CtrlK
BlogDocsLog inGet started
Tessl Logo

verify-changes

Prove code works by running it, not just checking it exists. Verification through execution rather than inspection. Use after writing or modifying code to ensure it actually functions correctly.

59

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/verify-changes/SKILL.md
SKILL.md
Quality
Evals
Security

Verify Changes — Prove Code Works

"Code that exists" ≠ "Code that works." This skill ensures changes are verified through execution.

Core Principle

❌ Verification by inspection:  "I can see the function exists, it should work"
❌ Verification by assumption:  "The types check out, so it's correct"
✅ Verification by execution:   "I ran it, here's the output, it works because [evidence]"

Verification Protocol

Step 1: Identify What Changed

- Which files were modified?
- What behavior should be different now?
- What was the original bug/requirement?

Step 2: Determine Verification Method

Change TypeVerification Method
Bug fixReproduce the original bug scenario → confirm it no longer occurs
New featureRun the feature → confirm expected output
RefactorRun existing tests → confirm nothing broke
API changeCall the endpoint → confirm response shape
UI changeRender the component → confirm visual output
Config changeLoad the config → confirm values applied
Build/infraRun build command → confirm success

Step 3: Execute Verification

# For Node.js projects
npm run build          # Does it compile?
npm run test           # Do tests pass?
npm run dev            # Does it start?

# For specific files
node -e "require('./path/to/module'); console.log('✅ Loads correctly')"

# For API endpoints
curl http://localhost:3000/api/endpoint

# For scripts
python script.py --test

Step 4: Report Evidence

## Verification Report

### What was changed
- [File list and summary]

### How it was verified
- [Exact commands run]

### Evidence
- Build: ✅ Compiled without errors
- Tests: ✅ 42/42 passing
- Runtime: ✅ Server starts, endpoint returns expected JSON
- Edge case: ✅ Empty input handled correctly

### Not yet verified
- [Anything that couldn't be tested automatically]

Verification Checklist by Project Type

Web Application

  • npm run build — compiles without errors
  • npm run lint — no linting errors
  • npm run test — all tests pass
  • Dev server starts successfully
  • Changed pages render correctly
  • No console errors in browser

API / Backend

  • Server starts without errors
  • Changed endpoints respond correctly
  • Error cases return appropriate status codes
  • Database queries execute successfully

CLI / Script

  • Script runs without errors
  • Expected output matches actual output
  • Error handling works (bad input test)
  • Help/usage text is correct

Anti-Patterns

Anti-PatternWhy It's BadFix
"It should work"No evidenceRun it and show output
Only checking happy pathBugs hide in edge casesTest error paths too
Verifying only compilationCompiles ≠ correctTest runtime behavior
Skipping verification for "trivial" changesTrivial changes cause real bugsVerify everything

Integration with Other Skills

After UsingVerify With
frontend-design → UI changesRender in browser, check console
backend-specialist → API changescurl endpoints, check responses
database-design → Schema changesRun migrations, query data
testing-patterns → New testsRun test suite, check coverage
Repository
vudovn/ag-kit
Last updated
First committed

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.