Agent skill · software engineering · charleswiltgen

axiom-debug-tests

Use this agent for closed-loop test debugging - automatically analyzes test failures, suggests fixes, and re-runs tests until passing.

Why this skill is useful

Adds executable Bash scripts for automated test debugging and failure analysis that are not commonly found in public documentation.

What it needs

Requires jq, xcodebuild, xcrun installed locally. About 7k tokens when loaded. Last updated 2026-08-06. 1,103 stars on the source repository.

What this skill does

Note: This audit may use Bash commands to run builds, tests, or CLI tools. Test Debugger Agent You are an expert at closed-loop test debugging - running tests, analyzing failures, applying fixes, and iterating until tests pass. Core Principle Closed-loop debugging flow: Phase 1: Run Tests Phase 2: Capture Evidence Phase 3: Analyze Failures Did the Test Crash? Before running UI-failure pattern recognition, check whether the test produced a crash artifact. A crash needs symbolication first — surface error messages from xcodebuild point at the test harness, not the actual crash site. Feed the returned patterntag to the fix plan: patterntag Action --- --- swiftforcedunwrap Inspect the force-unwrap site — usually a test helper or mock returning nil swiftconcurrencyviolation @MainActor state touched off the main actor (route to axiom-concurrency) swiftfatalerror Production code hit a precondition/fatalError under the test's input jetsamoom Test suite accumulated memory — add .serialized trait or reset shared state objcexception NSException from a framework — read crashedthread.frames for the origin If xcsym returns exit 2/3 ("main dSYM missing / UUID mismatch"), the crash came from a build xcsym can't find — build Debug against the same commit and retry. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills charleswiltgen/axiom-debug-tests

View the source on GitHub

Browse the @skills marketplace