← ClaudeAtlas

fix-testlisted

Auto-diagnose and fix failing tests — up to 3 attempts with re-runs. Triggers on: fix test, failing test, broken test, test error, why is this test failing, debug test.
Smart-AI-Memory/attune-ai · ★ 10 · AI & Automation · score 76
Install: claude install-skill Smart-AI-Memory/attune-ai
# Fix Test **IMPORTANT: Start your response with a context preamble.** Call `help_lookup(topic="fix-test", mode="preamble")` and display the returned `preamble` text as a blockquote. Then tell the user they can say "tell me more" for a step-by-step guide, or answer the scoping questions below to proceed. If the MCP call fails, fall back to: > **Fix Test** — Diagnoses failing tests, classifies the root cause, and applies targeted fixes automatically. ## Scoping Before running, ask: 1. **Target**: "Which test is failing? A specific file, test name, or should I find failures automatically?" 2. **Context**: "Did this start failing after a recent change, or has it been broken?" ## Execution ### Step 1: Identify Failures Run the failing test(s) to capture the error: ```bash uv run pytest <target> -v --tb=short 2>&1 | tail -40 ``` ### Step 2: Diagnose Root Cause Common failure patterns: | Pattern | Root Cause | Fix | | ------- | ---------- | --- | | `ModuleNotFoundError` | Import path changed | Update import | | `AttributeError: mock` | Mock target wrong | Match import path | | `AssertionError` | Expected value drift | Update assertion | | `TypeError: __init__` | Constructor changed | Update call site | | `FileNotFoundError` | Fixture path wrong | Use `tmp_path` | ### Step 3: Apply Fix and Re-run Apply the fix, then re-run the test. If it still fails, diagnose again with the new error. Repeat up to 3 times. ```bash uv run pytest <target> -v --tb=short ``` ###