iOS Agent Skill

https://nagarjuna2997.github.io/ios-agent-skill/iOS Agent Skill2026-09-16T21:51:01-05:00Nagarjunahttps://nagarjuna2997.github.io/ios-agent-skill/blog/asset-catalogs.htmlHow can design tokens generate light, dark and…2026-09-16T20:25:44-05:002026-09-16T21:51:01-05:00

Generate a real xcassets catalog from explicit color tokens, inspect its four variants, and compile it with actool.

https://nagarjuna2997.github.io/ios-agent-skill/blog/availability-guards.htmlHow should I review availability guards when moving a…2026-09-16T20:25:44-05:002026-09-16T21:51:01-05:00

A measured guard-review example that separates SDK availability, runtime readiness, and static-analysis limits.

https://nagarjuna2997.github.io/ios-agent-skill/blog/chatgpt-codex-ios.htmlChatGPT and Codex: plan the app, then verify it locally2026-09-16T19:49:22-05:002026-09-16T21:51:01-05:00

Separate a browser planning session from a connected development environment.

https://nagarjuna2997.github.io/ios-agent-skill/blog/choose-ai-client.htmlChoose an AI client for your iOS workflow2026-09-16T19:44:40-05:002026-09-16T21:51:01-05:00

Understand the difference between a skill, a local MCP connection and ChatGPT web setup.

https://nagarjuna2997.github.io/ios-agent-skill/blog/claude-hooks.htmlHow can Claude Code hooks protect generated files and…2026-09-16T20:25:44-05:002026-09-16T21:51:01-05:00

A tested generated-file guard and Stop check, with configuration, reproducible exit codes, and enforcement limits.

https://nagarjuna2997.github.io/ios-agent-skill/blog/claude-swift-review.htmlClaude Code: turn a Swift finding into a tested patch2026-09-16T19:49:22-05:002026-09-16T21:51:01-05:00

A small review-to-test loop for an existing iOS project.

https://nagarjuna2997.github.io/ios-agent-skill/blog/gemini-cli-ios.htmlGemini CLI: connect once and review one iOS feature2026-09-16T19:49:22-05:002026-09-16T21:51:01-05:00

Avoid duplicate connections and keep setup evidence separate from app evidence.

https://nagarjuna2997.github.io/ios-agent-skill/blog/generate-asset-catalog.htmlGenerate light and dark asset catalogs without a paid…2026-09-16T19:49:22-05:002026-09-16T21:51:01-05:00

Turn explicit color tokens into Assets.xcassets, then inspect the result in your app.

https://nagarjuna2997.github.io/ios-agent-skill/blog/muse-connection.htmlWhich Muse Code MCP settings actually work with a local…2026-09-16T20:25:44-05:002026-09-16T21:51:01-05:00

A reproducible Muse 1.3.0 connection check, with the exact configuration and clear limits on what discovery proves.

https://nagarjuna2997.github.io/ios-agent-skill/blog/muse-verification.htmlMuse Code: what our integration actually verifies2026-09-16T19:49:22-05:002026-09-16T21:51:01-05:00

Discovery and hooks are useful milestones, but they are not a finished app.

https://nagarjuna2997.github.io/ios-agent-skill/blog/review-swift-with-ai.htmlReview AI-generated Swift before you trust it2026-09-16T19:44:40-05:002026-09-16T21:51:01-05:00

A focused review, a small patch and a real test beat a confident completion message.

https://nagarjuna2997.github.io/ios-agent-skill/blog/swift-concurrency.htmlHow can I catch Swift concurrency review findings before…2026-09-16T20:25:44-05:002026-09-16T21:51:01-05:00

A real before-and-after MCP review with file and line evidence, plus the limits of text-based concurrency checks.

https://nagarjuna2997.github.io/ios-agent-skill/blog/swiftui-state-review.htmlSwiftUI: review state transitions before polishing the…2026-09-16T19:49:22-05:002026-09-16T21:51:01-05:00

Make loading, empty, success and error states part of the implementation brief.

https://nagarjuna2997.github.io/ios-agent-skill/blog/verify-swiftui-simulator.htmlFive checks for an AI-built SwiftUI app2026-09-16T19:44:40-05:002026-09-16T21:51:01-05:00

Use persistence, search and accessible states to make “it works” a testable claim.