mcpbeat Sign in

Journey Frontend Agent Skill

Use as the frontend build stage of the Butterbase journey. Implements the Frontend section of 02-plan.md by delegating to deploy-frontend. Scaffolds (if needed) and deploys via create_frontend_deployment + manage_frontend (start_deployment). Sets VITE_API_URL and VITE_APP_ID env. Skipped if the plan is API-only.

890 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
532
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/butterbase-ai/butterbase-skills --skill journey-frontend

The instruction itself

9 sections, as written by the author

Journey: Frontend

Stage 3j of the guided journey. Build (or adopt) and deploy the frontend.

When to use

  • Dispatched by journey when current_stage: frontend.
  • Directly via /butterbase-skills:journey-frontend.
  • Skipped (annotated (n/a)) if frontend_stack: none in 00-state.md.

Preflight

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.

Inputs

  • docs/butterbase/02-plan.md — the Frontend section.
  • docs/butterbase/00-state.md — for app_id, api_base, frontend_stack.

Procedure

  • Refresh docs. Call butterbase_docs with topic: "frontend". For framework-specific deploy patterns, also WebFetch https://docs.butterbase.ai/frontend. Skip if cache is fresh.

Use @butterbase/sdk

Any frontend that talks to the deployed Butterbase app should use @butterbase/sdk:

  • Install: npm install @butterbase/sdk inside the frontend project.
  • Initialize: import { createClient } from '@butterbase/sdk'; const bb = createClient({ apiUrl: import.meta.env.VITE_API_URL, appId: import.meta.env.VITE_APP_ID });
  • Auth: bb.auth.signInWithOAuth({ provider: 'google' }), bb.auth.signOut(), bb.auth.getSession().
  • Data: bb.db.from('posts').select('*').eq('user_id', userId).
  • Storage: bb.storage.upload(file), persist the returned object_id, resolve download URLs via the SDK at render time.
  • Realtime: bb.realtime.from('posts').on('insert', cb).subscribe().

Do NOT hand-roll fetch() against the REST API in a Butterbase frontend — the SDK handles auth headers, presigned URL refresh, realtime reconnection, and type-narrowing. The MCP tools are not for runtime code.

For framework-specific patterns (Next.js Server Components, SvelteKit load functions, etc.), call butterbase_docs with topic: "sdk".

Build and deploy

  • Read the Frontend section and frontend_stack from 00-state.md. Print: "About to deploy a <stack> frontend for app_id <id>. Proceed?". Wait for yes.
  • Invoke butterbase-skills:deploy-frontend via the Skill tool with the frontend spec, app_id, and api_base. The wrapped skill scaffolds (if no package.json exists in ./web or chosen path), sets VITE_API_URL and VITE_APP_ID, builds, calls create_frontend_deployment, then manage_frontend action: start_deployment.
  • Capture the live URL from the response. Show it to the user.
  • Append one line to docs/butterbase/04-build-log.md:

<ISO timestamp> frontend manage_frontend <live-url> ok

  • Also write the live URL into a new deployed_url: field in 00-state.md front-matter.
  • Tick - [x] frontend in 00-state.md, set current_stage: deploy.
  • Return to journey orchestrator (or ask "Continue to deploy verification? (yes/no)").

Outputs

  • Live deployed frontend URL.
  • deployed_url: in 00-state.md.
  • One line in 04-build-log.md.

Anti-patterns

  • ❌ Forgetting to set VITE_API_URL and VITE_APP_ID — frontend will load blank.
  • ❌ Wrong MIME types — let deploy-frontend handle the bundling; do not hand-roll.

Other skills for the same job

different authors, same section of the catalogue
Modal
by christophacham
×3

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

17k tokens
Github Workflow Automation
by ComeOnOliver
×3

Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management

9k tokens
Gcloud
by Dicklesworthstone
×2

Google Cloud Platform CLI - manage GCP resources including Compute Engine, Cloud Run, GKE, Cloud Functions, Storage, BigQuery, and more.

2k tokens
Backend Architect
by ComeOnOliver
×2

Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and observability. Use PROACTIVELY when creating new backend services or APIs.

7k tokens
Modal
by ComeOnOliver
×2

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

37k tokens
Aspire
by github
vendor ×1

Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment. Use when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire distributed application.

21k tokens
Bigquery Pipeline Audit
by github
vendor ×1

Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Returns a structured report with exact patch locations.

1k tokens
Msstore CLI
by github
vendor ×1

Microsoft Store Developer CLI (msstore) for publishing Windows applications to the Microsoft Store. Use when asked to configure Store credentials, list Store apps, check submission status, publish submissions, manage package flights, set up CI/CD for Store publishing, or integrate with Partner Center. Supports Windows App SDK/WinUI, UWP, .NET MAUI, Flutter, Electron, React Native, and PWA applications.

4k tokens

How to use it

Copy the folder

Take butterbase-ai/journey-frontend from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference npm. Without those the skill loads but fails at the first command.