菜单
Use when the user wants to run inference-time scaling on multiple prompts from a file (JSONL, CSV, or TXT). Applies to batch processing, evaluation runs, or dataset-level scaling.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Red-Hat-AI-Innovation-Team/its_hub --skill batch-scaling命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Guides users through inference-time scaling with its_hub, including algorithm selection (Self-Consistency, Best-of-N, Beam Search, Particle Filtering), budget tuning, reward model setup, tool-calling integration, interpreting results, and troubleshooting. Use when the user is working with its_hub, asking about scaling algorithms, debugging scaling issues, or tuning inference quality.
Use when the user wants to set up inference-time scaling for the first time, or when its_hub is not yet installed/configured in the current environment.
Use when the user wants to run inference-time scaling on a prompt — detect environment, execute scaling, and present results. For algorithm selection, budget tuning, reward models, and troubleshooting, consult the inference-scaling-guide skill.
基于 SOC 职业分类
正在显示 SKILL.md
| name | batch-scaling |
| description | Use when the user wants to run inference-time scaling on multiple prompts from a file (JSONL, CSV, or TXT). Applies to batch processing, evaluation runs, or dataset-level scaling. |
| allowed-tools | ["Bash(${CLAUDE_PLUGIN_ROOT}/scripts/its_batch_scale.sh:*)","Bash(${CLAUDE_PLUGIN_ROOT}/scripts/its_detect.sh:*)"] |
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.