Provides systematic verification for Claude Code sessions to improve correctness and quality.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "verification-loop" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/verification-loop/SKILL.md 2. Save it as ~/.claude/skills/verification-loop/SKILL.md 3. Reload skills and tell me it's ready
Run verification-loop on this Claude Code session to systematically check whether my recent code changes meet the requirements, introduce obvious errors, and provide a verification conclusion with a risk list.
A structured verification report with requirement coverage, detected issues, risks, and next-step recommendations.
Before I commit, use verification-loop to review this session’s implementation, focusing on edge cases, test coverage, and potential regressions, then output passed and failed checks.
A pre-commit check result listing verified items, missing tests, possible regression points, and suggested fixes.
Execute verification-loop on the solution just generated by Claude Code, comprehensively validating logic correctness, implementation completeness, and executability, then summarize confidence level.
A validation summary of the AI-generated solution describing reliability, key flaws, and whether adoption is recommended.
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.
# 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.
# 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.
Set up and manage Pi-hole DNS, blocking, and home network resolution.
Create reusable Manim animated explainers for technical concepts, graphs, and system flows.
Create animation-rich web presentations or convert PowerPoint decks for talks and pitches.
Orchestrate RFC-based multi-agent workflows with quality gates and merge queues.
Translate visa document images into English and generate a bilingual PDF.
Troubleshoot BGP sessions, routing policy issues, and collect safe diagnostic evidence.
Independently verify artifacts with different model lineages to catch missed defects.
Run verification checks before completion to ensure results are truly correct.
Run pre-release verification for Django projects across tests, security, and deployment checks.
Delegate code investigation, edits, and verification to Claude Code with background job management.
Verify AI-generated code for quality, security, and performance with more trust.
Get verified dependency audit verdicts to assess project component risks quickly.