gastown-operator

This skill enables an AI agent to orchestrate and manage Gas Town multi-agent systems on Kubernetes, using `kubectl-gt` commands to create, dispatch, and monitor resources like Rigs, Polecats, and Convoys.

22 stars
Complexity: medium

About this skill

The Gas Town Operator skill provides an AI agent with direct access to control the Gas Town Kubernetes Operator. It encapsulates the core functionalities needed to interact with Gas Town resources, such as creating new computation 'Rigs,' dispatching specific work units ('Beads') to them, and organizing these tasks into trackable 'Convoys.' The skill explicitly leverages the `kubectl-gt` CLI plugin, simplifying complex Kubernetes operations into golden commands. This skill is designed for automating the deployment, scaling, and monitoring of multi-agent workloads within a Kubernetes cluster. It allows an AI agent to respond to high-level user requests like 'create polecat' or 'deploy convoy' by executing the appropriate `kubectl-gt` commands, abstracting away the underlying YAML configurations and direct API calls. This is particularly useful for DevOps, SREs, or developers who need to quickly provision or manage distributed agent systems. By using this skill, users can delegate repetitive or complex Gas Town resource management tasks to an AI agent, ensuring consistency and reducing manual effort. It streamlines the workflow for setting up new agent environments, distributing computational tasks, and monitoring the health and progress of these systems within a Kubernetes-native context.

Best use case

The primary use case is automating the deployment, orchestration, and monitoring of the Gas Town multi-agent system on Kubernetes. DevOps teams, SREs, or developers managing Gas Town deployments would benefit most by enabling AI agents to handle routine setup, work dispatch, and health checks, reducing manual intervention and potential errors.

This skill enables an AI agent to orchestrate and manage Gas Town multi-agent systems on Kubernetes, using `kubectl-gt` commands to create, dispatch, and monitor resources like Rigs, Polecats, and Convoys.

The user should expect their Gas Town Kubernetes resources to be created, updated, or monitored as requested, with command-line output indicating the success or failure of the operation.

Practical example

Example input

Deploy a Gas Town Rig named 'athena' from `git@github.com:myorg/myrepo.git` with prefix 'dev' in the `gastown-system` namespace.

Example output

```bash
rig.gastown.gastown.io/athena created
```

When to use this skill

  • When needing to deploy a Gas Town Rig on a Kubernetes cluster.
  • When dispatching specific work units (Beads) to existing Gas Town Rigs.
  • When tracking batches of distributed work using Gas Town Convoys.
  • When monitoring the status or logs of Gas Town Polecats (worker agents).

When not to use this skill

  • When interacting with Kubernetes resources unrelated to Gas Town.
  • When the Gas Town Operator or `kubectl-gt` plugin is not installed on the target cluster/system.
  • When managing non-Kubernetes environments or non-Gas Town specific workloads.
  • When performing highly custom or unsupported Gas Town operations that require direct YAML manipulation outside of `kubectl-gt`.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/.claude/SKILL.md --create-dirs "https://raw.githubusercontent.com/boshu2/gastown-operator/main/.claude/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/.claude/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How gastown-operator Compares

Feature / Agentgastown-operatorStandard Approach
Platform SupportClaudeLimited / Varies
Context Awareness High Baseline
Installation ComplexitymediumN/A

Frequently Asked Questions

What does this skill do?

This skill enables an AI agent to orchestrate and manage Gas Town multi-agent systems on Kubernetes, using `kubectl-gt` commands to create, dispatch, and monitor resources like Rigs, Polecats, and Convoys.

Which AI agents support this skill?

This skill is designed for Claude.

How difficult is it to install?

The installation complexity is rated as medium. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Gas Town Operator Skill

Create Gas Town Kubernetes resources quickly and correctly.

**Use the kubectl-gt CLI** for normal workflows. YAML templates are for GitOps.

---

## Critical Facts

| Fact | Value |
|------|-------|
| API Group | `gastown.gastown.io/v1alpha1` |
| Operator NS | `gastown-system` |
| CRDs | Rig, Polecat, Convoy, Witness, Refinery, BeadStore |
| CLI Plugin | `kubectl-gt` |

---

## Golden Commands (CLI-First)

### Create Rig

```bash
kubectl gt rig create {{RIG}} \
  --git-url git@github.com:org/repo.git \
  --prefix {{PREFIX}} \
  -n gastown-system
```

### Dispatch Work (Sling)

```bash
# With explicit name
kubectl gt sling {{BEAD_ID}} {{RIG}} --name {{NAME}} -n gastown-system

# With themed name (mad-max, minerals, wasteland)
kubectl gt sling {{BEAD_ID}} {{RIG}} --theme mad-max -n gastown-system

# Wait for pod ready
kubectl gt sling {{BEAD_ID}} {{RIG}} --wait-ready --timeout 5m -n gastown-system
```

**Variables:** `{{BEAD_ID}}` (e.g., at-1234), `{{RIG}}` (e.g., athena), `{{NAME}}` (e.g., furiosa)

### Convoy (Batch Tracking)

```bash
kubectl gt convoy create "Wave 1" {{BEAD1}} {{BEAD2}} {{BEAD3}} -n gastown-system
```

### Monitor

```bash
kubectl gt polecat list -n gastown-system
kubectl gt polecat logs {{RIG}}/{{NAME}} -f -n gastown-system
kubectl gt polecat status {{RIG}}/{{NAME}} -n gastown-system
```

---

## CLI Commands

| Command | Description |
|---------|-------------|
| `kubectl gt rig list` | List rigs |
| `kubectl gt rig create <name>` | Create rig |
| `kubectl gt polecat list` | List polecats |
| `kubectl gt polecat logs <rig>/<name>` | Stream logs |
| `kubectl gt sling <bead> <rig>` | Dispatch work |
| `kubectl gt convoy list` | List convoys |
| `kubectl gt auth sync` | Sync Claude creds |

All commands support `-o json` and `-o yaml` output.

---

## Templates (YAML Alternative)

If you need declarative YAML (GitOps), templates are in `templates/`:

| Template | Use |
|----------|-----|
| `polecat-minimal.yaml` | Minimal K8s polecat (5 vars) |
| `polecat-kubernetes.yaml` | Full K8s polecat (all options) |
| `convoy.yaml` | Batch tracking |
| `secret-*.yaml` | Credentials |

**Validate:** `./scripts/validate-template.sh <file>`

---

## Quick Checks

```bash
kubectl gt rig list -n gastown-system          # List rigs
kubectl gt polecat list -n gastown-system      # List polecats
kubectl gt auth status -n gastown-system       # Check creds
kubectl get secrets -n gastown-system          # Check secrets
```

---

## Common Errors

| Error | Fix |
|-------|-----|
| `rig not found` | Create rig first: `kubectl gt rig create <name> --git-url ...` |
| `secret not found` | Create secrets: `kubectl create secret generic git-creds ...` |
| `missing gitRepository` | Fixed in v0.4.1 - sling now fetches from Rig |
| Stuck in Working | Check logs: `kubectl gt polecat logs <rig>/<name>` |

---

## JIT Load References

Load these when you need deeper context:

| Topic | Reference |
|-------|-----------|
| Full CRD specs | `.claude/references/CRD_REFERENCE.md` |
| Kubernetes mode | `.claude/references/KUBERNETES_MODE.md` |
| Troubleshooting | `.claude/references/TROUBLESHOOTING.md` |
| Anti-patterns | `FRICTION_POINTS.md` |
| Full templates | `templates/*.yaml` |

Related Skills

linux-shell-scripting

31392
from sickn33/antigravity-awesome-skills

Provide production-ready shell script templates for common Linux system administration tasks including backups, monitoring, user management, log analysis, and automation. These scripts serve as building blocks for security operations and penetration testing environments.

DevOps & InfrastructureClaude

iterate-pr

31392
from sickn33/antigravity-awesome-skills

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

DevOps & InfrastructureClaude

istio-traffic-management

31392
from sickn33/antigravity-awesome-skills

Comprehensive guide to Istio traffic management for production service mesh deployments.

DevOps & InfrastructureClaude

incident-runbook-templates

31392
from sickn33/antigravity-awesome-skills

Production-ready templates for incident response runbooks covering detection, triage, mitigation, resolution, and communication.

DevOps & InfrastructureClaude

incident-response-smart-fix

31392
from sickn33/antigravity-awesome-skills

[Extended thinking: This workflow implements a sophisticated debugging and resolution pipeline that leverages AI-assisted debugging tools and observability platforms to systematically diagnose and res

DevOps & InfrastructureClaudeGitHub Copilot

incident-responder

31392
from sickn33/antigravity-awesome-skills

Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive incident management.

DevOps & InfrastructureClaude

expo-cicd-workflows

31392
from sickn33/antigravity-awesome-skills

Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.

DevOps & InfrastructureClaude

error-diagnostics-error-trace

31392
from sickn33/antigravity-awesome-skills

You are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up error tracking systems, configure alerts, implement structured logging,

DevOps & InfrastructureClaude

error-debugging-error-trace

31392
from sickn33/antigravity-awesome-skills

You are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up error tracking systems, configure alerts, implement structured logging, and ensure teams can quickly identify and resolve production issues.

DevOps & InfrastructureClaude

error-debugging-error-analysis

31392
from sickn33/antigravity-awesome-skills

You are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents, and implementing comprehensive observability solutions.

DevOps & InfrastructureClaude

docker-expert

31392
from sickn33/antigravity-awesome-skills

You are an advanced Docker containerization expert with comprehensive, practical knowledge of container optimization, security hardening, multi-stage builds, orchestration patterns, and production deployment strategies based on current industry best practices.

DevOps & InfrastructureClaude

devops-troubleshooter

31392
from sickn33/antigravity-awesome-skills

Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability.

DevOps & InfrastructureClaude