realm / realm/SwiftLint

Use AI to implement new native SwiftLint rules

Open
#6,086 0 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Swift
Stars
19.7k
Forks
2.3k
Avg merge
1d 1h
Merged PRs (30d)
11

Description

It would be interesting to see how good AI is at writing native SwiftLint rules, and if it's good enough, we could just get AI to implement new rule requests.

The idea of this feature is to provide a standard interface for getting AI to write new rules.

Ideally the solution would use something like MCP (e.g. see https://github.com/modelcontextprotocol/swift-sdk, and to allow multiple AI engines, so that we can "benchmark" them.

See also https://github.com/realm/SwiftLint/pull/6032

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing SwiftLint pull request 6032 and the modelcontextprotocol/swift-sdk reference linked in the issue. Define the proposed standard interface for generating native SwiftLint rules, including support for multiple AI engines. Done means the design and implementation can benchmark those engines against new rule requests.

Written by the indexing model from the issue text.

Assessment

Tech stack
swift
Domain
tooling
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.