Stats
Actions
Tags
From its-hub
Runs inference-time scaling on multiple prompts from JSONL, CSV, or TXT files. Useful for batch processing, evaluation runs, or dataset-level scaling.
How this skill is triggered — by the user, by Claude, or both
Slash command
/its-hub:batch-scalingThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run inference-time scaling on multiple prompts from a file.
Run inference-time scaling on multiple prompts from a file.
prompt or messages fieldprompt column"${CLAUDE_PLUGIN_ROOT}/scripts/its_detect.sh"
If config=missing, tell the user to run the setup-guide skill first.
Call the batch scaling script with the input file and any overrides:
"${CLAUDE_PLUGIN_ROOT}/scripts/its_batch_scale.sh" [--algorithm ALG] [--budget N] [--model KEY] [--output FILE] <input-file>
The script loads config once and processes all prompts in a single process. Default output path is results/<input_name>_scaled.jsonl.
The script outputs a JSON summary with total, succeeded, failed, failures, and output_file.
Report: "N/M prompts completed successfully. K failed. Results written to <output_file>"
If there were failures, list the line numbers and error messages.
npx claudepluginhub red-hat-ai-innovation-team/its_hub --plugin its-hubDetects the inference-time scaling environment and executes scaling on a prompt, then presents the selected response and configuration metadata.
High-volume, asynchronous offline inference via Together AI's Batch API. Prepares JSONL inputs, uploads files, creates jobs, polls status, and downloads outputs for bulk classification, synthetic data generation, and dataset transformations.
Processes thousands of documents asynchronously using Google's Gemini Batch API at 50% lower cost. Enforces correct API patterns to avoid silent failures.