Ecspresso logo

Ecspresso

OrganizationPopular
kayac
ecspresso

ECS deployment tool - deploy, manage, and troubleshoot ECS services

Overview

Publisherkayac
Repositoryecspresso
Skill nameecspresso
Stars
1.1K
Forks
115
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kayac on GitHub. Read the source before you install it.

Installation

Install the Ecspresso AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kayac/ecspresso/tree/v2/skills/ecspresso
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kayac/ecspresso.git /tmp/ecspresso
mkdir -p .claude/skills
cp -r /tmp/ecspresso/skills/ecspresso .claude/skills/ecspresso
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ecspresso in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ecspresso on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ecspresso is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ecspresso Skill for LLM Agents

Overview

ecspresso is a deployment tool for Amazon ECS. You can use it to deploy, manage, and troubleshoot ECS services through configuration files.

Learning about ecspresso

Use the docs subcommand to look up how ecspresso works. This command requires no AWS credentials or config file.

bash
# Browse the table of contents to find relevant sections
ecspresso docs --index --json

# Search for a topic by keyword
ecspresso docs --search "fargate" --json

# Read the full documentation
ecspresso docs --json

Always use --json for structured output that is easier to parse.

Common workflows

Check current state before making changes

bash
# Show service status (running tasks, deployments, events)
ecspresso status --config ecspresso.yml

# Show differences between local definitions and running service
ecspresso diff --config ecspresso.yml

# Verify that resources referenced in definitions exist and are valid
ecspresso verify --config ecspresso.yml

Deploy

bash
# Preview what will change (dry-run)
ecspresso deploy --config ecspresso.yml --dry-run

# Deploy the service
ecspresso deploy --config ecspresso.yml

# Deploy and wait until stable
ecspresso deploy --config ecspresso.yml --wait-until stable

Rollback

bash
# Rollback to the previous task definition
ecspresso rollback --config ecspresso.yml

# Rollback with dry-run
ecspresso rollback --config ecspresso.yml --dry-run

Scale

bash
# Scale to a specific number of tasks
ecspresso scale --config ecspresso.yml --tasks 5

Run a one-off task

bash
# Run a standalone task using the service's task definition
ecspresso run --config ecspresso.yml

# Run and watch logs
ecspresso run --config ecspresso.yml --watch-container app

Inspect tasks

bash
# List running tasks as JSON
ecspresso tasks --config ecspresso.yml --output json

Render configuration for inspection

bash
# Render resolved task definition (with template variables expanded)
ecspresso render --config ecspresso.yml taskdef

# Render resolved service definition
ecspresso render --config ecspresso.yml servicedef

Configuration structure

ecspresso uses a config file (default: ecspresso.yml) that references a task definition file and optionally a service definition file.

ecspresso.yml          # Main config: region, cluster, service, file paths
ecs-task-def.json      # ECS task definition (JSON, YAML, or Jsonnet)
ecs-service-def.json   # ECS service definition (JSON, YAML, or Jsonnet)

Definition files support template syntax: {{ env "VAR" "default" }}, {{ must_env "VAR" }}, and plugin functions like {{ tfstate "resource.attr" }}.

Jsonnet is recommended over JSON/YAML

When creating or modifying definition files, prefer the Jsonnet (.jsonnet) format over JSON or YAML. Jsonnet has several advantages:

  • Comments: Jsonnet supports // and /* */ comments. JSON does not allow comments at all.
  • Trailing commas: No need to worry about trailing comma errors.
  • Variables and functions: You can define local variables, reuse values, and compute derived values with std.parseInt(), std.parseJson(), etc.
  • No template syntax conflicts: In JSON/YAML, Go template syntax {{ }} can cause readability issues. In Jsonnet, use native functions like std.native('env')('VAR', 'default') instead, which are cleaner and can return non-string types.
  • No separate install needed: ecspresso bundles the Jsonnet library.

Example Jsonnet config:

jsonnet
// ecspresso.jsonnet
{
  region: 'ap-northeast-1',
  cluster: 'default',
  service: 'myservice',
  service_definition: 'ecs-service-def.jsonnet',
  task_definition: 'ecs-task-def.jsonnet',
}

Example Jsonnet task definition:

jsonnet
// ecs-task-def.jsonnet
local env = std.native('env');
local must_env = std.native('must_env');
local tfstate = std.native('tfstate');
{
  family: 'myservice',
  cpu: '256',
  memory: '512',
  networkMode: 'awsvpc',
  requiresCompatibilities: ['FARGATE'],
  executionRoleArn: tfstate('aws_iam_role.ecs_execution.arn'),
  containerDefinitions: [
    {
      name: 'app',
      image: must_env('APP_IMAGE'),
      cpu: 0,
      portMappings: [{ containerPort: 8080 }],
      environment: [
        { name: 'ENV', value: env('ENV', 'production') },
      ],
      logConfiguration: {
        logDriver: 'awslogs',
        options: {
          'awslogs-group': '/ecs/myservice',
          'awslogs-region': 'ap-northeast-1',
          'awslogs-stream-prefix': 'app',
        },
      },
    },
  ],
}

Use ecspresso init --jsonnet to generate Jsonnet files from an existing service. For more details, run ecspresso docs --search "jsonnet" --json.

Tips

  • Always run ecspresso diff before ecspresso deploy to understand what will change.
  • Use --dry-run on destructive operations (deploy, rollback, delete, scale) to preview the action.
  • The verify command checks IAM roles, container images, secrets, and log groups referenced in definitions.
  • When you need to learn more about a specific feature, use ecspresso docs --search "<keyword>" --json to find the relevant documentation section.

Frequently asked questions

What does the Ecspresso AI skill do?

ECS deployment tool - deploy, manage, and troubleshoot ECS services

Why use Ecspresso on TypingMind?

Because you install it once and use it with any model. Ecspresso is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ecspresso in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kayac/ecspresso/tree/v2/skills/ecspresso. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ecspresso?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ecspresso?

As many as you like. As long as a model supports skills, you can use Ecspresso with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ecspresso AI skill free?

Yes. It is published on GitHub by kayac under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇