Catalog
affaan-m/verification-loop

affaan-m

verification-loop

A comprehensive verification system for Claude Code sessions. Use when verifying a Claude Code session's work before claiming it is complete.

NewUpdated Sep 9, 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

set -o pipefail
# TypeScript projects
npx --no-install 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

76/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

82

Quality

72

Clarity

80

Completeness

65

Summary

The verification-loop skill provides a structured, multi-phase verification system for validating code changes in Claude Code sessions before submitting PRs. It orchestrates build checks, type verification, linting, test execution with coverage metrics, security scanning for secrets and console statements, and diff review—all with a standardized output format and optional continuous monitoring mode.

Detected Capabilities

shell executionfile reading (grep)git operationsbuild command executiontest suite executionlinting executiontype checking executioncommand output parsing

Trigger Keywords

Phrases that agents use to match this skill to user intent.

verify code changespre-pr checklistquality gatesrun verification suitecheck coveragelint and testvalidate refactoring

Risk Signals

WARNING

Grep-based secret detection uses pattern 'sk-' which is OpenAI-specific; other secret formats not covered

Phase 5: Security Scan
INFO

No error handling documented for individual phase failures beyond 'STOP and fix'; unclear escalation strategy

Phase 1: Build Verification
INFO

Assumes npm/pnpm and Python tooling are available; no fallback or validation before execution

Multiple phases (1, 3, 4)
INFO

Git operations (git diff) assume a git repository exists; skill does not validate this precondition

Phase 6: Diff Review

Use Cases

  • Verify code changes before submitting pull requests
  • Validate TypeScript/JavaScript/Python projects post-refactoring
  • Run comprehensive quality gates (build, types, lint, tests, security)
  • Check test coverage against an 80% threshold
  • Detect leaked secrets or debugging code in version control
  • Review diff changes for unintended modifications or missing error handling

Quality Notes

  • Clear phased structure makes verification steps logical and easy to follow
  • Concrete shell commands reduce ambiguity for agent execution
  • Output format template is well-defined and standardized for consistent reporting
  • Security scan focuses on common issues (secrets, console.log) but is not exhaustive—pattern matching is limited
  • Skill assumes presence of project-specific npm scripts (npm run lint, npm run test); not all projects implement these
  • No guidance on handling projects with multiple languages or monorepo structures
  • Continuous mode documentation is vague ('mental checkpoint')—no concrete invocation mechanism specified
  • Missing edge cases: empty test suites, projects without coverage reporting, pre-commit hooks that might interfere
  • Does not address how to handle skipped tests or expected failures
Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v2.0

    Contract changed: description

    ✦ AIAdds set -o pipefail to type-check phase; switches to npx --no-install for TypeScript compilation.

    triggeringlicense2026-09-09

    LATEST
  2. v1.2

    Content updated

    ✦ AINo behavioral changes detected.

    2026-07-14

    View This Version
  3. v1.1

    Content updated

    ✦ AIAdds LICENSE file.

    2026-04-20

    View This Version
  4. v1.0

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

    2026-03-16

    View This VersionInitial version

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

Command Palette

Search for a command to run...

affaan-m/verification-loop | SkillRepo