fix-test

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.

Prerequisites: MUST READ .claude/skills/shared/understand-code-first-protocol.md AND .claude/skills/shared/evidence-based-reasoning-protocol.md before executing.

• docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models)
• .claude/skills/shared/estimation-framework.md — Story points and complexity (MUST provide story_points and complexity estimate in fix summary)
• docs/test-specs/ — Test specifications by module (read existing TCs for expected behavior context when diagnosing failures)

Skill Variant: Variant of /fix — test suite failure diagnosis and resolution.

Quick Summary

Goal: Run test suites, analyze failures, and fix the underlying code or test issues.

Workflow:

1. Run — Execute test suite and capture results
2. Analyze — Identify failing tests, classify as code bug vs test issue
3. Fix — Apply targeted fix to code or test