verification-loop — ai-agents verification-loop, everything-claude-code, official, ai-agents, ide skills, anthropic, claude-code, developer-tools, Claude Code, Cursor, Windsurf

Verified
v1.0.0
GitHub

About this Skill

Perfect for Code Review Agents needing comprehensive verification and validation of Claude Code sessions. A comprehensive verification system for Claude Code sessions.

# Core Topics

affaan-m affaan-m
[60.6k]
[7501]
Updated: 3/5/2026

Agent Capability Analysis

The verification-loop skill by affaan-m is an open-source official AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for ai-agents, anthropic, claude-code.

Ideal Agent Persona

Perfect for Code Review Agents needing comprehensive verification and validation of Claude Code sessions.

Core Value

Empowers agents to ensure quality gates pass by performing build verification using npm or pnpm, and type checking, providing a robust verification loop for code integrity and reliability, leveraging bash scripts and npm/pnpm build processes.

Capabilities Granted for verification-loop

Automating build verification for Claude Code projects
Validating type checks for refactored code
Ensuring quality gates pass before creating PRs

! Prerequisites & Limits

  • Requires npm or pnpm installed
  • Limited to Claude Code sessions
  • Dependent on bash script compatibility
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

verification-loop

Install verification-loop, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

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

bash
1# Check if project builds 2npm run build 2>&1 | tail -20 3# OR 4pnpm build 2>&1 | tail -20

If build fails, STOP and fix before continuing.

Phase 2: Type Check

bash
1# TypeScript projects 2npx tsc --noEmit 2>&1 | head -30 3 4# Python projects 5pyright . 2>&1 | head -30

Report all type errors. Fix critical ones before continuing.

Phase 3: Lint Check

bash
1# JavaScript/TypeScript 2npm run lint 2>&1 | head -30 3 4# Python 5ruff check . 2>&1 | head -30

Phase 4: Test Suite

bash
1# Run tests with coverage 2npm run test -- --coverage 2>&1 | tail -50 3 4# Check coverage threshold 5# Target: 80% minimum

Report:

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

Phase 5: Security Scan

bash
1# Check for secrets 2grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10 3grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10 4 5# Check for console.log 6grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

Phase 6: Diff Review

bash
1# Show what changed 2git diff --stat 3git 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:

markdown
1Set a mental checkpoint: 2- After completing each function 3- After finishing a component 4- Before moving to next task 5 6Run: /verify

Integration with Hooks

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

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is verification-loop?

Perfect for Code Review Agents needing comprehensive verification and validation of Claude Code sessions. A comprehensive verification system for Claude Code sessions.

How do I install verification-loop?

Run the command: npx killer-skills add affaan-m/everything-claude-code/verification-loop. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for verification-loop?

Key use cases include: Automating build verification for Claude Code projects, Validating type checks for refactored code, Ensuring quality gates pass before creating PRs.

Which IDEs are compatible with verification-loop?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for verification-loop?

Requires npm or pnpm installed. Limited to Claude Code sessions. Dependent on bash script compatibility.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add affaan-m/everything-claude-code/verification-loop. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use verification-loop immediately in the current project.

Related Skills

Looking for an alternative to verification-loop or another official skill for your workflow? Explore these related open-source skills.

View All

flags

Logo of facebook
facebook

Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.

243.6k
0
Developer

extract-errors

Logo of facebook
facebook

Use when adding new error messages to React, or seeing unknown error code warnings.

243.6k
0
Developer

fix

Logo of facebook
facebook

Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.

243.6k
0
Developer

flow

Logo of facebook
facebook

Use when you need to run Flow type checking, or when seeing Flow type errors in React code.

243.6k
0
Developer