓ 安全检测通过
184
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install swift-code-review
功能描述
Reviews Swift code for concurrency safety, error handling, memory management, and common mistakes. Use when reviewing .swift files for async/await patterns,...
使用说明 (SKILL.md)

Swift Code Review

Review Workflow

Follow this sequence in order. Do not emit findings until every Pass below is satisfied.

  1. Swift / toolchain baseline — Establish language and tooling context: Package.swift // swift-tools-version and any per-target Swift language version or swiftSettings in the manifest; for Xcode, SWIFT_VERSION (or equivalent) in project or target build settings; note if review is single-file only.
    Pass: You state a concrete Swift language version or mode (e.g. Swift 6 language mode, tools 5.10) before advice that depends on strict concurrency, migration-only syntax, or SDK availability.

  2. Read surrounding code — For each changed .swift file, read the full enclosing type, function, method, or property that contains the edits, not only the diff hunk.
    Pass: At least one full enclosing symbol (type or member) containing the change was read per changed file.

  3. Scope the checklist — Using Quick Reference, decide which Review Checklist rows and references apply; open those reference files; skip rows clearly unrelated to the diff.
    Pass: The review (or working notes) lists which checklist areas you applied, or marks areas N/A with a one-line reason tied to the diff (e.g. “no SwiftUI / @Observable in change”).

  4. Pre-report verification — Load and follow review-verification-protocol.
    Pass: That skill’s Hard gates (sequenced) are satisfied for each finding you will report (full symbol read, usage search before “unused”, caller checked before “missing handling”, severity calibrated, [FILE:LINE] proof).

Hard gates (same sequence, shorter)

Step Objective pass condition
1 Swift version/mode (or explicit single-file limitation) recorded before version- or SDK-gated advice.
2 Full enclosing symbol read per changed file, not diff-only.
3 Checklist areas + references listed or N/A with diff-tied reason.
4 review-verification-protocol completed for every reported issue.

Output format

Report findings as:

[FILE:LINE] ISSUE_TITLE
Severity: Critical | Major | Minor | Informational
Description of the issue and why it matters.

Quick Reference

Issue Type Reference
async/await, actors, Sendable, Task references/concurrency.md
@Observable, @ObservationIgnored, @Bindable references/observable.md
throws, Result, try?, typed throws references/error-handling.md
Force unwraps, retain cycles, naming references/common-mistakes.md

Review Checklist

  • No force unwraps (!) on runtime data (network, user input, files)
  • Closures stored as properties use [weak self]
  • Delegate properties are weak
  • Independent async operations use async let or TaskGroup
  • Long-running Tasks check Task.isCancelled
  • Actors have mutable state to protect (no stateless actors)
  • Sendable types are truly thread-safe (beware @unchecked)
  • Errors handled explicitly (no empty catch blocks)
  • Custom errors conform to LocalizedError with descriptive messages
  • Nested @Observable objects are also marked @Observable
  • @Bindable used for two-way bindings to Observable objects

When to Load References

  • Reviewing async/await, actors, or TaskGroups → concurrency.md
  • Reviewing @Observable or SwiftUI state → observable.md
  • Reviewing error handling or throws → error-handling.md
  • General Swift review → common-mistakes.md

Review Questions

  1. Are async operations that could run concurrently using async let?
  2. Could actor state change across suspension points (reentrancy bug)?
  3. Is @unchecked Sendable backed by actual synchronization?
  4. Are errors logged and presented with helpful context?
  5. Could any closure or delegate create a retain cycle?
安全使用建议
This skill appears coherent and low-risk: it only contains review instructions and reference materials and asks for no credentials or downloads. Before installing, confirm the following: (1) the referenced 'review-verification-protocol' skill (../review-verification-protocol/SKILL.md) exists in your environment or adjust the checklist, because the SKILL.md expects it to be loaded but does not declare it; (2) the agent that will run this skill has access to the repository files (Package.swift, .swift files, Xcode project settings) so the review can be performed; and (3) you are comfortable with an instruction-only skill from an unknown publisher (no homepage provided)—if provenance matters, prefer skills from known sources or check the owner ID externally. Otherwise this skill matches its stated purpose and does not request disproportionate access.
能力评估
Purpose & Capability
Name and description (Swift concurrency, error handling, memory management review) match the content of SKILL.md and the included reference documents. The skill does not request unrelated binaries, credentials, or config paths — everything it asks the agent to do (read .swift files, apply checklist) is proportionate to the stated purpose.
Instruction Scope
Instructions are precise and scoped to reviewing Swift source (read full enclosing symbol, apply checklist, provide file:line evidence). They do not request environment secrets or external network endpoints. One note: the runtime instructions require loading and following a 'review-verification-protocol' (path ../review-verification-protocol/SKILL.md) that is not included or declared as a dependency — this creates an implicit external dependency the agent will try to resolve at runtime. That is a usability/consistency concern but not an immediate security risk by itself.
Install Mechanism
No install spec and no code files with executable content; instruction-only skill means nothing is downloaded or written to disk during install. This is the lowest-risk install footprint.
Credentials
The skill declares no environment variables, no credentials, and no config paths. The SKILL.md does not access any undeclared env vars or secrets; all referenced inputs are code files and project manifests (Package.swift, Xcode SWIFT_VERSION), which are appropriate for a code-review skill.
Persistence & Privilege
always is false and the skill is user-invocable with normal model invocation. It does not request persistent presence, nor does it instruct modifying other skills or system-wide settings. No elevated privileges are requested.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install swift-code-review
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /swift-code-review 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.2.1
**Major update: Review workflow and hard verification protocol introduced.** - Added a sequential review workflow ensuring Swift version context, full-symbol reading, scoped checklist, and verification protocol compliance before reporting findings. - Introduced "Hard gates" table summarizing mandatory review steps. - Clarified output format for reporting issues. - Checklist and reference sections retained; organization improved for easier, more reliable code reviews.
v1.2.0
Swift code review skill adds quick reference and review checklist. - Introduces comprehensive review checklist for Swift code safety and best practices. - Adds quick reference links for concurrency, observability, error handling, and common mistakes. - Includes guidance on when to consult each reference. - Provides targeted review questions for async, actor, Sendable, error, and memory management scenarios.
元数据
Slug swift-code-review
版本 1.2.1
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 2
常见问题

Swift Code Review 是什么?

Reviews Swift code for concurrency safety, error handling, memory management, and common mistakes. Use when reviewing .swift files for async/await patterns,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 184 次。

如何安装 Swift Code Review?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install swift-code-review」即可一键安装,无需额外配置。

Swift Code Review 是免费的吗?

是的,Swift Code Review 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Swift Code Review 支持哪些平台?

Swift Code Review 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Swift Code Review?

由 Kevin Anderson(@anderskev)开发并维护,当前版本 v1.2.1。

💬 留言讨论