CtrlK
BlogDocsLog inGet started
Tessl Logo

verification-loop

A comprehensive verification system for Claude Code sessions.

40

Quality

38%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/verification-loop/SKILL.md
SKILL.md
Quality
Evals
Security

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

npx nx run-many --target=build --all --parallel 2>&1 | tail -20

If build fails, STOP and fix before continuing.

Phase 2: Type Check

npx tsc --noEmit 2>&1 | head -30

Report all type errors. Fix critical ones before continuing.

Phase 3: Lint Check

npx nx lint meerkat-core 2>&1 | head -30

Phase 4: Test Suite

# Run tests for affected project(s)
npx nx test meerkat-core 2>&1 | tail -50

# Run all tests
npx nx run-many --target=test --all 2>&1 | tail -50

# Target: 80% minimum coverage

Report:

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

Phase 5: Security Scan

# 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" packages/ 2>/dev/null | head -10

Phase 6: Diff Review

git diff --stat
git diff HEAD~1 --name-only

Review each changed file for:

  • Unintended changes
  • Missing error handling
  • SQL injection risks (string concatenation instead of AST)
  • Potential edge cases (null values, . delimiters, empty arrays)

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 next task

Run: /verify

Pre-Push Gate (MANDATORY)

Before ANY git push, run the full monorepo test suite:

npx nx run-many --target=test --all 2>&1 | tail -50

Rules:

  • If ANY test fails, DO NOT push. Fix the failing tests first.
  • This applies to all branches, not just main.
  • Run this even if only one package was changed — cross-package regressions are common.
  • After fixing failures, re-run the full suite to confirm before pushing.

Integration with Hooks

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

Repository
devrev/meerkat
Last updated
Created

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.