Verify completed code changes in six stages: build, type checks, lint, tests with coverage, searches for possible secrets, and diff review. Produces a pass/fail report with issues to fix and readiness for a pull request.
Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS/FAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.
Verifies changes made in Claude Code through six stages and summarizes results and required fixes. It checks the build, types, lint rules and code issues, tests with coverage, strings that may contain secrets, and the code diff, in that order. The report includes total tests, passes, failures, the percentage of code exercised by tests, and whether the work is ready for a pull request.
Use it after completing a feature, making substantial changes, or refactoring, and before creating a pull request. Diff review checks for unintended changes, missing error handling, and overlooked edge cases. For long development sessions, it also describes running checks every 15 minutes or after major changes to identify problems while work is still underway.
/verify before creating the pull request.”Uses Git and the project’s build, lint, and test commands. Type-checking examples use TypeScript’s tsc or Python’s pyright; Python lint examples use ruff. The coverage target is at least 80%. Security checks use string searches and do not represent a comprehensive vulnerability assessment. The license is MIT.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
A comprehensive verification system for Claude Code sessions.
Invoke this skill:
# 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.
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.
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
# Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50
# Check coverage threshold
# Target: 80% minimum
Report:
# 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
# Show what changed
git diff --stat
git diff HEAD~1 --name-only
Review each changed file for:
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. ...
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
This skill complements PostToolUse hooks but provides deeper verification. Hooks catch issues immediately; this skill provides comprehensive review.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design and audit interfaces for Web, iOS, and Android using WCAG 2.2 accessibility guidance. Check screen-reader labels, keyboard navigation, contrast, and control sizes to identify barriers and guide implementation for people using assistive technology.
Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.
Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.
Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.
Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.
Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.