A specialized AI skill for auditing Swift codebases for concurrency safety, memory management, and modern language best practices.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install swift-code-review
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install swift-code-review using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Swift Code Review?
The Swift Code Review skill is a high-precision auditing tool designed for Openclaw Skills users who need deep analysis of .swift files. It moves beyond simple syntax checking by evaluating code against the Swift 6 language mode, strict concurrency requirements, and modern SDK patterns like @Observable. It ensures that developers catch subtle bugs like actor reentrancy issues, Sendable conformance violations, and memory leaks before they reach production.
By leveraging this Openclaw Skills extension, engineering teams can maintain a high bar for code quality. The skill enforces a rigorous review workflow that requires context-gathering from Package.swift and full symbol analysis, ensuring that recommendations are technically sound and version-appropriate.
Swift Code Review Use Cases
- Auditing legacy Swift codebases for Swift 6 concurrency migration and Sendable compliance.
- Reviewing SwiftUI implementations to ensure correct usage of @Observable and @Bindable patterns.
- Identifying potential retain cycles in closures and delegate patterns during peer review.
- Validating error handling strategies to ensure no empty catch blocks or unsafe force unwraps exist in runtime-critical paths.
How Swift Code Review Works
- Baseline Establishment: The skill first identifies the Swift toolchain version and language mode via Package.swift or build settings to provide version-accurate advice.
- Contextual Reading: It reads the full enclosing type or function for every changed file to understand the scope beyond the immediate diff hunk.
- Scope Alignment: Using a predefined checklist, it identifies which technical domains (Concurrency, Observability, Error Handling) are relevant to the specific changes.
- Verification Protocol: Each finding is passed through a verification gate to ensure the issue is valid, calibrated by severity, and backed by code proof.
- Structured Reporting: It generates a standardized report detailing the file location, severity level, and a technical description of the findings.
Swift Code Review Setup
To integrate this review capability into your Openclaw Skills workflow, ensure the skill is available in your agent's library and follow these steps:
# Navigate to your project root
cd my-swift-project
# Trigger the review for a specific file or the current diff
openclaw run swift-code-review path/to/File.swift
Ensure that your Package.swift is accessible so the agent can determine the correct swift-tools-version for the review.
Swift Code Review Data Schema & Taxonomy
The skill organizes its review logic and references using the following taxonomy:
| Component | Description |
|---|---|
concurrency.md |
Reference for async/await, actors, TaskGroups, and Sendable conformance. |
observable.md |
Reference for SwiftUI Observation framework and state management. |
error-handling.md |
Best practices for typed throws, Result types, and localized errors. |
common-mistakes.md |
Patterns for avoiding retain cycles, force unwraps, and naming violations. |
Findings Report |
Text-based output using the format [FILE:LINE] ISSUE_TITLE. |
Swift Code Review Advanced Features
- Multi-Pass Validation: Enforces a strict sequence where findings are only emitted after language version and full-symbol context are established.
- Concurrency Depth: Specialized checks for actor reentrancy bugs and
@unchecked Sendablesynchronization validation. - Integration with Review Protocols: Automatically chains with the review-verification-protocol to eliminate false positives in AI-generated code reviews.
- Tailored Checklists: Dynamic scoping of review areas based on the specific contents of the code diff.
SKILL.md
Loading
Related Openclaw Skills
QRClaw
QRClaw is an open-source edge service that generates terminal-friendly UTF-8 QR codes and shareable smart links for AI agents and CLI tools.
Provably Fair RNG
A cryptographically verifiable random number generator with on-chain seed anchoring for transparent AI gaming and entertainment.
Agent Autonomy
A proactive framework that transforms AI agents into self-improving, autonomous partners through persistent memory and anticipatory workflows.
MeetingClaw
MeetingClaw is an intelligent meeting assistant that uses advanced voice recognition to transform raw audio into structured, actionable meeting minutes.
Agent Browser
Agent Browser is a high-performance Rust-based headless browser CLI designed to empower AI agents with seamless web navigation and interaction capabilities.
Institutional Site Builder
An advanced AI skill that transforms brand assets, PDFs, and logos into high-performance React institutional websites using Vite and Tailwind CSS 4.
Featured*
