gate

Verification before completion claims. Use when about to say "done", "fixed", or "complete". Runs checklist by workflow type with evidence requirements.

⭐23stars🔀0forks📁View on GitHub🕐Updated Jan 6, 2026⬇️3downloads

When & Why to Use This Skill

The 'gate' skill is a rigorous verification framework designed to ensure AI agents provide evidence-based proof before claiming task completion. By implementing mandatory checklists for building, debugging, and refactoring, it acts as a procedural guardrail that prevents speculative claims and ensures all outputs are validated through execution, observation, or measurement.

Use Cases

  • Software Development: Enforcing a 'Build' checklist to verify that new features execute without errors and handle edge cases before marking a task as done.
  • System Debugging: Requiring root cause identification and 'before-and-after' evidence to prove a fix actually resolves the reported symptoms.
  • Code Refactoring: Validating that refactored code maintains identical behavior and passes all existing tests to prevent regressions.
  • Quality Assurance: Eliminating anti-patterns like 'should work' or 'looks good' by mandating actual command outputs or debugger sessions as proof of success.
namegate
descriptionVerification before completion claims. Use when about to say "done", "fixed", or "complete". Runs checklist by workflow type with evidence requirements.

gate

Verify before claiming completion.

Trigger

Before claiming: "done", "fixed", "complete", "working", "ready"

Workflow A: Build

□ Feature executes without errors (show output)
□ Edge cases tested (empty, null, boundary)
□ Rollback tested if Type 2B/1
□ Dependencies verified

Workflow B: Debug

□ Root cause identified with evidence
□ Fix tested and resolves symptom
□ Prevention added (test/automation/guard)
□ Related bugs checked (same class)

Workflow C: Refactor

□ Existing tests pass unchanged
□ Behavior identical (output comparison)
□ Deletion complete (no orphans)
□ No new abstraction without justification

Verification Types

Type Description Sufficient for SHIP?
execution output Ran command, showed result ✓ Yes
observation Screenshot, debugger session ✓ Yes
measurement Metrics, benchmark data ✓ Yes
code review Inspection only ⚠️ Weak
assumption Not verified ✗ Blocks SHIP

Require execution output, observation, or measurement before completion claims.

Anti-Patterns

Claim Problem Required
"Should work" Speculation Actual output
"Looks good" No verification Test results
"Fixed the issue" No proof Before/after
"I think this resolves it" No confidence % X-Y% + basis

Incomplete Work

When blocked, state:

  • What's done (with evidence)
  • What's blocking (specific)
  • What's remaining

Type 2A Exception

Trivial changes (< 1 min rollback): completion allowed without full gate. Document undo command.

Common Rationalizations (All Wrong)

Thought Reality
"The tests passed" Tests ≠ verification. Did you run the ACTUAL command?
"It should work" "Should" = assumption. Show evidence.
"I already checked" When? Show the output.
"The user is waiting" Rushed verification = rework later.
"It's a simple change" Simple changes break production too.
"I'm pretty sure it works" Pretty sure ≠ evidence. Run it.