agentleFS
toonighttoonight/get-shit-done-for-antigravity/.agents/skills/empirical-validation/SKILL.md

empirical-validation

Skill952 starsChanged 3 months agoMITView on GitHub

Requires proof before marking work complete — no "trust me, it works

  • Sends data out

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the appropriate command or action

    line 33
  2. Very specific:

    Add to .gsd/JOURNAL.md under the task

    line 37
  3. Distinctive:

    If not, task is NOT complete

    line 42
  4. Distinctive:

    Never use these as justification for completion:

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Empirical Validation

Core Principle

"The code looks correct" is NOT validation.

Every change must be verified with empirical evidence before being marked complete.

Validation Methods by Change Type

Change TypeRequired ValidationTool
UI ChangesScreenshot showing expected visual statebrowser_subagent
API EndpointsCommand showing correct responserun_command
Build/ConfigSuccessful build or test outputrun_command
Data ChangesQuery showing expected data staterun_command
File OperationsFile listing or content verificationrun_command

Validation Protocol

Before Marking Any Task "Done"

  1. Identify Verification Criteria
    • What should be true after this change?
    • How can that be observed?
  2. Execute Verification
    • Run the appropriate command or action
    • Capture the output/evidence
  3. Document Evidence
    • Add to .gsd/JOURNAL.md under the task
    • Include actual output, not just "passed"
  4. Confirm Against Criteria
    • Does evidence match expected outcome?
    • If not, task is NOT complete

Examples

API Endpoint Verification

# Good: Actual test showing response
curl -X POST http://localhost:3000/api/login -d '{"email":"test@test.com"}' 
# Output: {"success":true,"token":"..."}

# Bad: Just saying "endpoint works"

UI Verification

# Good: Take screenshot with browser tool
- Navigate to /dashboard
- Capture screenshot
- Confirm: Header visible? Data loaded? Layout correct?

# Bad: "The component should render correctly"

Build Verification

# Good: Show build output
npm run build
# Output: Successfully compiled...

# Bad: "Build should work now"

Forbidden Phrases

Never use these as justification for completion:

  • "This should work"
  • "The code looks correct"
  • "I've made similar changes before"
  • "Based on my understanding"
  • "It follows the pattern"

Integration

This skill integrates with:

  • /verify — Primary workflow using this skill
  • /execute — Must validate before marking tasks complete
  • Rule 4 in GEMINI.md — Empirical Validation enforcement

Failure Handling

If verification fails:

  1. Do NOT mark task complete
  2. Document the failure in .gsd/STATE.md
  3. Create fix task if cause is known
  4. Trigger Context Health Monitor if 3+ failures

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.