OpenParable
Skip to content
← Back to skills

Validate Delivery

Testing & Quality
validate-delivery

Validate Delivery is an Agent Skill for testing & quality published in the agent-sh/agentsys repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when user asks to "validate delivery", "check readiness", or "verify completion". Runs tests, build, and requirement checks with pass/fail instructions.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/agent-sh/agentsys/blob/HEAD/.kiro/skills/validate-delivery/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/validate-delivery, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

validate-delivery

Autonomously validate that a task is complete and ready to ship.

Validation Checks

Check 1: Review Status

function checkReviewStatus(reviewResults) {
  if (!reviewResults) return { passed: false, reason: 'No review results' };
  if (reviewResults.approved) return { passed: true };
  if (reviewResults.override) return { passed: true, override: true };
  return { passed: false, reason: 'Review not approved' };
}

Check 2: Tests Pass

# Detect test runner and run
if grep -q '"test"' package.json; then
  npm test; TEST_EXIT_CODE=$?
elif [ -f "pytest.ini" ]; then
  pytest; TEST_EXIT_CODE=$?
elif [ -f "Cargo.toml" ]; then
  cargo test; TEST_EXIT_CODE=$?
elif [ -f "go.mod" ]; then
  go test ./...; TEST_EXIT_CODE=$?
else
  TEST_EXIT_CODE=0  # No tests
fi

Check 3: Build Passes

if grep -q '"build"' package.json; then
  npm run build; BUILD_EXIT_CODE=$?
elif [ -f "Cargo.toml" ]; then
  cargo build --release; BUILD_EXIT_CODE=$?
elif [ -f "go.mod" ]; then
  go build ./...; BUILD_EXIT_CODE=$?
else
  BUILD_EXIT_CODE=0  # No build step
fi

Check 4: Requirements Met

async function checkRequirementsMet(task, changedFiles) {
  const requirements = extractRequirements(task.description);
  const results = [];

  for (const req of requirements) {
    const implemented = await verifyRequirement(req, changedFiles);
    results.push({ requirement: req, implemented });
  }

  return {
    passed: results.every(r => r.implemented),
    requirements: results
  };
}

function extractRequirements(description) {
  const reqs = [];
  // Extract bullet points: - Item
  const bullets = description.match(/^[-*]\s+(.+)$/gm);
  if (bullets) reqs.push(...bullets.map(m => m.replace(/^[-*]\s+/, '')));
  // Extract numbered items: 1. Item
  const numbered = description.match(/^\d+\.\s+(.+)$/gm);
  if (numbered) reqs.push(...numbered.map(m => m.replace(/^\d+\.\s+/, '')));
  return [...new Set(reqs)].slice(0, 10);
}

Check 5: No Regressions

# Compare test counts before/after changes
git stash
BEFORE=$(npm test 2>&1 | grep -oE '[0-9]+ passing' | grep -oE '[0-9]+')
git stash pop
AFTER=$(npm test 2>&1 | grep -oE '[0-9]+ passing' | grep -oE '[0-9]+')
[ "$AFTER" -lt "$BEFORE" ] && REGRESSION=true || REGRESSION=false

Aggregate Results

const checks = {
  reviewClean: checkReviewStatus(reviewResults),
  testsPassing: { passed: TEST_EXIT_CODE === 0 },
  buildPassing: { passed: BUILD_EXIT_CODE === 0 },
  requirementsMet: await checkRequirementsMet(task, changedFiles),
  noRegressions: { passed: !REGRESSION }
};

const allPassed = Object.values(checks).every(c => c.passed);
const failedChecks = Object.entries(checks)
  .filter(([_, v]) => !v.passed)
  .map(([k]) => k);

Decision and Output

If All Pass

workflowState.completePhase({
  approved: true,
  checks,
  summary: 'All validation checks passed'
});

return { approved: true, checks };

If Any Fail

const fixInstructions = generateFixInstructions(checks, failedChecks);

workflowState.failPhase('Validation failed', {
  approved: false,
  failedChecks,
  fixInstructions
});

return { approved: false, failedChecks, fixInstructions };

Fix Instructions Generator

function generateFixInstructions(checks, failedChecks) {
  const instructions = [];

  if (failedChecks.includes('testsPassing')) {
    instructions.push({ action: 'Fix failing tests', command: 'npm test' });
  }
  if (failedChecks.includes('buildPassing')) {
    instructions.push({ action: 'Fix build errors', command: 'npm run build' });
  }
  if (failedChecks.includes('requirementsMet')) {
    const unmet = checks.requirementsMet.requirements
      .filter(r => !r.implemented)
      .map(r => r.requirement);
    instructions.push({ action: 'Implement missing', details: unmet.join(', ') });
  }

  return instructions;
}

Output Format

{
  "approved": true|false,
  "checks": {
    "reviewClean": { "passed": true },
    "testsPassing": { "passed": true },
    "buildPassing": { "passed": true },
    "requirementsMet": { "passed": true },
    "noRegressions": { "passed": true }
  },
  "failedChecks": [],
  "fixInstructions": []
}

Constraints

  • NO human intervention - fully autonomous
  • Returns structured JSON for orchestrator
  • Generates specific fix instructions on failure
  • Workflow retries automatically after fixes