Catalog
affaan-m/verification-loop

affaan-m

verification-loop

A comprehensive verification system for Claude Code sessions.

global
origin:ECC
New~608
v1.2Saved Jul 14, 2026

Verification Loop Skill

A comprehensive verification system for Claude Code sessions.

When to Use

Invoke this skill:

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

Verification Phases

Phase 1: Build Verification

# Check if project builds
npm run build 2>&1 | tail -20
# OR
pnpm build 2>&1 | tail -20

If build fails, STOP and fix before continuing.

Phase 2: Type Check

# TypeScript projects
npx tsc --noEmit 2>&1 | head -30

# Python projects
pyright . 2>&1 | head -30

Report all type errors. Fix critical ones before continuing.

Phase 3: Lint Check

# JavaScript/TypeScript
npm run lint 2>&1 | head -30

# Python
ruff check . 2>&1 | head -30

Phase 4: Test Suite

# Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50

# Check coverage threshold
# Target: 80% minimum

Report:

  • Total tests: X
  • Passed: X
  • Failed: X
  • Coverage: X%

Phase 5: Security Scan

# 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

Phase 6: Diff Review

# Show what changed
git diff --stat
git diff HEAD~1 --name-only

Review each changed file for:

  • 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.

Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Safety

78

Quality

68

Clarity

78

Completeness

62

Summary

A verification loop skill that guides Claude Code agents through a structured 6-phase quality assurance pipeline: build verification, type checking, linting, test suite execution, security scanning, and diff review. The skill provides shell command templates, output format guidance, and continuous mode recommendations for maintaining code quality throughout a session.

Detected Capabilities

shell executionfile reading (grep)build command executiontype checker executionlinter executiontest runner executiongit command executionproject analysis

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

verify code qualityrun verification checkspre-pull request checkstest coverage reviewsecurity scan for secretscomprehensive code review

Use Cases

  • Verify code quality before creating pull requests
  • Run comprehensive checks after refactoring or feature implementation
  • Establish repeatable verification checkpoints during long development sessions
  • Generate standardized verification reports summarizing build, type, lint, test, and security status
  • Catch secrets and console.log statements during development
  • Track test coverage and ensure minimum thresholds are met

Quality Notes

  • Clear phase-based structure makes the verification process easy to follow and implement
  • Provides concrete shell commands for multiple tech stacks (JavaScript/TypeScript/Python)
  • Security phase includes practical checks for common secrets patterns and debug statements
  • Output format is well-defined, helping agent understand what 'done' looks like
  • Mentions integration with hooks but does not explain how or provide implementation details
  • Phase 2 (Type Check) lacks guidance on when type errors are 'critical' vs. informational
  • No error handling guidance if tools are not installed or git is not initialized
  • Continuous mode mentions '/verify' command but skill does not define this command or integration point
  • Missing guidance on what constitutes 'fixed' for type/lint errors—should define pass criteria
  • No documentation of edge cases: monorepos, projects without git, missing npm/pnpm, no test scripts
Model: claude-haiku-4-5-20251001Analyzed: Jul 14, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.2

Content updated

2026-07-14

Latest
v1.1

Content updated

2026-04-20

v1.0

Seeded from github.com/affaan-m/everything-claude-code

2026-03-16

Use affaan-m/verification-loop in your dev environment

Command Palette

Search for a command to run...