Llmops-demo-ts deploy
Deploy the application or manage infrastructure. Handles Docker builds, CI/CD, and deployment workflows.
install
source · Clone the upstream repo
git clone https://github.com/yu-iskw/llmops-demo-ts
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/yu-iskw/llmops-demo-ts "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.claude/skills/deploy" ~/.claude/skills/yu-iskw-llmops-demo-ts-deploy && rm -rf "$T"
manifest:
.claude/skills/deploy/SKILL.mdsource content
Deploy
Execute the following deployment/infrastructure task:
$ARGUMENTS
Pre-deployment Checklist
- Verify build:
pnpm build - Run tests:
pnpm test - Check lint:
pnpm lint - Review environment: Verify .env configuration
Docker Deployment
# Build and start all services docker-compose up --build # Build specific service docker-compose build [service-name] # View logs docker-compose logs -f [service-name]
Environment Variables
Required variables (see .template.env):
/GOOGLE_CLOUD_PROJECT
— AI provider credentialsGOOGLE_API_KEY
— Observability (optional)LANGSMITH_API_KEY
— Backend server port (default: 3000)PORT
Post-deployment Verification
- Health check:
curl http://localhost:3000/health - Agent types:
curl http://localhost:3000/chat/agent-types - Test chat: Send a test message through the UI or API