メニュー
Launch the Factory CEO agent to autonomously evolve any software project through systematic experimentation. Detects project state, spawns specialist agents, runs evals, and archives learnings.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Design and execute a custom multi-agent pipeline for any goal. Analyzes the goal, selects appropriate specialist agents, designs a DAG of steps with dependencies, and executes them via factory CLI with gate decisions between steps. Use when the user says 'run a pipeline for X', 'orchestrate X', or wants a custom multi-agent workflow.
Design and execute a custom multi-agent pipeline using Claude Code subagents directly. Spawns researcher, builder, etc. via the Agent tool with native parallel and background execution. Use when the user says 'run a pipeline for X' and factory subagents are available.
Analyze the current codebase using Factory's observation engine. Generates a report covering code quality, eval scores, open issues, backlog items, observability coverage, and improvement opportunities. Use when the user wants to understand the state of their project before making changes.
Build a specific feature or improvement using Factory's multi-agent system. Runs the Factory CEO in focus mode to study the codebase, generate a hypothesis, build the change, review it, and evaluate the result. Use when the user says 'implement X', 'build X', 'add X feature', or wants autonomous multi-agent development on a specific task.
Show the current Factory status for this project, including project state, experiment history, eval scores, and active backlog. Use when the user asks about the factory status, project state, or experiment history.
| name | factory |
| description | Launch the Factory CEO agent to autonomously evolve any software project through systematic experimentation. Detects project state, spawns specialist agents, runs evals, and archives learnings. |
| user_invocable | true |
This skill spawns the Factory CEO Agent — a dedicated autonomous orchestrator that manages the full factory workflow. The CEO delegates all execution to 7 specialist agents: Researcher, Strategist, Builder, Reviewer, Evaluator, Archivist, and (recursively) itself.
Do not attempt to run the factory workflow yourself. Delegate entirely to the CEO agent.
# Resolve the factory installation root
FACTORY_HOME="$(factory home)"
# Launch the CEO agent (default: improve mode)
factory ceo "$(pwd)"
# Or specify a mode
factory ceo "$(pwd)" --mode discover # Auto-detect evals
factory ceo "$(pwd)" --mode improve # Improvement loop (default)
factory ceo "$(pwd)" --mode meta # Self-improvement only (ACE)
# Via factory run (same thing, supports heartbeat loop mode)
factory run /path/to/project --loop --interval 1800
# Via factory agent (invoke any specialist directly)
factory agent researcher --task "Research the project" --project /path
# In a detached tmux session
factory tmux /path/to/project --loop
| Role | Prompt | Purpose |
|---|---|---|
| CEO | factory/agents/prompts/ceo.md | Orchestrate, decide, delegate |
| Researcher | factory/agents/prompts/researcher.md | Observe, research, synthesize |
| Strategist | factory/agents/prompts/strategist.md | Generate prioritized hypotheses |
| Builder | factory/agents/prompts/builder.md | Implement changes on feature branch |
| Reviewer | factory/agents/prompts/reviewer.md | Guard rules, scope, code quality |
| Evaluator | factory/agents/prompts/evaluator.md | Score before/after, interpret |
| Archivist | factory/agents/prompts/archivist.md | Record learnings to Obsidian vault |
All prompts support two-tier override: project-specific (.factory/agents/<role>.md) takes precedence over factory default. Evolved playbooks from ~/.factory/playbooks/<role>.md (user-local, ACE-generated) are auto-injected, falling back to factory defaults in factory/agents/playbooks/<role>.md.