Swiftdata Code Review
v1.2.0Reviews SwiftData code for model design, queries, concurrency, and migrations. Use when reviewing .swift files with import SwiftData, @Model, @Query, @ModelA...
⭐ 0· 82·0 current·0 all-time
byKevin Anderson@anderskev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the actual contents: the package is a set of prose review instructions and reference docs specifically for SwiftData model design, queries, concurrency, and migrations. It does not request unrelated binaries, environment variables, or config paths.
Instruction Scope
SKILL.md and reference files limit themselves to reviewing .swift code (SwiftData patterns and anti-patterns). They do not instruct the agent to access unrelated system files, environment variables, external endpoints, or to exfiltrate data. The guidance is scoped to code-review questions and checklists.
Install Mechanism
No install spec and no code files with executable content — this is instruction-only, which minimizes risk because nothing is written to disk or downloaded during install.
Credentials
The skill declares no required environment variables, credentials, or config paths. There is no disproportionate credential request relative to its purpose.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills. Autonomous model invocation is allowed (platform default) but the skill itself does not request elevated privileges or permanent installation.
Assessment
This skill appears coherent and low-risk: it's a set of local review guidelines and examples for SwiftData. Before installing or using it, remember that any code you paste into the agent (for review) will be processed by the agent/LLM — avoid sharing proprietary secrets, API keys, or sensitive data inside source files you submit. If you need assurance about where data is sent, check your agent/platform privacy settings (how the LLM provider logs or stores prompts) — the skill itself does not add network endpoints or request credentials.Like a lobster shell, security has layers — review code before you run it.
latestvk97dptagyf67a7yrw237g7k1kn83c9sp
License
MIT-0
Free to use, modify, and redistribute. No attribution required.