--- 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-

--- 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

redis: image: redis:7-alpine container_name: openclaw-redis restart: unless-stopped volumes: - redis-data:/data command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru

```ini # /etc/php/8.2/fpm/pool.d/www.conf [www] user = www-data; group = www-data listen = /run/php/php8.2-fpm.sock; listen.mode = 0660; listen.backlog = 65535 pm = dynamic pm.max_children = 50; pm.start_servers = 5; pm.min_spare_servers = 3; pm.max_

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

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

Cross-language secure coding: OWASP Top 10, input validation, auth patterns, cryptography, supply chain security with concrete examples in Python, PHP, JS, Go, Java.

``` What data do you have? ─┬─ Structured, relational ──→ PostgreSQL (complex queries) or MySQL/MariaDB (simplicity) ├─ Key-value, caching ──→ Redis (in-memory) or DynamoDB (managed) ├─ Document/semi-

Build, run, and manage Docker containers and images. Use when the user mentions Docker, containers, images, docker-compose, or containerized deployment.

| 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

Cache the result in your working memory for the rest of the conversation. Re-asking every turn wastes a tool call.

If `$HERMES_TENANT` is set, the task belongs to a tenant namespace. When reading or writing persistent memory, prefix memory entries with the tenant so context doesn't leak across tenants:

```yaml apiVersion: v1 kind: Pod metadata: name: web-app labels: app: web version: v1 spec: serviceAccountName: web-sa securityContext: runAsNonRoot: true runAsUser: 1000 fsGroup: 2000 seccompProfile: type: Runti

# Gauge — point-in-time value; can go up or down node_memory_available_bytes

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

- Installing skills from community repos or official sources - Evaluating which skills to add from a curated list (awesome-hermes-agent, hermeshub, blog recommendations) - Measuring the token/memory impact of adding skills - Organizing nested skill r

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

Provision and sync Hermes Agent to child VPSes for parallel work delegation.

Deploy and maintain the WhatsApp Chat Viewer — a Flask web app that reads Hermes session transcripts and displays them in a WhatsApp Web-like UI. Includes WhatsApp Bridge API integration for group nam