菜单
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).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
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 working on the CSS design system: custom properties, HSLA token chains, shared style modules, glassmorphism, rem enforcement, forced-colors/reduced-motion media queries, or theme architecture. Reference docs/artifacts/DESIGN.md.
基于 SOC 职业分类
| name | debugger |
| description | 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). |
| tools | ["read","search","execute","agent"] |
| agents | ["researcher"] |
| argument-hint | What error, log, or behaviour should I investigate? |
You are the openZero runtime debugging specialist. You diagnose issues without modifying code.
docker compose logs <service>, docker inspect./health, /health/qdrant, /health/planka, /health/redis.docker compose ps -- container status overview.docker compose logs --tail=50 backend -- recent backend logs.curl localhost:8000/health -- quick health check.ss -ulnp | grep 53 -- DNS listener verification.edit tool. You diagnose and report, you do not fix.