About this skill
The `verification-loop` skill provides a robust, automated system for an AI agent to perform essential code quality checks within Claude Code sessions. Designed to integrate seamlessly into AI-assisted development workflows, this skill guides the agent through critical verification phases, including build validation and type checking (for both TypeScript and Python projects). It systematically identifies potential issues early, preventing integration problems and ensuring that code meets predefined quality gates before further actions like pull request creation or deployment. Rooted in best practices from the 'everything-claude-code' repository, it empowers Claude to deliver more reliable and production-ready software components by enforcing rigorous quality standards.
Best use case
Ensuring code quality and stability after development, before deployment, or during refactoring, especially in AI-assisted coding environments. It helps catch common errors like build failures or type mismatches early, guaranteeing the codebase adheres to predefined standards.
A comprehensive verification system for Claude Code sessions.
The AI agent will execute build and type-checking commands, report their outcomes (success or failure), and provide relevant log excerpts. If issues are found, the agent will clearly indicate what needs to be fixed. The ultimate outcome is a verified codebase or a clear report of issues preventing verification, ensuring code quality and readiness.
Practical example
Example input
Please run the full verification loop on the current codebase to check for build and type errors.
Example output
{
"verification_status": "failed",
"phase_1_build": {
"status": "success",
"output_tail": "Build complete in 5s\n"
},
"phase_2_type_check": {
"status": "failed",
"errors": [
"src/index.ts(10,5): error TS2322: Type 'string' is not assignable to type 'number'.",
"src/utils/data.ts(25,12): error TS2345: Argument of type 'boolean' is not assignable to parameter of type 'string'."
],
"output_head": "Found 2 errors.\n"
},
"recommendation": "Phase 2 (Type Check) failed. Please review and fix the reported TypeScript errors before proceeding."
}When to use this skill
- After completing a feature or significant code change
- Before creating a PR (Pull Request)
- When you want to ensure quality gates pass
- After refactoring
When not to use this skill
- When the project is not a software development project (e.g., pure data analysis script without a build process or type checking).
- When you are in the very initial prototyping phase and speed of iteration outweighs the need for rigorous verification.
- On codebases that do not use a build system or type checking (though this is less common in modern development).
- For tasks entirely unrelated to code, such as content generation or information retrieval.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/verification-loop/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How verification-loop Compares
| Feature / Agent | verification-loop | Standard Approach |
|---|---|---|
| Platform Support | Claude | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
A comprehensive verification system for Claude Code sessions.
Which AI agents support this skill?
This skill is designed for Claude.
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# 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 # 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 ```bash # 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 ```bash # JavaScript/TypeScript npm run lint 2>&1 | head -30 # Python ruff check . 2>&1 | head -30 ``` ### Phase 4: Test Suite ```bash # 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 ```bash # 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 ```bash # 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: ```markdown 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.
Related Skills
skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
git-workflow
Git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes.
kotlin-patterns
Coroutine'ler, null safety ve DSL builder'lar ile sağlam, verimli ve sürdürülebilir Kotlin uygulamaları oluşturmak için idiomatic Kotlin kalıpları, en iyi uygulamalar ve konvansiyonlar.
docker-patterns
Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Use when setting up containerized development environments or reviewing Docker configurations.
continuous-agent-loop
具有质量门、评估和恢复控制的连续自主代理循环模式。
autonomous-loops
自主Claude代码循环的模式与架构——从简单的顺序管道到基于RFC的多智能体有向无环图系统。
laravel-verification
Verification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
django-verification
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.