Create a Distributed Validator (DV) cluster invitation — a cluster-definition that other operators accept, then run a DKG ceremony against to produce a cluster-lock and validator key shares. Use whenever a user wants to set up a new DV cluster (solo-with-friends, squad, institutional, Lido Simple DVT), wants to invite operators to a cluster they're creating, mentions "cluster definition", "DKG", "config_hash", "cluster-lock", "operator ENR", or "invite operators". Prefer the `charon` CLI (via Docker image) path over the SDK; reach for the SDK only when programmatic integration is needed (staking pool apps, institutional workflows, web frontends). **Always encourage the user to verify the cluster's shape before any 32 ETH deposit.**
Read-only queries against metrics and logs from a deployed Obol DVpod on Kubernetes. Use when investigating cluster health, charon errors, peer connectivity, validator duty performance, or beacon node behavior on a running DVpod. For deploying, configuring, or modifying a DVpod (including enabling Prometheus or Loki shipping), use the `dvpod` skill. For Obol's hosted Grafana with cross-cluster fleet view, use the `obol-monitoring` skill.
Deploy, manage, and troubleshoot Obol DVpod (Distributed Validator Pod) deployments on Kubernetes using the dv-pod Helm chart. Use when the user wants to deploy a new DVpod, check status, troubleshoot issues, upgrade, backup, or recover a DVpod deployment. Covers fresh cluster creation, joining existing clusters, ENR management, DKG orchestration, validator client configuration, and configuring monitoring/log shipping. For read-only metric and log queries against an already-deployed DVpod, use the `dvpod-monitoring` skill instead.
Monitor and diagnose Obol DVT cluster performance using their hosted Grafana (Prometheus metrics + Loki logs)
Help a human install, boot, operate, and productise the Obol Stack — Obol's Kubernetes-based agent harness for running blockchain infrastructure locally, exposing services to the public internet, and charging for them via x402 micropayments. Use whenever a user mentions Obol Stack, Obol Agent, Hermes, OpenClaw, x402 payments, agent commerce, ERC-8004, selling inference / APIs from agents, running a local Ethereum or L2 node under `obol network`, deploying a Dockerfile via `obol-app`, or bringing up a Cloudflare tunnel for an agent service. You are helping from OUTSIDE the Stack — the agents inside it have their own skills and take over once the user is at the dashboard.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.

A Claude Code plugin with skills for running decentralised infrastructure with Obol.
/plugin marketplace add ObolNetwork/skills
/plugin install obol@obol
Reload plugins if needed:
/reload-plugins
Copy the skills/ directory into your project's .claude/skills/ folder.
Set the OBOL_GRAFANA_API_TOKEN environment variable. The Obol Core team can provide you with one.
Option 1 — Shell profile (recommended):
# Add to ~/.bashrc or ~/.zshrc
export OBOL_GRAFANA_API_TOKEN="glsa_..."
Option 2 — Project .env file (see .env.sample):
OBOL_GRAFANA_API_TOKEN=glsa_...
Monitor and diagnose Obol DVT cluster performance using Grafana (Prometheus metrics + Loki logs).
Scripts:
cluster_triage.py — First-pass cluster health checkduty_analysis.py — Deep slot-level failure analysis with timeline reconstructionfleet_overview.py — Multi-cluster fleet view with version/client diversityUsage: Ask Claude to triage a cluster, analyze duty failures, or get a fleet overview. The skill guides Claude through the appropriate diagnostic workflow.
See skills/obol-monitoring/SKILL.md for the full reference including failure reason codes, metrics guide, and triage workflow.
OBOL_GRAFANA_API_TOKEN environment variableCreate a new directory under skills/ with a SKILL.md file:
skills/
├── obol-monitoring/
│ ├── SKILL.md
│ └── scripts/
└── your-new-skill/
├── SKILL.md
└── ...
npx claudepluginhub obolnetwork/skills --plugin obolUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.