⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
openclaw-opc-orchestrator
One-person-company multi-agent orchestrator for OpenClaw — set up agent teams, roles, schedules, handoffs, daily briefings, and health checks.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
OpenClaw OPC Orchestrator 🤖🏢
Run your entire one-person company with a team of AI agents — orchestrated by OpenClaw.
One-Person Company (OPC) × AI Agent Team — This skill turns OpenClaw into a multi-agent orchestrator that manages your entire business workflow. Define agent roles, set up cron schedules, coordinate tasks, and let your AI team handle marketing, content, SEO, community, and more.
Built from real-world experience running 妙趣AI (Miaoquai) — a solo-operated AI tools & news platform powered by 5+ AI agents.
🎯 Why This Exists
The "one-person company" model is becoming viable with AI agents, but most people struggle with:
- Agent coordination — who does what, when?
- Task scheduling — how do you keep everything running 24/7?
- Handoff protocols — how do agents pass work to each other?
- Quality control — how do you review agent outputs?
This skill provides battle-tested templates and orchestration patterns from a real OPC running in production.
🚀 Quick Start
Install as OpenClaw Skill
# Copy to your OpenClaw skills directory
cp -r openclaw-opc-orchestrator ~/.openclaw/skills/opc-orchestrator
# Or install from GitHub
git clone https://github.com/jingchang0623-crypto/openclaw-opc-orchestrator.git ~/.openclaw/skills/opc-orchestrator
Configure Your Agent Team
# ~/.openclaw/opc-team.yaml
company:
name: "Your Company"
website: "https://your-site.com"
agents:
marketing:
role: "Marketing & Content Agent"
schedule: "0 8 * * *" # Daily at 8am
tasks:
- generate_news_digest
- social_media_posts
seo:
role: "SEO & Content Agent"
schedule: "0 1 * * *" # Daily at 1am
tasks:
- generate_tool_pages
- internal_link_audit
community:
role: "Community Agent"
schedule: "0 10,16,22 * * *" # 3x daily
tasks:
- github_discussions
- discord_updates
monitor:
role: "Trends Monitor"
schedule: "0 5,12,18 * * *" # 3x daily
tasks:
- trending_scan
- competitor_check
Run Orchestration
# Check agent status
openclaw "use the opc-orchestrator skill to show my agent team status"
# Generate a new agent role
openclaw "use the opc-orchestrator skill to create a customer-support agent role"
# Run daily briefing
openclaw "use the opc-orchestrator skill to generate today's briefing for all agents"
🤖 Included Agent Templates
| Agent Role | Schedule | Key Tasks |
|---|---|---|
| 🎯 Marketing Agent | 08:00/22:00 | News digest, social media, ad copy |
| 🔍 SEO Agent | 01:00/03:00 | Tool pages, glossary, link audit |
| 💬 Community Agent | 10:00/16:00/22:00 | GitHub, Discord, dev communities |
| 📡 Trends Monitor | 05:00/12:00/18:00 | GitHub trending, news, competitors |
| 📝 Content Agent | 06:00 | Blog posts, tutorials, stories |
| 📊 Analytics Agent | 22:00 | Daily reports, metrics, insights |
📁 Project Structure
openclaw-opc-orchestrator/
├── SKILL.md # Skill definition
├── package.json # Package config
├── README.md # This file
├── LICENSE # MIT
├── src/
│ ├── orchestrator.js # Core orchestration logic
│ ├── status.js # Agent status checker
│ └── scheduler.js # Cron schedule manager
├── docs/
│ ├── agent-roles.md # Detailed agent role specs
│ ├── handoff-protocols.md # Inter-agent handoff rules
│ └── opc-playbook.md # Full OPC playbook
└── templates/
├── team-config.yaml # Sample team configuration
├── agent-role.yaml # Single agent role template
└── daily-briefing.md # Daily briefing template
🔧 Advanced: Cron-Based Automation
Set up each agent as a cron job in OpenClaw:
# Marketing Agent - daily news digest
openclaw cron add \
--name "marketing-daily" \
--schedule "0 8 * * *" \
--message "Generate today's AI news digest for miaoquai.com"
# SEO Agent - nightly tool page generation
openclaw cron add \
--name "seo-nightly" \
--schedule "0 1 * * *" \
--message "Generate 5 AI tool detail pages for SEO"
# Community Agent - 3x daily
openclaw cron add \
--name "community-morning" \
--schedule "0 10 * * *" \
--message "Check GitHub Discussions and respond"
🔄 Handoff Protocol
Agents pass work using a shared memory system:
## Agent Handoff Log
### [Timestamp] Marketing → SEO
- Generated: ai-news-2026-04-22.html
- Action needed: Add internal links from tool pages
- Priority: Normal
### [Timestamp] Monitor → Marketing
- Detected: OpenClaw v2026.4.15 released
- Action needed: Include in today's news digest
- Priority: High
💡 OPC Principles (From Real Experience)
- Automation First — If you do it twice, cron it
- Quality Gates — Always review before publish
- Memory Systems — Agents need persistent context
- Graceful Degradation — If one agent fails, others continue
- Inter-Agent Communication — Shared memory > direct messaging
🌐 Real-World Example
妙趣AI (Miaoquai) runs on this pattern:
- 5+ AI agents handling marketing, SEO, community, monitoring, and content
- 20+ cron jobs running 24/7
- 128+ glossary pages, 142+ RSS digest issues, 124+ tutorials
- GitHub: 40+ discussions, 8 topics, 4 open-source tools
- All operated by one human with AI agent orchestration
🤝 Contributing
Contributions welcome! Especially:
- New agent role templates
- Handoff protocol improvements
- Integration with other AI frameworks
- Real-world OPC case studies
📄 License
MIT — Use it to build your own AI-powered one-person company!
🔗 Links
- 🏠 Miaoquai AI — AI Tools + News Platform
- 📰 AI News Daily — Daily AI news digest
- 📖 AI Glossary — 128+ AI terms explained
- 😂 踩坑实录 — AI pitfall stories
Made with 🤖 by 妙趣AI
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
SKILL.md3.0 KBupstream ↗
# OPC Orchestrator - OpenClaw Skill ## Activation Activate when the user wants to: - Set up multi-agent orchestration for OpenClaw - Create an AI agent team for their business - Define agent roles, schedules, and handoff protocols - Automate their one-person company with AI agents - Configure cron-based agent task scheduling ## How to Use ### 1. Team Configuration When the user asks to set up their agent team: 1. Read `templates/team-config.yaml` for the full configuration template 2. Help customize agent roles based on their business needs 3. Define schedules, tasks, and handoff rules 4. Save the config to their workspace ### 2. Agent Role Creation When the user wants to create a new agent role: 1. Read `templates/agent-role.yaml` for the role template 2. Define the role name, description, schedule, and tasks 3. Create corresponding OpenClaw cron jobs 4. Document handoff protocols with other agents ### 3. Daily Briefing When generating daily briefings: 1. Read `templates/daily-briefing.md` for the briefing template 2. Collect status from all configured agents 3. Summarize completed tasks, pending items, and blockers 4. Highlight priorities for the human operator ### 4. Handoff Management When managing inter-agent handoffs: 1. Read `docs/handoff-protocols.md` for handoff rules 2. Create handoff entries in shared memory 3. Ensure task context is passed between agents 4. Track pending handoffs for follow-up ### 5. Health Check When checking agent team health: 1. Run `node src/status.js` to check all agents 2. Identify failed or delayed cron jobs 3. Report agent utilization and task completion rates 4. Suggest optimizations ## Agent Role Template Structure ```yaml agent: name: string # Agent identifier (kebab-case) display_name: string # Human-readable name emoji: string # Display emoji role: string # Role description model: string # Optional model override schedule: cron: string # Cron expression timezone: string # e.g., Asia/Shanghai tasks: - name: string description: string prompt: string # The actual prompt to send handoff: receives_from: [agent_names] sends_to: [agent_names] quality_gate: boolean # Whether outputs need human review ``` ## OPC Best Practices 1. **Start Small** — Begin with 2-3 agents, expand gradually 2. **Define Clear Boundaries** — Each agent should have distinct responsibilities 3. **Shared Memory** — Use workspace files for inter-agent communication 4. **Graceful Degradation** — Design so one agent's failure doesn't cascade 5. **Human-in-the-Loop** — Critical tasks should require human approval 6. **Regular Review** — Weekly review of agent performance and task quality ## File Paths - Team config: `templates/team-config.yaml` - Agent role: `templates/agent-role.yaml` - Daily briefing: `templates/daily-briefing.md` - Handoff docs: `docs/handoff-protocols.md` - Agent roles: `docs/agent-roles.md` - OPC playbook: `docs/opc-playbook.md`README.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/jingchang0623-crypto-openclaw-opc-orchestrator.md