Verification loop
This skill should be used when the user asks to "verify code", "run verification", "check quality", "validate changes", or before creating a PR. Provides comprehensive verification including build, type check, lint, tests, security scan, and diff review.From its SKILL.md
npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill verification-loopAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
3.5 KB, 897 tokens by cl100k_base, as published. Nobody here has run it
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
Choose the commands adaptively for the current project instead of running every example blindly. Use the stack-appropriate command from references/STACK-DETECTION.md when the repo does not match the default examples below.
Phase 1: Build Verification
# Python projects (uv)
uv build 2>&1 | tail -20
# OR
python -m build 2>&1 | tail -20
# Node.js projects
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
# 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
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
Phase 4: Test Suite
# Python projects
pytest --cov=src --cov-report=term-missing 2>&1 | tail -50
# Node.js projects
npm run test -- --coverage 2>&1 | tail -50
Report:
- Total tests: X
- Passed: X
- Failed: X
- Coverage: X%
Phase 5: Security Scan
# Python: Check for secrets
grep -rn "sk-" --include="*.py" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.py" . 2>/dev/null | head -10
pip-audit
# Node.js: 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 debug statements
grep -rn "print(" --include="*.py" src/ 2>/dev/null | head -10
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
Phase 6: Diff Review
# 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:
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.
Reference Files
Load only what is needed:
references/STACK-DETECTION.md- how to choose the right verification command set for the current reporeferences/REPORT-TEMPLATE.md- report structure for final verification outputexamples/example-verification-report.md- example final report
What ships with it: 3 files
865 B alongside SKILL.md
examples/
references/
- REPORT-TEMPLATE.md248 B
- STACK-DETECTION.md420 B
Gives 2 of the 12 instructions most quality gates skills give in 897 tokens
Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06
- Read full output and check exit codein 45 of 1524, across 40 files
- Verify output confirms the claimin 44 of 1524, across 39 files
- Identify the command that proves the claimin 43 of 1524, across 39 files
- Execute the full verification commandin 36 of 1524, across 30 files
- Produce a verification reporthere, and in 34 of 1524, across 18 files
- Review git diff changesin 30 of 1524, across 16 files
- Fix build failures immediatelyhere, and in 29 of 1524, across 9 files
- Group findings by severityin 28 of 1524
- State claim only with evidencein 27 of 1524, across 22 files
- Verify regression tests with red-green cyclein 26 of 1524, across 22 files
- Run the full test suitein 26 of 1524, across 25 files
- Run test suite with coveragein 25 of 1524, across 10 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.