encore-getting-started
Set up Encore.ts from scratch. Install the CLI, log in, create an app, check that it runs, and connect Encore's MCP servers, with a pointer to the skill for each step. Ends where building starts. Not for architecture or feature questions.
- Installs
- 678
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/encoredev/skills --skill encore-getting-started- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads encore-getting-started automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Setting Up Encore.ts
Instructions
This guide is for Encore.ts. For Encore Go, use encore-go-getting-started. If the user hasn't said which language they want, ask.
Do the steps in order. Each step says how to tell it worked. If a step fails, load the skill it names.
1. Check the CLI
encore version
- Prints
encore version v...: go to step 2. - Command not found: install it (
encore-install), then go to step 2.
2. Log in
Skip this step if the user only wants to run the app locally.
encore auth whoami
logged in as <email>: go to step 3.not logged in.: startencore auth loginin the background. Send the user the pairing code and URL it prints, and ask them to approve it in a browser on any device. Wait forSuccessfully logged in!(encore-login).logged in as app <app-id>, or no person can approve a login (CI): an auth key can't create apps. Ask the user to create the app in the Cloud Dashboard, then runencore app clone <app-id>,cdinto it, and go to step 4.
3. Create the app
encore app create my-app --example=ts/hello-world
cd my-app
- Ends with
Successfully created app my-app!: go to step 4. - Keep the
--exampleflag. In a terminal, the CLI asks for a language and template when it's missing. Without a terminal, which is how agents usually run commands, it can't ask, and creates an empty Go app instead. - Empty app: for an app with no services, use
--example=ts/emptyinstead, and skip step 4. - Other templates and errors: see
encore-create-app.
4. Check that it runs
encore check 'curl /hello/world'
- Prints
{"message":"Hello world!"}and exits 0: go to step 5. - Fails: see
encore-run.
To keep the app running for the user, start encore run in the background, never in the foreground (encore-run). The API is at http://localhost:4000, and the local development dashboard, with a trace of every request, is at http://localhost:9400.
5. Connect Encore's MCP servers
The MCP servers let you inspect and call the app while you build it, and read its deploys once it's on Encore Cloud. If the user created the app with --llm-rules=<tool>, the local server may already be configured for that tool: check before adding it again.
-
Local server: from the app's root directory, run
encore mcp start. It printsMCP stdio Command: encore mcp run --app=<app-id>. Add that command to the user's tool. In Claude Code:claude mcp add --transport stdio encore-local -- encore mcp run --app=<app-id> -
Encore Cloud server (only if you logged in at step 2):
claude mcp add --transport http --scope user encore-cloud https://api.encore.dev/mcp -
Cursor, VS Code, other tools, or an API key instead of signing in: see
encore-mcp.
6. Report back
Setup is done. Tell the user:
- Where the app is: its directory, and, if it's on Encore Cloud, its Cloud Dashboard at
https://app.encore.dev/<app-id>. - What's left for them: their tool loads the new MCP servers when it restarts. If you added
encore-cloud, they also need to authenticate it once: in Claude Code,/mcp, selectencore-cloud, and choose Authenticate.
To build on the app, load the skill for the task. The hello-world app has one service, hello, in hello/.
| To | Load |
|---|---|
| Add endpoints, validation, and errors | encore-api |
| Add services or call one service from another | encore-service |
| Add a SQL database | encore-database |
| Require login on endpoints | encore-auth |
| Add Pub/Sub, cron jobs, buckets, secrets, or caching | encore-pubsub, encore-cron, encore-bucket, encore-secret, encore-cache |
| Write tests | encore-testing |
Deploy: commit, then git push encore | encore-deploy |
FAQ
What does the encore-getting-started skill do?
Set up Encore.ts from scratch. Install the CLI, log in, create an app, check that it runs, and connect Encore's MCP servers, with a pointer to the skill for each step. Ends where building starts. Not for architecture or feature questions.
How do I install encore-getting-started?
Run npx skills add https://github.com/encoredev/skills --skill encore-getting-started in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/encore-getting-started/ (personal) or .claude/skills/encore-getting-started/ (project).
Which AI agents can use encore-getting-started?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is encore-getting-started safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains encore-getting-started?
It is published by encoredev in encoredev/skills, and it is an official skill from the maker of the technology it covers. It has 678 recorded installs.
More from encoredev/skills
encore-api
encoredev/skills
Define typed API endpoints in Encore.ts using api(...) from encore.dev/api. Covers typed request/response interfaces, path/query/header/cookie params, request validation, and APIError. For raw endpoints (api.raw()) and inbound webhooks, use encore-webhook instead.
encore-auth
encoredev/skills
Protect Encore.ts endpoints with authentication and authorize callers. Covers authHandler, Gateway, getAuthData, and auth: true.
encore-code-review
encoredev/skills
Review existing Encore.ts code for best practices and common anti-patterns.
encore-service
encoredev/skills
Implement Encore.ts services and lay out an application using encore.service.ts, service directories, systems, and encore/clients. For service boundaries and architecture decisions, use encore-architecture.
encore-database
encoredev/skills
Work with PostgreSQL in Encore.ts using SQLDatabase from encore.dev/storage/sqldb — schema migrations and SQL queries.
encore-testing
encoredev/skills
Write or run automated tests for Encore.ts code with encore test and vitest/jest. Covers isolated per-test databases, calling handlers directly, and describe/it/expect.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available