templates/skills/languages/objectivec/SKILL.md
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
npx skillsauth add hivellm/rulebook Objective-CInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
CRITICAL: Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
# Complete quality check sequence:
xcodebuild clean build # Build verification
xcodebuild test -scheme YourScheme # All tests
# clang static analyzer runs automatically in Xcode builds
# Security audit:
# Use Xcode's built-in analyzer or third-party tools
CRITICAL: Use Modern Objective-C with ARC and strict warnings.
IMPORTANT: These commands MUST match your GitHub Actions workflows!
# Pre-Commit Checklist (MUST match .github/workflows/*.yml)
# 1. Format check (matches workflow)
clang-format --dry-run --Werror **/*.{h,m}
# 2. Static analysis (matches workflow)
xcodebuild analyze -scheme YourScheme -sdk iphonesimulator
# 3. Build (matches workflow)
xcodebuild build -scheme YourScheme -sdk iphonesimulator \
ONLY_ACTIVE_ARCH=NO CODE_SIGN_IDENTITY="" CODE_SIGNING_REQUIRED=NO
# 4. Run tests (matches workflow)
xcodebuild test -scheme YourScheme -sdk iphonesimulator \
-destination 'platform=iOS Simulator,name=iPhone 15'
# If ANY fails: ❌ DO NOT COMMIT - Fix first!
Why This Matters:
clang-format -i locally but --dry-run in CI = failure@import XCTest;
#import "DataProcessor.h"
@interface DataProcessorTests : XCTestCase
@property (nonatomic, strong) DataProcessor *processor;
@end
@implementation DataProcessorTests
- (void)setUp {
[super setUp];
self.processor = [[DataProcessor alloc] initWithThreshold:0.5];
}
- (void)testProcessValidInput {
NSArray *input = @[@1, @2, @3];
NSArray *result = [self.processor process:input];
XCTAssertNotNil(result);
XCTAssertGreaterThan(result.count, 0);
}
- (void)testProcessHandlesNil {
XCTAssertThrows([self.processor process:nil]);
}
@end
<!-- OBJECTIVEC:END -->research
Create structured analyses with numbered findings, execution plans, and task materialization
research
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
development
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
data-ai
Autonomous AI agent loop for iterative task implementation (@hivehub/rulebook ralph)