Edict Multi Agent Orchestration
Install and run the Edict (三省六部) twelve-agent OpenClaw pipeline with mandatory review gates, kanban visibility, and audit trails for serious multi-agent products.
Overview
Edict Multi-Agent Orchestration is an agent skill most often used in Build (also Ship and Operate) that installs the twelve-agent Edict/OpenClaw pipeline with veto review gates, kanban dashboard, and audit trails.
Install
npx skills add https://github.com/aradotso/trending-skills --skill edict-multi-agent-orchestrationWhat is this skill?
- Twelve specialized agents in a Tang Dynasty-inspired checks-and-balances pipeline
- Mandatory Menxia (门下省) review/veto gate before parallel Six Ministries execution
- Real-time React kanban dashboard and full audit trails on OpenClaw
- Per-agent LLM configuration across Crown Prince triage through memorial archival
- Documented flow: taizi → zhongshu → menxia → shangshu → ministries → memorial
- 12 specialized AI agents in the Edict pipeline
- Mandatory Menxia (门下省) review/veto quality gate before execution
Adoption & trust: 1.3k installs on skills.sh; 31 GitHub stars; 0/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your multi-agent setup lacks enforced review, parallel role separation, and a visible workflow board so tasks slip through without auditability.
Who is it for?
Builders standardizing on OpenClaw who need governance-style agent pipelines with veto review and dashboard visibility for non-trivial automation products.
Skip if: Quick single-agent coding tasks, teams unwilling to run OpenClaw infrastructure, or projects that only need a one-shot CrewAI script without operational dashboards.
When should I use this skill?
User asks to set up Edict, configure 三省六部 agents, install Edict orchestration, use OpenClaw multi-agent dashboard, or deploy gated AI agent pipelines with kanban.
What do I get? / Deliverables
You configure Edict on OpenClaw with twelve routed agents, a mandatory Menxia review gate, live kanban tracking, and archived memorial outputs for each completed pipeline run.
- Configured Edict twelve-agent pipeline on OpenClaw
- Operational kanban dashboard view with audit trail access
- Documented agent role graph from triage through memorial archival
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Multi-agent orchestration is canonical build/agent-tooling work when you are wiring agent roles, gates, and dashboards into the product or dev environment. Agent-tooling subphase is where OpenClaw-backed pipelines, per-agent LLM config, and kanban ops get integrated—not a one-off chat prompt.
Where it fits
Install Edict on OpenClaw and map twelve agent roles with per-agent LLM settings before your app triggers automated pipelines.
Route release-check tasks through Menxia veto so shoddy agent output is sent back before ministry executors merge changes.
Use the React kanban board and memorial audit trail to see which agent stage failed during a production incident workflow.
How it compares
OpenClaw-native orchestration with a mandatory veto gate and kanban ops—richer governance than typical CrewAI/AutoGen crew scripts.
Common Questions / FAQ
Who is edict-multi-agent-orchestration for?
Solo and indie builders shipping agent-heavy workflows on OpenClaw who want structured roles, review gates, and a kanban view instead of ad-hoc multi-agent chats.
When should I use edict-multi-agent-orchestration?
Use it in Build/agent-tooling when standing up the pipeline, in Ship/review when enforcing pre-ship agent quality gates, and in Operate/monitoring when you rely on audit trails and board state to debug agent handoffs.
Is edict-multi-agent-orchestration safe to install?
It drives multi-agent execution with network and shell dependencies via OpenClaw; review the Security Audits panel on this page, lock down agent permissions, and sandbox LLM keys before production workloads.
SKILL.md
READMESKILL.md - Edict Multi Agent Orchestration
# Edict (三省六部) Multi-Agent Orchestration > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. Edict implements a 1400-year-old Tang Dynasty governance model as an AI multi-agent architecture. Twelve specialized agents form a checks-and-balances pipeline: Crown Prince (triage) → Zhongshu (planning) → Menxia (review/veto) → Shangshu (dispatch) → Six Ministries (parallel execution). Built on [OpenClaw](https://openclaw.ai), it provides a real-time React kanban dashboard, full audit trails, and per-agent LLM configuration. --- ## Architecture Overview ``` You (Emperor) → taizi (triage) → zhongshu (plan) → menxia (review/veto) → shangshu (dispatch) → [hubu|libu|bingbu|xingbu|gongbu|libu2] (execute) → memorial (result archived) ``` **Key differentiator vs CrewAI/AutoGen**: Menxia (门下省) is a mandatory quality gate — it can veto and force rework before tasks reach executors. --- ## Prerequisites - [OpenClaw](https://openclaw.ai) installed and running - Python 3.9+ - Node.js 18+ (for React dashboard build) - macOS or Linux --- ## Installation ### Quick Demo (Docker — no OpenClaw needed) ```bash # x86/amd64 (Ubuntu, WSL2) docker run --platform linux/amd64 -p 7891:7891 cft0808/sansheng-demo # Apple Silicon / ARM docker run -p 7891:7891 cft0808/sansheng-demo # Or with docker-compose (platform already set) docker compose up ``` Open http://localhost:7891 ### Full Installation ```bash git clone https://github.com/cft0808/edict.git cd edict chmod +x install.sh && ./install.sh ``` The install script automatically: - Creates all 12 agent workspaces (taizi, zhongshu, menxia, shangshu, hubu, libu, bingbu, xingbu, gongbu, libu2, zaochao, legacy-compat) - Writes SOUL.md role definitions to each agent workspace - Registers agents and permission matrix in `openclaw.json` - Symlinks shared data directories across all agent workspaces - Sets `sessions.visibility all` for inter-agent message routing - Syncs API keys across all agents - Builds React frontend - Initializes data directory and syncs official stats ### First-time API Key Setup ```bash # Configure API key on first agent openclaw agents add taizi # Then re-run install to propagate to all agents ./install.sh ``` --- ## Running the System ```bash # Terminal 1: Data refresh loop (keeps kanban data current) bash scripts/run_loop.sh # Terminal 2: Dashboard server python3 dashboard/server.py # Open dashboard open http://127.0.0.1:7891 ``` --- ## Key Commands ### OpenClaw Agent Management ```bash # List all registered agents openclaw agents list # Add/configure an agent openclaw agents add <agent-name> # Check agent status openclaw agents status # Restart gateway (required after config changes) openclaw gateway restart # Send a message/edict to the system openclaw send taizi "帮我分析一下竞争对手的产品策略" ``` ### Dashboard Server ```python # dashboard/server.py — serves on port 7891 # Built-in: React frontend + REST API + WebSocket updates python3 dashboard/server.py # Custom port PORT=8080 python3 dashboard/server.py ``` ### Data Scripts ```bash # Sync official (agent) statistics python3 scripts/sync_officials.py # Update kanban task states python3 scripts/kanban_update.py # Run news aggregation python3 scripts/fetch_news.py # Full refresh loop (runs all scripts in sequence) bash scripts/run_loop.sh ``` --- ## Configuration ### Agent Model Configuration (`openclaw.json`) ```json { "agents": { "taizi": {