--- name: hermes-agent-mastery description: "Definitive mastery-level skill for Hermes Agent internals, configuration, and operations. Covers architecture, multi-provider LLM routing, gateway ops, skill authoring, cron/background jobs, memory/hindsig

--- name: openclaw-mastery description: "Complete mastery of OpenClaw — the open-source AI agent platform. Covers Docker gateway deployment, ClawHub skill ecosystem, browser automation (CamoFox/Patchright/Scrapling), multi-provider LLM config, prompt

--- name: openclaw-install description: "Deploy OpenClaw (openclaw.ai) — the open-source AI agent platform with Docker gateway, ClawHub skills, browser automation, and multi-provider LLM support." version: 1.0.0 metadata: hermes: tags: [opencla

1. [Overview & Tool Landscape](#overview--tool-landscape) 2. [HCL Syntax & Core Concepts](#hcl-syntax--core-concepts) 3. [Providers — AWS, GCP, Azure & Multi-Cloud](#providers--aws-gcp-azure--multi-cloud) 4. [Resources](#resources) 5. [Data Sources](

--- name: ai-agent-mastery description: "Comprehensive mastery of AI agent architecture, patterns, and engineering. Covers MCP server design, agent spawning/delegation, ACP protocol, x402 payment, memory systems, prompt engineering for agents, multi-

Comprehensive PHP mastery covering modern PHP 8+, OOP & design patterns, security, frameworks, database/ORM, testing, performance, deployment, and production operations.

End-to-end CI/CD pipeline mastery — GitHub Actions, GitLab CI, Jenkins, deployment strategies, and release automation

| Source | URL | Skills | Quality | |--------|-----|--------|---------| | Official Hermes Skills Hub | agentskills.io / `hermes skills browse` | Curated | High | | awesome-hermes-agent | github.com/0xNyk/awesome-hermes-agent | 100+ links | Curated li

## Key Files & Paths | Path | Purpose | |------|---------| | `~/.hermes/skills/` | Installed skill directories (gateway scans depth 2) | | `~/.hermes/skill-repos/` | Cloned git repos for persistence + future pulls | | `/usr/local/lib/hermes-agent/opt

[Install] WantedBy=multi-user.target ```

--- name: kanban-orchestrator description: Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worke

| Component | Purpose | |-----------|---------| | **kube-apiserver** | REST API entry point; validates and stores data in etcd | | **etcd** | Distributed key-value store; single source of truth for cluster state | | **kube-scheduler** | Assigns pods

Production monitoring, observability, and SRE practices — Prometheus, Grafana, Alertmanager, Loki, Jaeger, OpenTelemetry, and incident management

# Check DNS propagation dnsviz.net # Online tool # Or use multiple resolvers for dns in 8.8.8.8 1.1.1.1 9.9.9.9; do echo "=== $dns ===" && dig @$dns example.com A +short done

Design scalable distributed systems using structured approaches — load balancing, caching, message queues, databases, and microservices

### One-shot LLM queries (preferred over hermes chat) ```bash llm-ask <provider> "question" llm-ask groq "What is 7*8?" # Free, 212 tok/s llm-ask opencode-go "Explain X" # Default provider llm-ask openrouter "Research Y" # 33+ free m

Production-grade front-end engineering: semantic HTML5, scalable CSS architecture, responsive design, performance optimization, and security hardening.

```nginx # /etc/nginx/nginx.conf user www-data; worker_processes auto; worker_rlimit_nofile 65535; events { worker_connections 4096; multi_accept on; use epoll; } http { sendfile on; tcp_nopush on; tcp_nodelay on; keepalive_timeout 65; server_tok

### State Management: Provider & Riverpod

Named slots (`@folder`) render multiple pages in one layout simultaneously:

Comprehensive Python mastery skill covering architecture, idiomatic code, design patterns, security, testing, performance, and deployment for production-grade Python applications.

React mastery: hooks deep dive, state management, component patterns, security, performance optimization, and testing.

### MariaDB Galera Cluster Setup ```bash # my.cnf (each node) [mysqld] binlog-format=ROW default-storage-engine=InnoDB innodb-auto-increment-offset=1 # Node 1=1, Node 2=2, Node 3=3 wsrep-provider=/usr/lib/galera/libgalera_smm.so wsrep-cluster-addr

### Building Images 1. Analyze the project to determine base image and dependencies 2. Create a multi-stage Dockerfile for minimal final image 3. Build: `docker build -t name:tag .` 4. Verify: `docker images | grep name`

--- name: kanban-worker description: Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load

Production server hardening — SSH, fail2ban, UFW/iptables, auditd, kernel tuning, intrusion detection, and compliance

Discover, evaluate, install, and organize Hermes Agent skills from community repos and official sources. Handles parallel cloning, nested repo symlinking, frontmatter validation, token impact measurem

Webhook subscriptions: event-driven agent runs.

[Install] WantedBy=multi-user.target ```