Skip to content

LeoYeAI/agent-master-skills / skills/agi-farm

agi-farm

Flagged

Interactive setup wizard that creates a fully working multi-agent AI team on OpenClaw. One command bootstraps agents, SOUL.md personas, comms infrastructure (inboxes/outboxes/broadcast), cron jobs, auto-dispatcher (HITL + rate-limit backoff + dependency checking), and a portable GitHub bundle โ€” all customized to team name, size (3/5/11 agents), domain, and frameworks (autogen/crewai/langgraph). Includes a React + SSE live ops dashboard with file-watcher (~350ms push latency) and persistent macOS LaunchAgent. Model-selection guidance built in. Commands: setup | status | rebuild | export | dashboard | dispatch

FileKindSize
README.mdmarkdown8.8 KB
SKILL.mdskill md17.5 KB
_meta.jsonconfig275 B
auto-dispatch.pyscript18.3 KB
dashboard-react/README.mdmarkdown1.1 KB
dashboard-react/eslint.config.jsscript758 B
dashboard-react/index.htmlother474 B
dashboard-react/package-lock.jsonmanifest113.1 KB
dashboard-react/package.jsonmanifest637 B
dashboard-react/public/vite.svgother1.5 KB
dashboard-react/src/App.cssother606 B
dashboard-react/src/App.jsxother3.2 KB
dashboard-react/src/assets/react.svgother4.0 KB
dashboard-react/src/components/AgentMiniCard.jsxother1.2 KB
dashboard-react/src/components/Header.jsxother3.4 KB
dashboard-react/src/components/LastUpdated.jsxother362 B
dashboard-react/src/components/Nav.jsxother1.5 KB
dashboard-react/src/components/tabs/Agents.jsxother4.0 KB
dashboard-react/src/components/tabs/Alerts.jsxother5.3 KB
dashboard-react/src/components/tabs/Broadcast.jsxother1.7 KB
dashboard-react/src/components/tabs/Budget.jsxother5.3 KB
dashboard-react/src/components/tabs/Comms.jsxother4.4 KB
dashboard-react/src/components/tabs/Crons.jsxother9.1 KB
dashboard-react/src/components/tabs/HITL.jsxother6.2 KB
dashboard-react/src/components/tabs/Knowledge.jsxother4.7 KB
dashboard-react/src/components/tabs/OKRs.jsxother2.6 KB
dashboard-react/src/components/tabs/Overview.jsxother8.9 KB
dashboard-react/src/components/tabs/Projects.jsxother40.9 KB
dashboard-react/src/components/tabs/RD.jsxother5.5 KB
dashboard-react/src/components/tabs/Tasks.jsxother9.7 KB
dashboard-react/src/components/tabs/Velocity.jsxother5.0 KB
dashboard-react/src/hooks/useDashboard.jsscript2.5 KB
dashboard-react/src/index.cssother4.3 KB
dashboard-react/src/main.jsxother229 B
dashboard-react/vite.config.jsscript332 B
dashboard.htmlother57.0 KB
dashboard.pyscript44.5 KB
generate.pyscript11.6 KB
references/dashboard.mdmarkdown1.9 KB
scripts/auto-dispatch.pyscript19.1 KB
scripts/register-crons.pyscript7.2 KB
# ๐Ÿฆ… AGI Farm

> One wizard. Full multi-agent AI team. Live in minutes.

**AGI Farm** is an [OpenClaw](https://docs.openclaw.ai) skill that bootstraps a fully operational multi-agent AI system โ€” agents, workspaces, cron jobs, comms infrastructure, live ops dashboard, and a portable GitHub bundle โ€” all from a single interactive wizard.

---

## โœจ What It Does

- ๐Ÿง™ **Interactive setup wizard** โ€” answers 6 questions, generates everything
- ๐Ÿค– **Multi-agent team** โ€” 3, 5, or 11 pre-wired specialist agents
- ๐Ÿ“ก **Live ops dashboard** โ€” React + SSE, ~350ms push latency, persistent LaunchAgent
- ๐Ÿ”„ **Auto-dispatcher** โ€” cron-driven task delegation with HITL, rate-limit backoff, dependency checking
- ๐Ÿ“ฆ **Portable bundle** โ€” export your team to GitHub with one command
- ๐Ÿงฉ **Framework support** โ€” autogen, crewai, langgraph out of the box

---

## ๐Ÿ—บ๏ธ Architecture

### System Overview

```mermaid
graph TB
    User["๐Ÿ‘ค User"] -->|"/agi-farm setup"| Cooper["๐Ÿฆ… Cooper\nOrchestrator"]

    subgraph Workspace ["~/.openclaw/workspace/"]
        Cooper --> TASKS["๐Ÿ“‹ TASKS.json"]
        Cooper --> COMMS["๐Ÿ“ฌ comms/\ninboxes & outboxes"]
        Cooper --> BROADCAST["๐Ÿ“ข broadcast.md"]
    end

    subgraph Agents ["Specialist Agents"]
        Sage["๐Ÿ”ฎ Sage\nSolution Architect"]
        Forge["โš’๏ธ Forge\nImpl. Engineer"]
        Pixel["๐Ÿ› Pixel\nDebugger"]
        Vista["๐Ÿ”ญ Vista\nBiz Analyst"]
        Cipher["๐Ÿ”Š Cipher\nKnowledge Curator"]
        Vigil["๐Ÿ›ก๏ธ Vigil\nQA Engineer"]
        Anchor["โš“ Anchor\nContent Specialist"]
        Lens["๐Ÿ“ก Lens\nMultimodal"]
    end

    COMMS -->|"inbox task"| Sage & Forge & Pixel & Vista & Cipher & Vigil & Anchor & Lens
    Sage & Forge & Pixel & Vista & Cipher & Vigil & Anchor & Lens -->|"outbox result"| Cooper

    subgraph Infra ["Infrastructure"]
        Dispatcher["๐Ÿ”„ auto-dispatch.py\n(cron every 1 min)"]
        Dashboard["๐Ÿ“Š dashboard.py\n(SSE server :8080)"]
        CronJobs["โฐ OpenClaw Crons\n(heartbeat, sweep, dispatch)"]
    end

    Dispatcher -->|"trigger agent sessions"| Agents
    Dashboard -->|"file-watch"| Workspace
```

### Setup Wizard Flow

```mermaid
flowchart LR
    S1["Step 1\nTeam Name"] --> S2["Step 2\nOrchestrator Name"]
    S2 --> S3["Step 3\nTeam Size\n3 / 5 / 11"]
    S3 --> S35["Step 3.5\nDomain"]
    S35 --> S36["Step 3.6\nCustom Agents?"]
    S36 --> S4["Step 4\nFrameworks"]
    S4 --> S5["Step 5\nGitHub?"]
    S5 --> S6["Step 6\nConfirm"]
    S6 --> S7["Step 7\nWrite team.json\nassign models"]
    S7 --> S8["Step 8\nGenerate workspace\nfiles via generate.py"]
    S8 --> S9["Step 9\nCreate OpenClaw\nagents"]
    S9 --> S10["Step 10\nRegister cron jobs"]
    S10 --> S11["Step 11\nInstall frameworks"]
    S11 --> S12["Step 12\nGitHub push"]
    S12 --> S13["Step 13\nCommit workspace"]
    S13 --> S14["Step 14\nInit registries\nhealth check"]
    S14 --> DONE["โœ… Team is live!"]
```

### Auto-Dispatcher Logic

```mermaid
flowchart TD
    Start["โฐ Cron triggers\nevery 1 min"] --> LoadState["Load TASKS.json\nDISPATCHER_STATE.json"]
    LoadState --> HITL["HITL scan\nneeds_human_decision?"]
    HITL -->|"yes"| Notify["๐Ÿšจ Notify orchestrator\n2h cooldown"]
    HITL -->|"no"| Stale["Stale reset\nin_progress >90 min?"]
    Notify --> Stale
    Stale -->|"yes"| Reset["Reset to pending"]
    Stale --> Pending["Filter pending tasks\nby eligible agents"]
    Reset --> Pending
    Pending --> Check["Per agent checks:\nnot orchestrator\nnot on cooldown\nnot rate-limited\nnot blocked\ndeps satisfied\nhas inbox messages"]
    Check -->|"eligible"| Trigger["๐Ÿš€ Trigger agent session\nparallel fire-and-forget"]
    Check -->|"skip"| Log["๐Ÿ“ Log skip reason"]
    Trigger --> RateCheck["Detect rate-limit\nin early output?"]
    RateCheck -->|"yes"| Backoff["Set 10-min backoff"]
    RateCheck -->|"no"| UpdateState["Update DISPATCHER_STATE.json\ncooldown timer"]
    Backoff --> UpdateState
    Log --> UpdateState
    UpdateState --> Done["Done โ€” next run in 1 min"]
```

### Dashboard Architecture

```mermaid
graph LR
    subgraph Backend ["dashboard.py (Python)"]
        Watcher["WorkspaceWatcher\nwatchdog 250ms debounce"]
        Cache["SlowDataCache\nagents + crons 30s refresh"]
        SSE["SSE Broadcaster\n/api/stream"]
    end

    subgraph Frontend ["dashboard-react (Vite + React 18)"]
        Hook["useDashboard.js\nSSE + auto-reconnect"]
        Tabs["Overview ยท Agents ยท Tasks\nVelocity ยท Budget ยท OKRs\nR&D ยท Broadcast"]
    end

    subgraph Files ["Workspace Files (watched)"]
        TJ["TASKS.json"]
        AS["AGENT_STATUS.json"]
        BU["BUDGET.json"]
        VE["VELOCITY.json"]
        OK["OKRs.json"]
        BC["comms/broadcast.md"]
    end

    Files -->|"fs events"| Watcher
    Watcher --> SSE
    Cache --> SSE
    SSE -->|"push ~350ms"| Hook
    Hook --> Tabs
```

### Agent Communication Protocol

```mermaid
sequenceDiagram
    participant U as ๐Ÿ‘ค User
    participant C as ๐Ÿฆ… Cooper
    participant I as ๐Ÿ“ฌ comms/inboxes/
    participant A as ๐Ÿค– Specialist Agent
    participant O as ๐Ÿ“ค comms/outboxes/
    participant T as ๐Ÿ“‹ TASKS.json

    U->>C: Request
    C->>T: Create task (status: pending)
    C->>I: Write task to agent inbox

    loop Auto-Dispatcher (every 1 min)
        A->>I: Reads inbox
        A->>A: Executes task
        A->>O: Writes result to outbox
        A->>I: Marks task [DONE]
    end

    C->>O: Reads agent outbox
    C->>T: Update task (status: complete)
    C->>U: Synthesized result
```

---

## ๐Ÿš€ Quick Start

```bash
# Install via ClawHub
clawhub install agi-farm

# Run the setup wizard
/agi-farm setup
```

Answer the questions. Your team will be live in ~2 minutes.

---

## ๐Ÿ“ฆ Commands

| Command | What it does |
|---------|-------------|
| `/agi-farm setup` | Full wizard โ€” agents, workspace, crons, bundle, GitHub |
| `/agi-farm status` | Team health: agents, tasks, cron status |
| `/agi-farm rebuild` | Regenerate workspace from existing bundle (preserves edits) |
| `/agi-farm export` | Push bundle to GitHub |
| `/agi-farm dashboard` | Launch live ops room (React + SSE, :8080) |
| `/agi-farm dispatch` | Run auto-dispatcher manually |

---

## ๐Ÿค– Team Presets

### 3-agent (Minimal)
```
๐Ÿฆ… Orchestrator  โ”€โ”€โ–บ  ๐Ÿ”ฎ Researcher  โ”€โ”€โ–บ  โš’๏ธ Builder
```

### 5-agent (Standard)
```
๐Ÿฆ… Orchestrator  โ”€โ”€โ–บ  ๐Ÿ”ฎ Researcher  โ”€โ”€โ–บ  โš’๏ธ Builder
                 โ”€โ”€โ–บ  ๐Ÿ›ก๏ธ QA          โ”€โ”€โ–บ  โš“ Content
```

### 11-agent (Full Stack โ€” Recommended)
```
๐Ÿฆ… Cooper (Orchestrator)
โ”œโ”€โ”€ ๐Ÿ”ฎ Sage     Solution Architect
โ”œโ”€โ”€ โš’๏ธ Forge    Implementation Engineer
โ”œโ”€โ”€ ๐Ÿ› Pixel    Debugger
โ”œโ”€โ”€ ๐Ÿ”ญ Vista    Business Analyst
โ”œโ”€โ”€ ๐Ÿ”Š Cipher   Knowledge Curator
โ”œโ”€โ”€ ๐Ÿ›ก๏ธ Vigil    QA Engineer
โ”œโ”€โ”€ โš“ Anchor   Content Specialist
โ”œโ”€โ”€ ๐Ÿ“ก Lens     Multimodal Specialist
โ”œโ”€โ”€ ๐Ÿ”„ Evolve   Process Improvement Lead
โ””โ”€โ”€ ๐Ÿงช Nova     R&D Lead
```

---

## ๐Ÿง  Model Selection Guide

| Role | Recommended tier | Why |
|------|-----------------|-----|
| Orchestrator | High (`sonnet`, `opus`) | Delegation judgment, broad reasoning |
| Architect / Researcher | High | Deep analysis, design decisions |
| Implementation Engineer | Mid (`glm-5`, `sonnet`) | Fast code gen, cost-efficiency |
| Debugger | High (`opus`) | Root-cause analysis |
| Business Analyst / Knowledge | Mid-high (`gemini-2.0-pro-exp`) | Long-context research |
| QA Engineer | Fast (`glm-4.7-flash`) | High-volume pattern checks |
| Content / Multimodal | Multimodal (`gemini-2.0-pro-exp`) | Vision + rich generation |
| R&D / Process Improvement | High | Creative + structured experiments |

---

## ๐Ÿ›Ÿ Troubleshooting

| Symptom | Fix |
|---------|-----|
| `generate.py` fails: `ModuleNotFoundError` | `pip3 install jinja2` |
| `openclaw` not found in cron | Set `OPENCLAW_BIN=/path/to/openclaw` env var |
| Dashboard shows stale data | `launchctl stop ai.coopercorp.dashboard && launchctl start ai.coopercorp.dashboard` |
| Agent stuck >30 min | Check `comms/broadcast.md` for `[BLOCKED]` tags |
| Rate-limit backoff too aggressive | Edit `RATE_LIMIT_BACKOFF_MIN` in `scripts/auto-dispatch.py` |
| `gh repo create` fails | Run `gh auth login` first |

---

## ๐Ÿ“ Structure

```
agi-farm/
โ”œโ”€โ”€ SKILL.md                     OpenClaw skill entry point
โ”œโ”€โ”€ generate.py                  Workspace file generator (Jinja2)
โ”œโ”€โ”€ scripts/
โ”‚   โ”œโ”€โ”€ auto-dispatch.py         Cron-driven task dispatcher
โ”‚   โ””โ”€โ”€ register-crons.py        Cron job registration
โ”œโ”€โ”€ templates/                   30 templates (SOUL.md, CLAUDE.md, TASKS.json, ...)
โ”œโ”€โ”€ references/
โ”‚   โ””โ”€โ”€ dashboard.md             Dashboard reference docs
โ””โ”€โ”€ dashboard-react/             Vite + React 18 frontend (dist/ served by dashboard.py)
```

---

## ๐Ÿ“„ License

MIT โ€” built for [OpenClaw](https://docs.openclaw.ai) ยท published on [ClawHub](https://clawhub.com)
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path โ€” even casually (like "the xlsx in my downloads") โ€” and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall