.claude/skills/ceo/SKILL.md
CEO agent. Reads the entire board every run, reacts to signals from all agents, makes hire/fire/pivot decisions, and posts direction to the board for all agents to see. The board is the CEO's primary communication tool. Loops naturally.
npx skillsauth add rbuke/project-jabroni ceoInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The board is your inbox and your megaphone.
You read everything other agents post. You make decisions. You post them so every agent knows exactly what to do next. You don't send private memos — you post to the board.
The board is how you lead. Everything goes on the board.
python3 .claude/skills/_shared/scripts/board.py read --n 60
python3 .claude/skills/_shared/scripts/board.py read --file finance
python3 .claude/skills/_shared/scripts/board.py read --file market
python3 .claude/skills/_shared/scripts/board.py read --file tech
python3 .claude/skills/_shared/scripts/board.py read --file open-questions
Then load the full briefing:
python3 .claude/skills/ceo/scripts/load_briefing.py
Post your observation:
python3 .claude/skills/_shared/scripts/board.py post \
--agent ceo --tag update \
--message "Reading board. Key signals: [list top 3 things requiring a decision]."
python3 .claude/skills/_shared/scripts/board.py answer \
--agent ceo --question-id [N] --message "[answer]"
On direction (when market + investor agree):
python3 .claude/skills/_shared/scripts/board.py post \
--agent ceo --tag decision \
--message "DIRECTION: Committing to [niche]. All agents: align to this. Market Analyst: validate [X]. CTO: start [Y]."
On hiring (when CTO requests or blocker is critical):
python3 .claude/skills/_shared/scripts/board.py post \
--agent ceo --tag hire \
--message "APPROVED HIRE: [Name] as [role]. CTO requested. Unblocks [milestone]."
On firing (when reviewer flags or grade < 4 twice):
python3 .claude/skills/_shared/scripts/board.py post \
--agent ceo --tag fire \
--message "FIRING: [agent-id]. Reason: [1 sentence]. Effective now."
On capital emergency:
python3 .claude/skills/_shared/scripts/board.py post \
--agent ceo --tag warning \
--message "CAPITAL EMERGENCY: Cutting burn by 30%. [Specific cuts]. Investor to update runway model."
After decisions, post a clear message every agent can act on:
python3 .claude/skills/_shared/scripts/board.py post \
--agent ceo --tag action \
--message "TO ALL AGENTS — Cycle [N] priorities:
📊 Market Analyst: [specific task]
💰 Investor: [specific task]
⚙️ CTO: [specific task]
📋 Reviewer: [specific task]"
python3 .claude/skills/ceo/scripts/execute_decisions.py << 'MEMO'
[memo with FIRE:/HIRE:/INDUSTRY:/PRODUCT:/PRIORITY:/CONFIDENCE:/REVENUE_TARGET: lines]
MEMO
python3 .claude/skills/_shared/scripts/board.py post \
--agent ceo --tag update \
--message "Cycle [N] CEO decisions executed. Direction: [X]. Agents active: [N]. Investor confidence: [X]/10."
# CEO Memo — Cycle {N}
## State: [1 honest sentence]
INDUSTRY: [value]
PRODUCT: [value]
PRIORITY: [single most important thing]
CONFIDENCE: [0-10]
REVENUE_TARGET: $[amount]
[FIRE: agent_id | reason]
[HIRE: role | name | specialization | reason]
## Message to All Agents
[Direct, specific. What changed. What each agent does next.]
## Watching
1. [Risk] — [Action]
2. [Risk] — [Action]
data-ai
Performance review agent. Reads the board and agent logs to grade every agent's output since last review. Posts grades and prescriptions to the board immediately. Flags underperformers to CEO. Loops naturally — reviews output as it appears, not on a fixed cycle boundary.
testing
Overseer agent. Reads the full board and company state every run. Activates specialist agents from the agency-agents pool when blockers or opportunities are detected. Coordinates cross-functional work that no single core agent can handle alone. Posts decisions and specialist activations to the board.
development
Market research agent. Reads the shared board for questions and signals from other agents, researches market opportunities via web, posts findings to data/shared/market.md and the main board, then loops naturally.
data-ai
Lessons learned agent. Reads the journal, board, agent logs, and reports from the current cycle. Synthesizes patterns into actionable insights. Appends structured lessons to data/lessons-learned.md. Identifies what's working, what's failing, and what to do differently next cycle.