production-deployment-phase
执行生产部署工作流程,通过将验证过的预发布构建升级到生产环境,使用语义版本控制、健康检查和发布标记。在运行/ship-prod命令、预发布验证后部署到生产环境或升级预发布构建到生产环境时使用。
📖 中文导读:执行生产部署工作流程,通过将验证过的预发布构建升级到生产环境,使用语义版本控制、健康检查和发布标记。在运行/ship-prod命令、预发布验证后部署到生产环境或升级预发布构建到生产环境时使用。 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。
name: production-deployment-phase description: Executes production deployment workflow by promoting validated staging builds to production with semantic versioning, health checks, and release tagging. Use when running /ship-prod command, deploying to production after staging validation, or promoting staging builds to production environment.
Execute production deployment workflow by promoting validated staging builds to production with semantic versioning, health checks, release tagging, and comprehensive monitoring. **Prerequisite-driven production promotion:**- Verify staging validation: Check state.yaml manual_gates.staging_validation.status = approved
- Bump semantic version: Update package.json/version files (major.minor.patch)
- Create release tag: Tag git commit with new version
- Deploy to production: Push to production branch or trigger deployment
- Run health checks: Verify endpoints, databases, services operational
- Generate ship report: Document deployment artifacts and metadata
- Monitor post-deploy: Watch logs, metrics, alerts for 15-30 minutes
Example workflow:
Verifying staging validation complete... ✅
Current version: 2.6.0
Bump type: minor (new features added)
New version: 2.7.0
Creating git tag v2.7.0... ✅
Pushing to production branch... ✅
Triggering production deployment... ✅
Health checks:
API endpoints: 200 OK ✅
Database connections: healthy ✅
Cache: operational ✅
CDN: propagated ✅
Production deployment successful!
Release: https://github.com/user/repo/releases/tag/v2.7.0
Ship report: specs/NNN-slug/production-ship-report.md
**Auto-invoke when:**
/ship-prodcommand executed- User mentions "deploy to production", "ship to prod", "production release"
- state.yaml shows current_phase: ship-prod
Prerequisites required:
- Staging validation approved (manual_gates.staging_validation.status = approved)
- Rollback gate passed (quality_gates.rollback.status = passed)
- Git repository has remote configured
- Production deployment configuration exists
Check workflow state for staging validation approval:
# Read workflow state
STATE_FILE="specs/$(ls -t specs/ | head -1)/state.yaml"
STAGING_STATUS=$(grep -A2 "staging_validation:" "$STATE_FILE" | grep "status:" | awk '{print $2}')
if [ "$STAGING_STATUS" != "approved" ]; then
echo "❌ BLOCKED: Staging validation not approved"
echo "Current status: $STAGING_STATUS"
echo "Run: /validate-staging to complete manual validation"
exit 1
fi
echo "✅ Staging validation approved"
Blocking conditions:
- Staging validation status ≠ approved
- Rollback gate status ≠ passed
- No staging deployment exists
Determine version bump type and update version files:
# Read current version
CURRENT_VERSION=$(node -p "require('./package.json').version")
# Determine bump type from CHANGELOG or git commits
# - major: Breaking changes
# - minor: New features (backward compatible)
# - patch: Bug fixes only
# Use npm version or manual update
npm version minor -m "chore: bump version to %s for production release"
NEW_VERSION=$(node -p "require('./package.json').version")
echo "Version bumped: $CURRENT_VERSION → $NEW_VERSION"
Semantic versioning rules:
- Major (X.0.0): Breaking changes, API contract changes
- Minor (0.X.0): New features, backward compatible
- Patch (0.0.X): Bug fixes, no new features
Files to update:
- package.json (version field)
- CHANGELOG.md (unreleased → version section)
- Any version constants in code
Tag the commit and push to remote:
# Create annotated tag
git tag -a "v${NEW_VERSION}" -m "Release v${NEW_VERSION}
$(sed -n "/## \[${NEW_VERSION}\]/,/## \[/p" CHANGELOG.md | head -n -1)"
# Push tag to remote
git push origin "v${NEW_VERSION}"
echo "✅ Tag created and pushed: v${NEW_VERSION}"
Tag format:
- Annotated tags required (not lightweight)
- Prefix with "v" (e.g., v2.7.0)
- Include CHANGELOG excerpt in tag message
Trigger production deployment based on deployment model:
# Model 1: Git push to production branch
git push origin main:production
# Model 2: GitHub Actions deployment
gh workflow run deploy-production.yml \
-f version="${NEW_VERSION}" \
-f environment=production
# Model 3: Direct deployment platform (Vercel, Netlify, etc.)
vercel --prod --yes
Deployment verification:
- Wait for deployment to complete
- Check deployment platform status
- Verify deployment ID/URL returned
- Record deployment metadata
Verify all critical services operational:
echo "Running production health checks..."
# API endpoints
for ENDPOINT in /health /api/status /api/version; do
STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://production.example.com$ENDPOINT")
if [ "$STATUS" = "200" ]; then
echo " ✅ $ENDPOINT: $STATUS OK"
else
echo " ❌ $ENDPOINT: $STATUS FAILED"
HEALTH_FAILED=true
fi
done
# Database connectivity
# (Run via deployment platform or SSH to production)
# Cache/Redis
# CDN propagation
# Background jobs
if [ "$HEALTH_FAILED" = "true" ]; then
echo "❌ Health checks failed - initiate rollback"
exit 1
fi
echo "✅ All health checks passed"
Critical checks:
- API endpoints return 200 OK
- Database connections healthy
- Cache/Redis operational
- CDN serving latest assets
- Background jobs processing
Create production-ship-report.md with deployment metadata:
cat > specs/$FEATURE_SLUG/production-ship-report.md <<EOF
# Production Ship Report: $FEATURE_SLUG
## Deployment Summary
- **Version**: v${NEW_VERSION}
- **Deployed at**: $(date -Iseconds)
- **Deployment ID**: ${DEPLOYMENT_ID}
- **Production URL**: https://production.example.com
- **Release URL**: https://github.com/user/repo/releases/tag/v${NEW_VERSION}
## Health Checks
- API endpoints: ✅ All passing
- Database: ✅ Healthy
- Cache: ✅ Operational
- CDN: ✅ Propagated
## Deployment Artifacts
- Git tag: v${NEW_VERSION}
- Commit SHA: ${COMMIT_SHA}
- Deployment platform: ${PLATFORM}
## Rollback Procedure
1. Revert git tag: git tag -d v${NEW_VERSION} && git push origin :refs/tags/v${NEW_VERSION}
2. Deploy previous version: git push origin v${PREVIOUS_VERSION}:production
3. Monitor health checks
EOF
echo "✅ Ship report generated"
Report contents:
- Deployment metadata (version, time, ID, URLs)
- Health check results
- Rollback procedure
- Post-deployment monitoring plan
Watch production for 15-30 minutes after deployment:
echo "Monitoring production (15-30 minutes)..."
echo "Watch for:"
echo " - Error rate spikes"
echo " - Performance degradation"
echo " - User reports/support tickets"
echo " - Background job failures"
# Monitor logs (varies by platform)
# - Vercel: vercel logs --follow
# - Heroku: heroku logs --tail
# - AWS: CloudWatch logs
# - Netlify: Netlify UI
echo "Monitor dashboard: https://monitoring.example.com/dashboard"
Monitoring checklist:
- Error rates normal (<1% increase)
- Response times acceptable (<10% degradation)
- No critical alerts triggered
- Background jobs processing normally
- No user-reported issues in first 30 minutes
If issues detected:
- Assess severity (critical vs minor)
- Initiate rollback if critical
- Apply hotfix if minor and fixable quickly
- Document incident for post-mortem
- ✓ Staging validation approved (state.yaml verified)
- ✓ Rollback gate passed (confidence in recovery procedure)
- ✓ Version bumped correctly (semantic versioning followed)
- ✓ Git tag created and pushed (v${VERSION} format)
- ✓ Production deployment triggered and completed
- ✓ Health checks passing (all critical services operational)
- ✓ Ship report generated (production-ship-report.md created)
- ✓ Post-deployment monitoring complete (15-30 minutes, no issues)
- ✓ Release URL accessible (GitHub release created)
- ✓ Deployment metadata recorded (ID, URLs, timestamps)
Quality gates passed:
- No critical errors in first 30 minutes
- Error rate <1% increase from baseline
- Response times <10% degradation
- No user-reported critical issues
- All background jobs processing normally