agents
Use when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls…
Use as the functions build stage of the Butterbase journey. Implements the Functions section of 02-plan.md by delegating to function-dev for each function. Calls deploy_function per function; smokes each with invoke_function. Skipped if the plan has no functions.
$ npx -y skills add butterbase-ai/butterbase-skills --skill journey-functions --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/journey-functionsContext preview
The summary Claude sees to decide when to auto-load this skill.
Use as the functions build stage of the Butterbase journey. Implements the Functions section of 02-plan.md by delegating to function-dev for each function. Calls deploy_function per function; smokes each with invoke_function. Skipped if the plan has no functions.
name: journey-functions description: Use as the functions build stage of the Butterbase journey. Implements the Functions section of 02-plan.md by delegating to function-dev for each function. Calls deploy_function per function; smokes each with invoke_function. Skipped if the plan has no functions.
Stage 3e of the guided journey. Implement and deploy each function in the plan.
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.
0. **Refresh docs.** Call `butterbase_docs` with `topic: "functions"`. For trigger types and ctx shape, also WebFetch `https://docs.butterbase.ai/functions`. Skip if cache is fresh.
0.5. **Check built-in integrations first.** Before writing function code that calls an external SaaS for email / messaging / calendar / CRM / payments:
Inside a function, prefer `ctx.db` / `ctx.storage` / `ctx.user` for the common cases — those are pre-wired and authenticated against the calling user. But for cross-app calls, scripts, or scheduled jobs that operate on multiple apps, instantiate `@butterbase/sdk` with a service key (`bb_sk_`) and use the same client surface as the frontend.
Example for a cron function that aggregates from another app:
import { createClient } from '@butterbase/sdk';
export async function handler(_request: Request, ctx: { env: Record<string,string> }) {
const other = createClient({
apiUrl: ctx.env.OTHER_APP_API_URL,
apiKey: ctx.env.OTHER_APP_SERVICE_KEY,
});
const { data } = await other.db.from('events').select('*').gte('created_at', ...);
// ...
return new Response('ok');
}For server-side patterns, `butterbase_docs` `topic: "sdk"`.
For each function in the plan, in order:
1. Print: `"About to build function: <name> (trigger=<trigger>). Proceed?"`. Wait for `yes`. 2. Invoke `butterbase-skills:function-dev` via the Skill tool with the function spec (name, trigger, behaviour, dependencies) and `app_id`. The wrapped skill scaffolds the handler, writes tests where appropriate, and calls `deploy_function`. Reminder it must enforce: handler signature `(request, { db, env, user })` and must return `new Response(...)`. 3. Smoke: call `invoke_function` for HTTP/cron functions and confirm a 2xx + expected body. For WebSocket, defer the smoke to frontend integration. 4. Append one line per function to `docs/butterbase/04-build-log.md`: `<ISO timestamp> functions deploy_function <fn-name> ok` 5. After all functions are done, tick `- [x] functions` in `00-state.md`, set `current_stage:` to the next unchecked stage. 6. Return to `journey` orchestrator (or ask `"Continue to the next stage? (yes/no)"`).
Claude Code plugin for Butterbase — the AI-Native Backend-as-a-Service. This plugin gives Claude deep knowledge of Butterbase's 42+ MCP tools, guides you through common workflows, and auto-configures the MCP server connection.
Repo: butterbase-ai/butterbase-skills
Use when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls…
Use when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage
Use when configuring OAuth providers (Google/GitHub/Apple/X/etc.), setting up post-login auth hooks, tuning JWT lifetimes, or generating service API keys
Use when building a new Butterbase app from scratch, creating a full-stack application, or when the user asks to set up a complete backend with database, auth,…
Use when contributing to the Butterbase codebase, adding new MCP tools, creating API routes, writing migrations, or understanding the monorepo architecture
Use when users report access denied errors, see wrong data, RLS policies are not working, or when troubleshooting Row-Level Security issues in Butterbase