Menu
通过生成并运行 Python 脚本处理大体量 Excel 文件，适用于 read_excel 全量读取成本高、需要分批处理或复杂计算的任务。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
通过 Python 脚本 (python-docx) 处理复杂 Word 文档操作
Word 文档读取、编辑与内容生成
Use when performing systematic codebase health checks, proactive bug hunting, or comprehensive code review across a repository. Trigger for requests like "find bugs", "code audit", "check code quality", "find dead code", "race condition review", and periodic maintenance inspections.
Scaffold MCP server projects and baseline tool contract checks. Use for defining tool schemas, generating starter server layouts, and validating MCP-ready structure.
Lightweight helper to enforce TDD-style loops for non-deterministic agents.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
| name | excel_code_runner |
| description | 通过生成并运行 Python 脚本处理大体量 Excel 文件，适用于 read_excel 全量读取成本高、需要分批处理或复杂计算的任务。 |
| file_patterns | ["*.xlsx","*.xlsm","*.xls"] |
| resources | ["references/largefile_code_workflow.md"] |
| version | 1.0.0 |
优先采用“探查 -> 写脚本 -> 执行 -> 验证”的四步流程：
get_file_info 查看 size_bytes，超过阈值时保持“子上下文只读探索 + 摘要返回”。read_excel(max_rows=200) 获取列名与样本数据。write_text_file 生成 scripts/temp/*.py 脚本。pandas.read_excel(usecols=..., nrows=...) 做范围控制。outputs/，不要把全量数据直接回传。run_code 执行脚本，默认 python_command=auto。stderr_tail，修复后再次写入并执行。关键约束：