菜单
OmniCore CLI usage via `bbot <command>` for starting kernel/supervisor, checking status, managing sessions, and updating config/secrets. Use when running or documenting OmniCore CLI commands or when CLI flags/behavior change.
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。
基于 SOC 职业分类
Create and maintain ExecPlans for complex features or significant refactors. Use when planning work that requires design + implementation steps, especially when the repo requires ExecPlans in docs/exec-plans and strict format per PLANS.md.
Complete project architecture and structure guide. Use when exploring the codebase, understanding project organization, finding files, or needing comprehensive architectural context. Triggers on architecture questions, directory navigation, or project overview needs.
OmniCore architecture and developer guide reference. Use when asked to explain, review, or update OmniCore design philosophy, kernel/adapters/event sourcing, sessions/root paths, compaction and summaries, heartbeat, supervisor or CLI behavior, or to maintain developer-guide.md.
Guide for creating effective skills. This skill should be used when you need to create a new skill (or update an existing skill) that extends capabilities with specialized knowledge, workflows, or tool integrations.
TypeScript code style and optimization guidelines. Use when writing TypeScript code (.ts, .tsx, .mts files), reviewing code quality, or implementing type-safe patterns. Triggers on TypeScript development, type safety questions, or code style discussions.
Unified LLM API library (@mariozechner/pi-ai) for TypeScript/JavaScript that abstracts provider differences across OpenAI, Anthropic, Google, Azure, Mistral, Groq, xAI, Cerebras, Amazon Bedrock, GitHub Copilot, and OpenAI-compatible services. Use when implementing LLM integrations, building agentic workflows with tool calling, switching between AI providers, managing conversation context, handling streaming responses, implementing vision capabilities, or tracking token usage and costs. Triggers on installing/configuring pi-ai, defining tools with TypeBox schemas, implementing stream/complete calls, handling tool calls and results, cross-provider handoffs, context serialization, or any multi-provider LLM integration work.
| name | omnicore-cli |
| description | OmniCore CLI usage via `bbot <command>` for starting kernel/supervisor, checking status, managing sessions, and updating config/secrets. Use when running or documenting OmniCore CLI commands or when CLI flags/behavior change. |
Run OmniCore CLI commands. Source code you can find in @bbot/omnicore src/cli.ts.
bbot <command> [args...]
kernel: Start the kernel.supervisor: Start the supervisor (spawns the kernel).status: Show kernel status from the event log.restart: Request a kernel restart via event.sessions: List sessions.session-archive <sessionId>: Archive a session.session-rename <sessionId> <title>: Rename a session.session-root <sessionId> <path>: Set session root path (only before first LLM call).sessions-rebuild: Rebuild sessions projection from the event log.Examples:
bbot status
bbot sessions --status archived --limit 50
bbot session-root session:abc /path/to/root
config: Interactive wizard (TTY required).config wizard: Same as config.config show: Print current kernel config (JSON).config set-model <provider> <model>config set-base-url <url>config set-thinking <off|minimal|low|medium|high|xhigh>config set-compaction-enabled <true|false|1|0|yes|no>config set-compaction-reserve <tokens>config set-compaction-keep <tokens>config set-auto-compact <number|off>config set-secret <key> <value> or config set-secret <key> --promptExamples:
bbot config set-model openai gpt-4o-mini
bbot config set-base-url https://api.openai.com/v1
bbot config set-thinking medium
bbot config set-secret llm.apiKey --prompt
SKILLS file in the same change.