Run any Skill in Manus with one click

juliaz-devops

Service management, process supervision, and operational tasks for the juliaz_agents multi-agent system. Trigger whenever Raphael asks to start, stop, restart, or check the status of any service — PM2, Docker, bridge, orchestrator, OpenClaw, cowork-mcp, frontend, or backend. Also trigger for: environment variable management, port conflicts, log tailing, deployment, health checks, 'is Julia running', 'start everything', 'check status', 'why is X down', pm2, docker compose, or any operational/infrastructure task. If the user mentions starting services, checking health, or managing processes — use this skill.

Run Skill in Manus

Overview

Install command

npx skills add https://github.com/abzhaw/juliaz_agents --skill juliaz-devops

Copy and paste this command into Claude Code to install the skill

Source

abzhaw/juliaz_agents

Stars0

Forks0

UpdatedMarch 8, 2026 at 21:07

SKILL.md

readonly

More from this repository

same repository

juliaz-agent-architect

abzhaw/juliaz_agents

Architecture patterns and anti-patterns for Julia's multi-agent system. Trigger when making architectural decisions — adding agents, changing message flow, redesigning tool registries, or evaluating the system's structure. Also trigger for: 'architecture', 'system design', 'how should agents work together', 'add a new agent', 'agent patterns', or any structural question about the multi-agent system.

2026-03-080

juliaz-agent-builder

abzhaw/juliaz_agents

Scaffolding and creating new agents or sub-agents within the juliaz_agents ecosystem. Trigger whenever Raphael wants to create a new agent, add a new sub-agent, define a new agent's personality/identity, set up agent heartbeats, or modify an existing agent's SOUL/IDENTITY/TOOLS/AGENTS files. Also trigger when discussing agent conventions, the SOUL.md pattern, or how agents should be structured in this project. If someone says 'new agent', 'create an agent', 'agent personality', 'SOUL.md', or 'add a bot' — this is the skill to use.

2026-03-080

juliaz-agent-improve

abzhaw/juliaz_agents

Systematic improvement of Julia's agents through performance analysis, prompt engineering, and validation. Trigger when optimizing any agent's behavior — orchestrator, frontend Julia, OpenClaw relay, or any sub-agent. Also trigger for: 'improve agent', 'agent not working well', 'optimize prompt', 'tool not being used correctly', 'Julia gives wrong answers', or any agent quality issue.

2026-03-080

juliaz-debug

abzhaw/juliaz_agents

Cross-system diagnostics and troubleshooting for the juliaz_agents multi-agent system. Trigger when Raphael reports something is broken, not working, or behaving unexpectedly — messages not arriving, Julia not responding, bridge errors, orchestrator crashes, rate limits, silent failures, queue issues, or any 'why isn't X working' question. Also trigger for: 'debug', 'broken', 'not working', 'error', 'Julia isn't responding', 'messages stuck', 'bridge down', 'check logs', 'what went wrong', or any troubleshooting request. If something in the multi-agent system is misbehaving, this is the skill to reach for.

2026-03-080

juliaz-feature

abzhaw/juliaz_agents

Adding new features to the juliaz_agents system — new tools, API endpoints, frontend components, MCP tools, or capabilities. Trigger when Raphael wants to: add a new tool to the orchestrator or bridge, create a new API endpoint in the backend, add a frontend component or page, extend cowork-mcp with new Claude tools, add a new OpenClaw skill, or implement any new capability across the system. Also trigger for 'add a tool', 'new endpoint', 'new page', 'new component', 'extend Julia', 'Julia should be able to...', or any request to add functionality to the multi-agent system.

2026-03-080

juliaz-system

abzhaw/juliaz_agents

Foundational knowledge about the juliaz_agents multi-agent system architecture. ALWAYS trigger this skill when the conversation involves ANY component of Julia's agent ecosystem — orchestrator, bridge, cowork-mcp, OpenClaw, frontend, backend, ADHD agent, julia_medium_agent, or thesis workspace. Also trigger when Raphael asks 'where is X', 'how does X work', 'what connects to what', or any architectural/navigation question about the system. This is the map of the entire codebase and how the pieces fit together.

2026-03-080

Source

abzhaw

abzhaw/juliaz_agents

View GitHub Repository View Creator Repositories

Install command

Download

Run Skill in Manus

Useful forSOC

Network and Computer Systems AdministratorsComputer and Mathematical Occupations15-1244L4

name

juliaz-devops

description

juliaz-devops — Service Management & Operations

Operational knowledge for running, monitoring, and troubleshooting the juliaz_agents infrastructure.

Service Map

Service	Manager	Port	Start Command	Health Check
Backend API	Docker Compose	3000	`cd julia/backend && docker compose up -d`	`curl http://localhost:3000/health`
Bridge	PM2	3001	`pm2 start ecosystem.dev.config.js --only bridge`	`curl http://localhost:3001/health`
Frontend	PM2	3002	`pm2 start ecosystem.dev.config.js --only frontend`	`curl http://localhost:3002`
Cowork MCP	PM2	3003	`pm2 start ecosystem.dev.config.js --only cowork-mcp`	`curl http://localhost:3003/health`
Orchestrator	PM2	—	`pm2 start ecosystem.dev.config.js --only orchestrator`	Check PM2 status
OpenClaw	CLI	18789 (ws)	`openclaw gateway start --force`	`openclaw health`

Start Everything (Development)

# 1. Backend (Docker — must be first, other services depend on DB)
cd julia/backend && docker compose up -d

# 2. All PM2 services (bridge, frontend, cowork-mcp, orchestrator)
pm2 start ecosystem.dev.config.js

# 3. OpenClaw gateway (separate because it's a CLI tool)
openclaw gateway start --force

Or use the convenience script:

./start-devops.sh

Stop Everything

pm2 stop all
cd julia/backend && docker compose down
openclaw gateway stop  # if applicable

PM2 Operations

# Status of all services
pm2 list

# Tail all logs
pm2 logs

# Tail specific service
pm2 logs bridge
pm2 logs orchestrator

# Restart a specific service
pm2 restart bridge
pm2 restart orchestrator

# Restart all
pm2 restart all

# Delete all (clean slate)
pm2 delete all

# Start production config
pm2 start ecosystem.config.js

# Start development config
pm2 start ecosystem.dev.config.js

PM2 Config Details

Both ecosystem.config.js and ecosystem.dev.config.js include:

Auto-restart with exponential backoff
10-restart cap before giving up
Environment variable injection from .env.secrets
cwd set to each service's directory

Key difference: dev config uses npm run dev (with watch/hot reload), production uses npm run start.

Docker Operations (Backend Only)

# Start
cd backend && docker compose up -d

# Check status
docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}"

# View logs
docker compose -f julia/backend/docker-compose.yml logs -f

# Rebuild after schema changes
cd julia/backend && docker compose down && docker compose up -d --build

# Reset database (destructive!)
cd julia/backend && docker compose down -v && docker compose up -d
# Then: npx prisma migrate deploy (or npx prisma db push)

Port Map

3000 → Backend REST API (Docker)
3001 → Bridge MCP Server
3002 → Frontend Next.js Dashboard
3003 → Cowork MCP (Claude delegation)
18789 → OpenClaw WebSocket gateway
5432 → PostgreSQL (Docker, internal)

To check what's using a port:

lsof -i :3000 -i :3001 -i :3002 -i :3003 -P -n

Environment Variables

Template: .env.example Live secrets: .env.secrets (NEVER commit this)

Key variables:

Variable	Used By	Purpose
`ANTHROPIC_API_KEY`	orchestrator, cowork-mcp	Claude API access
`OPENAI_API_KEY`	orchestrator, frontend	GPT-4o fallback + frontend chat
`DATABASE_URL`	backend	PostgreSQL connection string
`LOB_API_KEY`	orchestrator	Physical letter sending
`CLAUDE_MODEL`	cowork-mcp	Override default model (defaults to claude-haiku-4-5-20251001)
`DEFAULT_MODEL`	orchestrator	Override orchestrator model
`POLL_INTERVAL_MS`	orchestrator	Bridge polling interval (default 5000)

Health Check Commands

Quick system-wide health check:

echo "=== PM2 ===" && pm2 list 2>&1
echo "=== Docker ===" && docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}"
echo "=== Ports ===" && lsof -i :3000 -i :3001 -i :3002 -i :3003 -P -n
echo "=== Bridge ===" && curl -s http://localhost:3001/health | python3 -m json.tool
echo "=== Backend ===" && curl -s http://localhost:3000/health
echo "=== Cowork ===" && curl -s http://localhost:3003/health
echo "=== OpenClaw ===" && openclaw health 2>&1

Common Issues & Fixes

Symptom	Likely Cause	Fix
Bridge not responding	PM2 process crashed	`pm2 restart bridge`
"EADDRINUSE" on startup	Port already in use	`lsof -i :<port>` then `kill <PID>`
Orchestrator not replying	Bridge is down, or API key expired	Check bridge health first, then check `.env.secrets`
Cowork MCP 500 errors	Missing ANTHROPIC_API_KEY	Verify `.env.secrets` has valid key
Docker containers gone	Docker Desktop restarted	`cd julia/backend && docker compose up -d`
OpenClaw can't connect	Gateway not started	`openclaw gateway start --force`
Frontend build fails	Missing deps or TS errors	`cd julia/frontend && npm install && npx next build`
PM2 shows "errored"	Check logs	`pm2 logs <service-name> --lines 50`
Database connection refused	PostgreSQL container down	`docker compose -f julia/backend/docker-compose.yml up -d`
Rate limit errors (429)	Too many API calls	Orchestrator has built-in backoff; wait or increase `POLL_INTERVAL_MS`

Build Commands

# Backend
cd julia/backend && npm run build

# Bridge
cd julia/bridge && npm run build

# Frontend
cd julia/frontend && npx next build

# Cowork MCP
cd julia/cowork-mcp && npm run build

# Orchestrator
cd julia/orchestrator && npm run build

# TypeScript check (all)
npx tsc --noEmit  # from each service directory

Testing

# Backend (only component with tests configured)
cd julia/backend && npm test

# Frontend lint
cd julia/frontend && npx next lint

Logs Location

PM2 logs are stored at ~/.pm2/logs/:

bridge-out.log, bridge-error.log
orchestrator-out.log, orchestrator-error.log
frontend-out.log, frontend-error.log
cowork-mcp-out.log, cowork-mcp-error.log

OpenClaw Operations

# Check status
openclaw status

# Start gateway
openclaw gateway start --force

# View dashboard
openclaw dashboard

# Send a task to OpenClaw's agent
openclaw agent --message "Send a summary to +1234567890 on WhatsApp" --thinking high

# Tail events
openclaw logs

# Health check
openclaw health