testingby vibeeval
Verification Loop Skill
vibeeval/verification-loop
Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.
What it changes
Passed 18 of 20 test cases with the skill, and 15 of 20 without it.
Without skill77%
With skill91%
Checks it passed that the model alone missed
- Uses READY or NOT READY for PR in the overall status line
- Specifies npm run test -- --coverage to run tests with coverage
- States that execution must stop immediately if the build phase fails
and 1 more in the full report
3 fixed17 passed either way2 still failing0 broke
- Pass-rate lift
- +14 pp
- Tokens
- -3%
- Agent turns
- 0%
- Response time
- -43%
Model gemini-3.6-flashMeasured 8/3/2026v120 of 22 cases passed with skill · 20 comparable
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhat command and flag combination should be executed in a Node.js project during Phase 4 to run unit tests with coverage data collection?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Specifies npm run test -- --coverage to run tests with coverage | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md120 linessingle file
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
# 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
# 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
Track record
Benchmark
18 / 20
test cases passed, vs 15 / 20 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/1/2026Version v1