← ClaudeAtlas

cross-verifylisted

Run 17-question 8-Habit cross-verification checklist on a plan or implementation. Use AFTER planning and BEFORE committing to implementation. Maps to ALL 8 Habits.
pitimon/8-habit-ai-dev · ★ 3 · Code & Development · score 77
Install: claude install-skill pitimon/8-habit-ai-dev
# Cross-Verify (8-Habit Checklist) **All Habits** | **Anti-pattern**: Shipping without reflecting on quality from multiple perspectives ## When to Use - After writing a plan, before starting implementation - Before creating a PR for a multi-file change - When something feels off but you can't pinpoint why ## When to Skip - Single-line bug fixes with obvious root cause - Formatting or linting changes - Dependency version bumps with passing CI ## Auto-Detection (Structured Output Blocks) Before running the manual checklist, search for structured output blocks in the current directory: 1. Glob for `*-prd.md`, `*-requirements.md`, `*-tasks.md`, `*-breakdown.md`, `*-review.md` files 2. Read each file and look for `<!-- SKILL_OUTPUT:` blocks 3. If found, pre-populate evidence for: - **Q4**: Extract `ears_count` and `success_criteria_count` from requirements block - **Q5**: Extract `test_coverage_checked` from review block - **Q8**: Compare `task_count` vs `ears_count` for scope alignment — flag if `task_count > ears_count * 3` - **Q14**: Extract `decision_count` from design block — flag if only 1 option was presented (no third alternative considered) - **Q16**: Extract `sticky_decisions` from design block — flag if 0 sticky decisions in a design with >3 decisions (WHY not captured) - **Q4**: Cross-check `decision_count` against requirements `success_criteria_count` — flag if decisions don't cover all criteria 4. Mark auto-populated answers with `✓A` (auto-