kiro-verify-completion

Verifies task, fix, test, and feature claims using fresh command outputs and exit codes.

Updated Apr 16, 2026
One-click install
npx skills add https://github.com/manatago/gion --skill kiro-verify-completion-manatago
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kiro-verify-completion
Source: https://github.com/manatago/gion/tree/main/.claude/skills/kiro-verify-completion
Command: npx skills add https://github.com/manatago/gion --skill kiro-verify-completion-manatago

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents premature or false completion claims by requiring fresh, scope-aligned evidence for tasks, fixes, tests, and feature readiness so teams and agents do not trust stale or secondhand success reports.

Core Features & Use Cases

  • Claim-to-checklist mapping: Associates claim types (TASK, FIX, TEST_OR_BUILD, FEATURE_GO) with concrete validation commands or checklists and requires their latest outputs.
  • Evidence evaluation and clear outcomes: Validates exit codes, command outputs, coverage and integration status, and returns VERIFIED, NOT_VERIFIED, or MANUAL_VERIFY_REQUIRED with documented gaps and next actions.
  • Use Case: Before marking a feature GO or trusting an autonomous subagent report, run the prescribed validation commands, attach fresh command outputs and exit codes, and let the Skill determine whether the claim is supported.

Quick Start

Verify the claim "FIX: resolve crash on startup" using the latest reproduction command output and exit code as fresh evidence.

Frequently Asked Questions about kiro-verify-completion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify task completion claims with fresh command-level evidence?

Verify completion claims by running prescribed validation commands, attaching fresh command outputs and exit codes, and evaluating current code state to return VERIFIED, NOT_VERIFIED, or MANUAL_VERIFY_REQUIRED with documented gaps.

What is the best way to prevent false fix claims during CI runs?

Prevent false fix claims by requiring fresh, scope-aligned evidence for FIX claims. Validate the latest reproduction command outputs and exit codes to ensure teams and agents do not trust stale or secondhand success reports.

How do I validate autonomous agent handoff reports before marking a feature GO?

Validate autonomous agent handoff reports by applying the FEATURE_GO claim-to-checklist mapping. Require fresh coverage and integration status evidence to determine whether the feature readiness claim is actually supported.

Does this verification process work with TEST_OR_BUILD claims in development workflows?

Yes, the verification process supports TEST_OR_BUILD claims. It validates exit codes and command outputs during development workflows, returning clear outcomes with documented gaps and next actions to prevent premature success reports.

When should I expect a MANUAL_VERIFY_REQUIRED outcome from completion verification?

Expect a MANUAL_VERIFY_REQUIRED outcome when submitted evidence contains documented gaps. The verification process returns this status when fresh command outputs, exit codes, or runtime state evidence are insufficient to fully support the claim.

What validation commands and evidence do I need to verify a development task claim?

To verify a development task claim, you need prescribed validation commands, fresh command outputs, current exit codes, and current code or runtime state evidence to evaluate whether the completion or success claim is fully supported.