メニュー
Scaffold a new openZero native crew entry in agent/crews.yaml with characters, keywords, scheduling, and Planka persistence.
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
| name | new-crew |
| description | Scaffold a new openZero native crew entry in agent/crews.yaml with characters, keywords, scheduling, and Planka persistence. |
Creates a new crew definition in agent/crews.yaml following openZero conventions.
Ask for:
basic, business, education, or private./day, /week, /month, /quarter, /year, or fixed cron.Create crew entry in agent/crews.yaml using the template in references/crew-template.yaml. Generate:
id: lowercase, underscores (e.g. fitness_tracker).name: use Semantic Priming -- evocative professional title, not generic.description: one clear sentence.keywords: 8-15 routing trigger words covering synonyms and related concepts.characters: 2-3 archetypes with hyper-specific role names.instructions: detailed multi-line prompt with Planka ACTION tag guidance.Add Planka persistence to instructions if the crew produces actionable output:
When you produce actionable items, emit:
[ACTION: CREATE_TASK | BOARD: <crew board name> | LIST: <appropriate list>]
Cross-reference agent/agent-rules.md to ensure the new crew aligns with Z's behavioral guidelines.
Verify the YAML is valid:
python3 -c "import yaml; yaml.safe_load(open('agent/crews.yaml'))"
Use when working on Z's persona/identity system, crew YAML definitions, agent-rules.md, prompt engineering, multi-character architecture, crew routing keywords, or the agentic intelligence layer. Expert in Semantic Priming and LLM behaviour shaping.
Use when working on FastAPI endpoints, Python services, scheduled tasks, LLM routing, message bus, memory, voice/TTS, notifier, email rules, or any external API wrapper (Calendar, Gmail, SearXNG, Qdrant, weather). Covers the entire src/backend/ codebase.
Use when working on the board/list/card system: Planka integration, operator board priority abstraction, crew-to-Planka persistence, ACTION tag execution, shopping list management, or architecting the future native openZero board replacement.
Use when working on commercialisation strategy: BSL-1.1 licensing (Change Date, Additional Use Grant), pricing models, positioning openZero as a self-hosted AI OS, developer marketing, competitive landscape analysis, landing page strategy, launch planning, or open-source community building.
Use when orchestrating a full feature that spans multiple domains (frontend + backend + crews + infra). Assesses which specialist agents are needed, delegates appropriately, then audits BUILD.md and artifacts for staleness. User-invocable orchestrator.
Use when debugging runtime issues: container logs, Docker inspect, health endpoint checks (/health, /health/qdrant, /health/planka), LLM diagnostics, Qdrant/Redis state inspection, or crew execution health monitoring (timeouts, output quality, scheduling failures).