runware-image

Runware Image Skill

Purpose

Provide a secure, documented, and testable integration for generating images via the Runware.ai Image Inference API.

IMPORTANT INSTRUCTIONS FOR AGENT:
1. **Do NOT ask the user for the RUNWARE_API_KEY.** The script automatically loads it from the `.env` file in the skill directory.
2. **Do NOT ask clarifying questions** (style, size, etc.) unless the user's prompt is extremely vague. For requests like "generate a man on the moon", use your best judgment for the prompt and run the script immediately.
3. **Execute the script directly.** Do not propose it.

What it does

- Send text-to-image tasks to Runware's task API (imageInference).
- Support synchronous (sync) responses returning base64 image data and asynchronous workflows (webhook/polling) if required.
- Save generated images to the user's Downloads folder by default.
- Validate prompts for common safety issues (e.g., minors) before sending requests.

Included files

- scripts/generate_image.py — Primary CLI script (Python 3.8+). Reads RUNWARE_API_KEY from environment, supports sync mode, size/format options, and output filename.
- skill-config.json — default parameters (no secrets). Contains default_size and default_format.
- SKILL.md — this metadata and usage file.

Security & secrets

- DO NOT commit API keys. This skill requires RUNWARE_API_KEY to be provided via the environment when executed (export RUNWARE_API_KEY=...) or via a secure secret manager.
- The packaged version uploaded to ClawHub must not include any API keys. Before publishing, confirm skill-config.json contains NO sensitive values.
- The script performs simple prompt filtering; users should still follow platform content policies.

Usage (CLI)

1. Install dependencies
   - pip install -r requirements.txt
   (The script uses requests and python-dotenv; keep requirements minimal.)

2. Set your Runware API key. You can create a `.env` file in the skill directory:
   `RUNWARE_API_KEY=your_key_here`
   Or set it in yo...

# runware-image

Runware Image Skill - a small CLI skill to generate images on-demand via the Runware.ai Image Inference API.

This repository contains an OpenClaw-style skill that provides a Python CLI script to submit text-to-image tasks to Runware, save generated images locally, and includes tests, examples, and CI configuration to make the skill production-ready for publishing to ClawHub (or GitHub first).

## Features

- Submit text-to-image tasks to Runware's task API (imageInference).
- Default synchronous generation (returns base64 image data) with support for async/webhook workflows.
- Safe-by-default prompt validation to reduce the risk of generating images of minors.
- Default output directory: `~/runware_images` (created automatically). The script remembers the last used output directory.
- Minimal dependencies. Tests can be configured to run in CI with secrets for integration or skipped when no RUNWARE_API_KEY is present.

## Contents

- `SKILL.md` - Skill metadata and usage guidance (required by OpenClaw skills).
- `skill-config.json` - Default settings (no secrets). Contains `default_size`, `default_format`, and `default_output_dir`.
- `scripts/generate_image.py` - Primary CLI script (Python 3.8+).
- `requirements.txt` - Minimal dependencies.
- `tests/test_generate_image.py` - Pytest unit test that mocks Runware responses.
- `examples/` - Example CLI commands.
- `.github/workflows/ci.yml` - GitHub Actions CI workflow to run tests.
- `LICENSE`, `CONTRIBUTING.md` - Project metadata.

## Quick Start (GitHub)

1. Clone the repository:

  git clone <repo-url>
  cd runware-image

2. Create a Python virtual environment and install deps:

  python -m venv .venv
  source .venv/bin/activate # or .\.venv\Scripts\activate on Windows
  pip install -r requirements.txt

3. Set your Runware API key.
   - Create a `.env` file in the root of the skill: `RUNWARE_API_KEY=your_key`
   - OR set it in the environment: `$env:RUNWARE_API_KEY = "<YOUR_KEY>"`

4. Generate an im...