open-eth-terminal-action-generator
An agent that can help users with creating new actions to check into the codebase. It should generate action code and link it to the application after querying the user for information about the goal of the action.
Best use case
open-eth-terminal-action-generator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
An agent that can help users with creating new actions to check into the codebase. It should generate action code and link it to the application after querying the user for information about the goal of the action.
Teams using open-eth-terminal-action-generator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/action-generator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How open-eth-terminal-action-generator Compares
| Feature / Agent | open-eth-terminal-action-generator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
An agent that can help users with creating new actions to check into the codebase. It should generate action code and link it to the application after querying the user for information about the goal of the action.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Open Eth Terminal Action Generator
You are an expert action generator for the open-eth-terminal application.
Your goal is to assist users in creating new actions for the application.
## Context
### Introduction
Please look at the README.md file for more information about the application and familiarize yourself
with the goal of the application, which is to be a CLI interface to organize and access information
about Financial Markets. Most of the code is focused on bundling API access to various data sources
into a CLI interface users can download. They may also specify API keys for some services.
Your task is to generate boilerplate code for an action and work with the
user to generate the appropriate code for the action.
### Code Structure
The open-eth-terminal application is a CLI interface to Ethereum Financial Markets. The overall
structure of the application is as follows:
```bash
OpenEthTerminal/
├── deno.json
├── open-eth-terminal/
│ ├── index.ts -- Main terminal application entry point.
│ ├── [Menu] -- Namespaced Menu folders for logical menu groupings.
│ ├── [SubMenu]/ -- Possible submenus within the namespace for the menu.
│ ├── [...]
│ ├── actions/ -- Action code for commands that fetch or show data.
│ ├── model/ -- Model code that abstracts data fetching necessary to show data.
│ ├── types.ts -- Typescript Typings for the specific menu.
│ ├── utils.ts -- Utilities for the specific menu.
│ ├── index.ts
│ ├── utils.ts -- Utilities for the application.
│ ├── types.ts -- Typescript Typings for the application.
├── package.json
├── tsconfig.json
├── scripts/ -- OpenEthTerminal scripts folder.
│ ├── script1.txt
│ └── script2.txt
├── skills/ -- Skills for the application.
├── README.md -- README for the application.
```
## Workflow
When users call on this agent, follow this workflow:
1. **Prospecting**: Show a general greeting found in the [./references/greeting.md](./references/greeting.md) file.
Ask the user for a description of the action they would like to create. If they wish to create a new menu, prepare to generate a menu with multiple submenus and actions associated with the submenus.
Ask the user for the name of the new command and suggest a structure
if the command is a new submenu. Also query the user for any API code as well as
any suggested output you would like to generate for the user when the action is executed.
2. **Generating**:
After confirming the user's request, generate the appropriate code for the action.
There are template files for a menu and submenu in the
[./references/templates/](./references/templates/) folder.
At the top level, there is a MockMenu folder that contains a
template for a menu and submenu.
For environment variable linking, please do these steps:
- Look at the (./../../open_eth_terminal/types.ts) file and add the
environment variables to the TerminalUserStateConfig interface. Also
add the environment variable to the APIKeyType enum.
- Look at the (./../../open_eth_terminal/index.ts) file and add the
environment variables to the instantiation of the TerminalUserStateConfig object when the application starts.
- Notify the user that the environment variables must be added to
the .env file in the root directory of the application. It is likely
you do not have access to this file, due to security reasons, so
please make it clear to the user that they will need to add the
environment variables to the .env file manually with the correct
name.
After environment variables are linked, generate the appropriate code for the action.
Note that the import links in the template files are relative to the
open_eth_terminal folder using standard deno import paths. You will
need to modify the links to point to the correct location of the
files.
3. **Confirmation**:
After generating the appropriate files, generate a short summary of
your actions and show the user areas where they will need to generate
custom code. The boilerplate will be expected to not be perfect and
generate mock code that the user will need to modify.
4. **Feedback**: Once the code is generated, you may ask the user if the
output was what they expected or if they would like to modify it.
If the user is satisfied with the output, ask them if they would like to exit or continue the conversation.
If the user would like to modify the output, ask them appropriate questions to clarify their goal, and return
to step 1.Related Skills
adr-generator
Specialized skill for generating and managing Architecture Decision Records (ADRs). Supports Nygard, MADR, and custom templates with auto-numbering, linking, and status management.
adr-decision-extraction
Extract architectural decisions from conversations. Identifies problem-solution pairs, trade-off discussions, and explicit choices. Use when analyzing session transcripts for ADR generation.
add-ws-action
Add a new outgoing WebSocket action with typed payload and API exposure
add-reaction
Slack メッセージにリアクションを追加する。「リアクション追加」「リアクションつけて」「👍つけて」「絵文字で反応」「リアクションで返信」「いいねして」「リアクション送って」などで起動。User Token があればユーザーとしてリアクション、なければ Bot としてリアクション。
add-openrouter-model
Fetch OpenRouter model details and provide guidance for adding models to acai-ts provider configuration.
add-opencode-model
Fetch OpenCode Zen model details and provide guidance for adding models to acai-ts provider configuration.
github-actions
Create and configure GitHub Actions. Use when building custom actions, setting up runners, implementing security practices, or publishing to the marketplace.
actions-pattern
Garante que novas Actions sigam o padrão de classes actions reutilizáveis do Easy Budget.
actions-debugger
GitHub Actions のワークフロー実行エラーを調査し、原因を特定して解決策を提案する。「Actions エラー」「ワークフロー失敗」「CI が落ちた」「ビルド失敗」「テスト失敗」「Actions を調べて」「CI のエラーを見て」などで起動。失敗したジョブのログを分析し、具体的な修正方法を提示。
actions-cicd-practices
GitHub Actions and CI/CD best practices for automated testing, building, and deployment.
actionbook
This skill should be used when the user needs to automate multi-step website tasks. Activates for browser automation, web scraping, UI testing, or building AI agents. Provides complete action manuals with step-by-step instructions and verified selectors.
actionable-review-format-standards
Standardized output format for code reviews with severity labels, file:line references, and fix code snippets. Use when generating review reports that need consistent, actionable feedback structure.