A high-performance batch processing skill for running asynchronous AI inference jobs at scale through the Doubleword API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install doubleword-api
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install doubleword-api using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Doubleword Batches?
Doubleword Batches is a powerful skill designed to handle large volumes of AI inference requests without the overhead of real-time processing. It allows users to submit thousands of independent requests in a single batch, making it an essential addition to your collection of Openclaw Skills for cost-effective and scalable AI operations. By leveraging the Doubleword API, this skill manages the entire lifecycle of asynchronous jobs, from file preparation to result retrieval.
This skill is particularly valuable for developers and data scientists who need to process massive datasets where immediate response times are not critical but throughput and cost efficiency are. It supports OpenAI-compatible endpoints, ensuring seamless integration into existing workflows while offering advanced features like flexible completion windows and partial result streaming.
Doubleword Batches Use Cases
- Processing thousands of independent AI prompts for data augmentation.
- Large-scale text analysis or sentiment classification on historical datasets.
- Generating batch summaries for extensive document libraries.
- Executing AI workloads during off-peak hours to reduce costs.
- Handling background inference tasks that exceed standard rate limits.
How Doubleword Batches Works
- Generate a JSONL file containing multiple independent request objects.
- Upload the request file to the Doubleword API to receive a unique file ID.
- Initialize a batch job by specifying the file ID and a completion window (1h or 24h).
- Monitor the job status through periodic polling until processing reaches completion.
- Retrieve the processed results or error logs via the generated output file IDs.
Doubleword Batches Setup
To integrate this skill into your Openclaw Skills library, follow these steps:
- Ensure you have a valid Doubleword API key and set it as an environment variable:
export DOUBLEWORD_API_KEY="your_api_key_here"
- (Optional) Use the provided helper script to generate your first batch file:
python scripts/create_batch_file.py output.jsonl
- Start submitting batches using the standard CLI or API integration.
Doubleword Batches Data Schema & Taxonomy
The skill utilizes specific file formats and metadata for job tracking:
| Component | Format | Description |
|---|---|---|
| Input File | JSONL | Newline-delimited JSON containing custom_id, method, url, and body. |
| Output File | JSONL | Contains the original custom_id paired with the AI response body and status code. |
| Error File | JSONL | Captures failed requests with specific error codes and messages for debugging. |
| Metadata | JSON | Tracks request_counts (total, completed, failed) and job status. |
Doubleword Batches Advanced Features
- Flexible completion windows: Choose 24h for maximum savings or 1h for priority processing.
- Real-time result streaming: Access partial results via the X-Incomplete header before the full batch completes.
- Intelligent error handling: Automatic error log generation for targeted retries of failed requests.
- Scalable throughput: Support for high-concurrency workloads with file sizes up to 200MB.
- Granular job monitoring: Detailed status tracking including validating, in_progress, and cancelling states.
SKILL.md
Loading
Related Openclaw Skills
mflux: Local Apple Silicon Image Generation
A high-performance MLX-based skill for generating images locally on Apple Silicon using FLUX.2 and Z-Image models.
ModelWar AI CoreWar Arena
A competitive arena where AI agents battle in a virtual computer using the classic CoreWar programming game.
Scrapling
A high-performance Python-based web scraping tool designed for resilient data extraction from static, dynamic, and anti-bot protected websites.
Local Pandoc
A versatile document conversion skill that enables AI agents to transform Markdown files into professional PDFs, HTML, and Word documents using the Pandoc utility.
Doubleword Batches
A powerful batch processing system for executing large-scale AI inference requests asynchronously with significant cost savings.
Baselight MCP
A powerful MCP server connection providing real-time SQL access to over 50 premium datasets directly within your AI coding agent or IDE.
Featured*
