agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Generate deployment configurations (Docker, Kubernetes) for the current project
$ npx -y skills add jmagly/aiwg --skill deploy-gen --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/deploy-genContext preview
The summary Claude sees to decide when to auto-load this skill.
Generate deployment configurations (Docker, Kubernetes) for the current project
namespace: aiwg name: deploy-gen platforms: [all] description: Generate deployment configurations (Docker, Kubernetes) for the current project
<!-- AIWG-SKILL-CALLOUT --> > **Skill access pattern (post-kernel-pivot, 2026.5+)** > > Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via: > > ```bash > aiwg discover "<capability>" > aiwg show skill <name> > ``` > > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).
Generate production-ready deployment configurations based on project analysis.
**REF-001**: BP-8 - Containerized Deployment
> "Production-grade agentic workflows require containerized deployment with proper isolation, resource management, and orchestration."
/deploy-gen docker [options] /deploy-gen k8s [options] /deploy-gen compose [options]
| Argument | Required | Description | |----------|----------|-------------| | type | Yes | Deployment type: docker, k8s, compose |
| Option | Default | Description | |--------|---------|-------------| | --output | ./deploy/ | Output directory for generated files | | --app-name | (from package.json) | Application name | | --port | 3000 | Application port | | --multi-stage | true | Use multi-stage Dockerfile | | --health-check | true | Include health check endpoints |
Detect project characteristics:
Analyzing project... - Runtime: [node/python/go/java] - Package manager: [npm/yarn/pip/go mod] - Entry point: [detected or ask] - Dependencies: [count] - Build required: [yes/no]
Choose appropriate templates based on analysis:
| Runtime | Template | |---------|----------| | Node.js | `templates/deploy/docker/node.Dockerfile` | | Python | `templates/deploy/docker/python.Dockerfile` | | Go | `templates/deploy/docker/go.Dockerfile` |
Generate deployment files with project-specific values.
deploy/ ├── Dockerfile # Multi-stage build ├── .dockerignore # Exclude dev files └── docker-build.sh # Build helper script
deploy/k8s/ ├── deployment.yaml # Pod specification ├── service.yaml # Service exposure ├── configmap.yaml # Environment configuration ├── hpa.yaml # Horizontal Pod Autoscaler └── kustomization.yaml # Kustomize base
deploy/ ├── docker-compose.yml # Service definition ├── docker-compose.dev.yml # Development overrides └── .env.example # Environment template
# Generate Dockerfile for Node.js project /deploy-gen docker # Generate full Kubernetes manifests /deploy-gen k8s --app-name my-api --port 8080 # Generate Docker Compose for local development /deploy-gen compose --output ./ # Generate all deployment types /deploy-gen docker && /deploy-gen k8s && /deploy-gen compose
Templates use these variables:
| Variable | Source | |----------|--------| | `{{APP_NAME}}` | --app-name or package.json | | `{{PORT}}` | --port option | | `{{NODE_VERSION}}` | .nvmrc or latest LTS | | `{{PYTHON_VERSION}}` | .python-version or 3.11 | | `{{ENTRY_POINT}}` | Detected from project |
aiwg deploy-gen <type> [options]
From Unified Plan:
| Metric | Target | |--------|--------| | Zero to containerized | <2 minutes | | Generated configs | Production-ready | | Security baseline | Non-root, minimal image |
Generate deployment for: $ARGUMENTS
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing