Skip to main content
A comprehensive verification system for Claude Code sessions that runs multiple quality checks before deployment.

​
When to Use

  • After completing a feature or significant code change
  • Before creating a PR
  • When you want to ensure quality gates pass
  • After refactoring

​
Verification Phases

1
Build Verification
2
Check if project builds:
3
npm run build 2>&1 | tail -20
# OR
pnpm build 2>&1 | tail -20
4
If build fails, STOP and fix before continuing.
5
Type Check
6
# TypeScript projects
npx tsc --noEmit 2>&1 | head -30

# Python projects
pyright . 2>&1 | head -30
7
Report all type errors. Fix critical ones before continuing.
8
Lint Check
9
# JavaScript/TypeScript
npm run lint 2>&1 | head -30

# Python
ruff check . 2>&1 | head -30
10
Test Suite
11
# Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50

# Check coverage threshold
# Target: 80% minimum
12
Report:
13
  • Total tests: X
  • Passed: X
  • Failed: X
  • Coverage: X%
    • 14
    Security Scan
    15
    # Check for secrets
grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10

# Check for console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
    16
    Diff Review
    17
    # Show what changed
git diff --stat
git diff HEAD~1 --name-only
    18
    Review each changed file for:
    19
  • Unintended changes
  • Missing error handling
  • Potential edge cases

    • ​
    Output Format

    After running all phases, produce a verification report: 
    VERIFICATION REPORT
==================

Build:     [PASS/FAIL]
Types:     [PASS/FAIL] (X errors)
Lint:      [PASS/FAIL] (X warnings)
Tests:     [PASS/FAIL] (X/Y passed, Z% coverage)
Security:  [PASS/FAIL] (X issues)
Diff:      [X files changed]

Overall:   [READY/NOT READY] for PR

Issues to Fix:
1. ...
2. ...

    ​
    Continuous Mode

    For long sessions, run verification every 15 minutes or after major changes: 
    Set a mental checkpoint:
- After completing each function
- After finishing a component
- Before moving to next task

Run: /verify

    ​
    Integration with Hooks

    This skill complements PostToolUse hooks but provides deeper verification. Hooks catch issues immediately; this skill provides comprehensive review.