菜单
Use as the AI build stage of the Butterbase journey. Implements the AI section of 02-plan.md by delegating to the ai skill. Calls manage_ai (update_config) to set defaults and optionally BYOK. Skipped if the plan has no LLM/embeddings usage.
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
Claude Code plugin for Butterbase — 30+ guided skills and auto-configured MCP for the AI-native backend-as-a-service.
Use when the user wants to read/write their Butterbase substrate — the per-user agent-memory backend that holds entities, business state, institutional memory, and an append-only action ledger. Use for: founder copilots, AI agents that need memory across sessions, anything that proposes actions on the user's behalf.
Use when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits. Agents are first-class app resources defined by a `graph_spec` and invoked over `/v1/<app_id>/agents/<name>/runs`.
Use as the agents build stage of the Butterbase journey. Implements the Agents section of 02-plan.md by delegating to the `agents` skill for each agent. Registers any required MCP servers, validates each graph_spec, creates the agent, and smokes it via invoke_agent. Skipped if the plan has no agents.
Use as stage 1 of the Butterbase journey, when the user has only a rough idea ("I want to build something that..."). Conducts a concrete, one-question-at-a-time brainstorm that surfaces who the user is, what they do first, what the must-haves are, and inline-tags Butterbase capabilities (→ manage_schema, → deploy_function, etc.). Produces docs/butterbase/01-idea.md.
Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md. Translates the idea + capability map into a concrete Butterbase plan — tables (with columns/types/RLS shape), auth providers, function list (name + trigger), storage buckets, AI/RAG/realtime/durable usage, and the chosen frontend stack. In hackathon mode, ruthlessly cuts scope into a "ship now" vs "post-hackathon" split. Produces docs/butterbase/02-plan.md.
| name | journey-ai |
| description | Use as the AI build stage of the Butterbase journey. Implements the AI section of 02-plan.md by delegating to the ai skill. Calls manage_ai (update_config) to set defaults and optionally BYOK. Skipped if the plan has no LLM/embeddings usage. |
Stage 3f of the guided journey. Configure AI gateway defaults (model, BYOK).
journey when current_stage: ai./butterbase-skills:journey-ai.(n/a)) if the plan has no AI section.If docs/butterbase/03-preflight.md is missing, older than 24 hours, or 00-state.md has app_id: null, invoke butterbase-skills:journey-preflight first. Wait for it to return successfully before proceeding.
docs/butterbase/02-plan.md — the AI section.docs/butterbase/00-state.md — for app_id.Refresh docs. Call butterbase_docs with topic: "ai". For BYOK and model lists, also WebFetch https://docs.butterbase.ai/ai. Skip if cache is fresh.
Read the AI section. Print it back: "About to configure AI: default model=<m>, BYOK=<yes/no>. Proceed?". Wait for yes.
Invoke butterbase-skills:ai via the Skill tool with the AI plan and app_id. The wrapped skill calls manage_ai action: update_config (and per-provider key updates if BYOK).
Smoke: call manage_ai action: chat with a tiny prompt ("say ok") to confirm the gateway responds.
Append one line to docs/butterbase/04-build-log.md:
<ISO timestamp> ai manage_ai ok
Tick - [x] ai in 00-state.md, set current_stage: to the next unchecked stage.
Return to journey orchestrator (or ask "Continue to the next stage? (yes/no)").
04-build-log.md.manage_ai action: list_models — list first.