VE

verification-loop

Automates build, test, lint, and security checks.

Install

mkdir -p .claude/skills/verification-loop && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13543" && unzip -o skill.zip -d .claude/skills/verification-loop && rm skill.zip

Installs to .claude/skills/verification-loop

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

A comprehensive verification system for Codex work sessions.
60 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Verify project build status
  • Perform type checking for TypeScript and Python projects
  • Conduct lint checks for JavaScript/TypeScript and Python
  • Run test suites with coverage reporting
  • Execute security scans for secrets and console logs
  • Review code diffs for unintended changes and edge cases

How it works

The skill runs a multi-phase verification loop including build, type checking, linting, test suites, and security scans, then generates a complete report on project readiness.

Inputs & outputs

You give it
Code session or project changes
You get back
complete verification report with overall readiness status

When to use verification-loop

  • Checking project readiness before PR
  • Automating build verification
  • Running security scans for secrets
  • Ensuring test coverage compliance

About this skill

Verification Loop Skill

A comprehensive verification system for Codex work 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 the project builds
npm run build
# OR
pnpm build

If build fails, STOP and fix before continuing.

Phase 2: Type Check

# TypeScript projects
npx tsc --noEmit

# Python projects
pyright .

Report all type errors. Fix critical ones before continuing.

Phase 3: Lint Check

# JavaScript/TypeScript
npm run lint

# Python
ruff check .

Phase 4: Test Suite

# Run tests with coverage
npm run test -- --coverage

# Check coverage threshold
# Target: 80% minimum

Report:

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

Phase 5: Security Scan

# Check for secrets
rg -n "sk-" -g "*.ts" -g "*.js" .
rg -n "api_key" -g "*.ts" -g "*.js" .

# Check for console.log
rg -n "console\\.log" -g "*.ts" -g "*.tsx" src

Phase 6: Diff Review

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

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 the next task

Re-run the checklist from Phase 1 to Phase 6.

Integration with Hooks

This skill complements lightweight automated checks but provides deeper verification. Automated checks catch issues quickly; this skill provides a comprehensive review pass.

When not to use it

  • When the build fails and needs fixing before continuing
  • When critical type errors exist and need fixing before continuing
  • When automated checks are sufficient for quick issue detection

Limitations

  • Requires fixing build failures before proceeding to other phases
  • Requires fixing critical type errors before proceeding
  • Complements, but does not replace, lightweight automated checks

How it compares

This skill provides a complete, multi-phase verification system that goes beyond lightweight automated checks, offering a deeper review of project quality and readiness.

Compared to similar skills

verification-loop side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
verification-loop (this skill)04moReviewIntermediate
moai-foundation-quality03moNo flagsAdvanced
checking-changes15moReviewBeginner
codex-code-review18moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

moai-foundation-quality

modu-ai

Enterprise code quality orchestrator with TRUST 5 validation, proactive analysis, and automated best practices enforcement

04

checking-changes

streamlit

Validates all code changes before committing by running format, lint, type, and unit test checks. Use after making backend (Python) or frontend (TypeScript) changes, before committing or finishing a work session.

16

codex-code-review

tyrchen

Perform comprehensive code reviews using OpenAI Codex CLI. This skill should be used when users request code reviews, want to analyze diffs/PRs, need security audits, performance analysis, or want automated code quality feedback. Supports reviewing staged changes, specific files, entire directories, or git diffs.

16

security-audit

ruvnet

Comprehensive security scanning and vulnerability detection. Includes input validation, path traversal prevention, CVE detection, and secure coding pattern enforcement. Use when: authentication implementation, authorization logic, payment processing, user data handling, API endpoint creation, file upload handling, database queries, external API integration. Skip when: read-only operations on public data, internal development tooling, static documentation, styling changes.

337

lint-and-validate

davila7

Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.

68

agent-tester

ruvnet

Agent skill for tester - invoke with $agent-tester

15

Search skills

Search the agent skills registry