become-ceo
Your AI executive team on Discord. 7 specialists (engineering, finance, marketing, devops, legal, management, chief of staff) each with its own model and personality. Use when setting up, configuring, scaling, or troubleshooting a multi-bot Discord workspace where you are the CEO and AI agents are your team.
Best use case
become-ceo is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Your AI executive team on Discord. 7 specialists (engineering, finance, marketing, devops, legal, management, chief of staff) each with its own model and personality. Use when setting up, configuring, scaling, or troubleshooting a multi-bot Discord workspace where you are the CEO and AI agents are your team.
Teams using become-ceo should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/become-ceo/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How become-ceo Compares
| Feature / Agent | become-ceo | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Your AI executive team on Discord. 7 specialists (engineering, finance, marketing, devops, legal, management, chief of staff) each with its own model and personality. Use when setting up, configuring, scaling, or troubleshooting a multi-bot Discord workspace where you are the CEO and AI agents are your team.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Become CEO — Your AI Executive Team
7 AI specialists on Discord. You give the orders, they do the work.
## Quick Start
**One-click setup** (recommended for new servers):
```bash
bash <(curl -fsSL https://raw.githubusercontent.com/wanikua/become-ceo/main/setup.sh)
```
The v2.3 setup script auto-detects your OS/architecture/container environment, validates network connectivity, installs all dependencies, and runs an interactive configuration wizard for LLM provider, API key, model selection, Discord bot tokens, Notion integration, and GitHub authentication. Features: `--upgrade` to update an existing installation, `--uninstall` for clean removal, `--reset` to factory-reset config, `--skip-optional` for minimal installs (no GitHub CLI/Chromium), Docker/LXC auto-detection, auto-backup before config changes, post-install health check, and auto-start with smoke test. Colors auto-disable when piped/redirected (respects `NO_COLOR`). Use `--check` to verify your environment, `--dry-run` to preview, or `--version` to check the version. Supports Ubuntu 22.04+, Debian 12+, Amazon Linux 2023, Fedora 38+ on amd64/arm64.
**Manual / existing OpenClaw install:**
1. Install this skill: `clawdhub install become-ceo`
2. Copy `references/openclaw-template.json` to `~/.openclaw/openclaw.json`
3. Fill in your LLM API key, model IDs, and Discord bot tokens
4. Start: `systemctl --user start openclaw-gateway`
For full details, see the [setup guide on GitHub](https://github.com/wanikua/become-ceo).
## Your Team
- **Chief of Staff** (main) — routes your orders (fast model)
- **Engineering** — code, architecture, system design (strong model)
- **Finance** — budgets, cost control (strong model)
- **Marketing** — content, branding, social (fast model)
- **DevOps** — servers, CI/CD, infrastructure (fast model)
- **Management** — projects, coordination (fast model)
- **Legal** — compliance, contracts (fast model)
## Config
See [references/openclaw-template.json](references/openclaw-template.json) for the full config template.
- Each Discord account **MUST** have `"groupPolicy": "open"` — does NOT inherit from global
- `identity.theme` sets each team member's personality
- `bindings` maps each agent to its Discord bot
- Replace `$LLM_PROVIDER`, `$MODEL_FAST`, `$MODEL_STRONG` with your chosen provider and models
## Workspace Files
| File | What it does |
|---|---|
| `QUICKSTART.md` | ⭐ One-page cheat sheet — commands, patterns, troubleshooting |
| `SOUL.md` | How your team behaves (5 scenario templates) |
| `IDENTITY.md` | Org chart and model tiers (5 org structure templates) |
| `USER.md` | About you, the CEO (5 persona templates) |
| `AGENTS.md` | Group chat rules, memory protocol (5 workflow templates) |
| `TOOLS.md` | Equipment manifest — services, servers (5 stack templates) |
| `HEARTBEAT.md` | Periodic monitoring checks (5 monitoring templates) |
## Sandbox
Off by default. To enable read-only sandboxed execution:
```json
"sandbox": {
"mode": "all",
"workspaceAccess": "ro",
"docker": { "network": "none" }
}
```
Agents run in isolated containers with read-only workspace access and no network. The gateway handles all API authentication externally. See [OpenClaw docs](https://github.com/wanikua/become-ceo) for advanced sandbox options.
## Extending with ClawdHub Skills
Install additional skills from the ClawdHub marketplace:
```bash
# Core skills
clawdhub install email-daily-summary # Email triage and daily digests
clawdhub install gcalcli-calendar # Google Calendar integration
clawdhub install github-trending-cn # GitHub trending repos digest
clawdhub install hacker-news # Tech news monitoring
clawdhub install docker-essentials # Container management
clawdhub install automation-workflows # Pre-built workflow templates
# Extended skills
clawdhub install system-resource-monitor # Server health monitoring
clawdhub install rss-feeds # Custom news aggregation
clawdhub install slack-bridge # Multi-platform messaging
clawdhub install ai-image-gen # Visual content generation
clawdhub install screenshot-diff # Visual change detection
```
All installed skills are available to every agent immediately after restart. Combine skills for compound value — see `references/skill-combinations.md` for 8 multi-skill recipes.
## Skill Governance
- **Pin production-critical skills** to specific versions: `clawdhub install email-daily-summary@1.2.0`
- **Auto-update low-risk skills** (weather, news): `clawdhub update weather`
- **Audit regularly**: `clawdhub outdated` shows available updates
- **Review before installing**: always check a new skill's SKILL.md for security red flags
- **Credential isolation**: never put API keys in SKILL.md files — use environment variables via sandbox config
- Set up a weekly skill audit cron on Chief of Staff to maintain your skill library
## Troubleshooting
- **@everyone doesn't work** — enable Message Content Intent + Server Members Intent in Discord Developer Portal
- **Messages silently dropped** — set `"groupPolicy": "open"` on each Discord account entry
## Growing Your Team
1. Add to `agents.list` with unique `id` and `identity.theme`
2. Create Discord bot, enable intents
3. Add to `channels.discord.accounts` with `"groupPolicy": "open"`
4. Add binding, invite bot, restart gatewayRelated Skills
weather
Get current weather and forecasts (no API key required).
quadrants
Manage Quadrants tasks and projects via natural language. Use when the user wants to create, view, complete, or organize tasks on the Eisenhower Matrix. Supports listing projects, adding tasks (single or bulk), viewing priority tasks, completing tasks, and getting project overviews. Triggers on mentions of "quadrants", "tasks", "to-do", "eisenhower", "priority matrix", or task management requests.
OpenViking Skill
OpenViking 上下文数据库集成 — 给 AI 朝廷加上长期记忆和知识库。
notion
Notion API for creating and managing pages, databases, and blocks.
Hacker News
Search and browse Hacker News with API access to stories, comments, users, and hiring threads.
github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
browser-use
Automates browser interactions for social media management across Instagram, LinkedIn, and X. Handles posting, DMs, connection requests, lead scraping, and monitoring. Use when the user needs to navigate, interact with, or extract data from approved websites.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.