Import Personal Documents. Use when the user wants to import a local directory or explicit files into 材序 at the ingest stage, including “导入一批材料”“先把这个目录吃进去”“先建立可继续建库的解析上下文”. Prefer caixu-skill when the user asks for the full end-to-end mainline or is unsure which stage to run. This skill creates or loads a library, starts an ingest pipeline run, lets the agent choose per-file routes over low-level OCR and parser tools, persists ParsedFile records, and hands off library_id plus run_id to build-asset-library. Do not use it for asset extraction, lifecycle judgment, package building, or submission.
在用户要“导入一批材料”“先把这个目录吃进去”“先建立可继续建库的解析上下文”时使用这个 skill。
library_id，再创建 ingest pipeline runlist_local_files，让 agent 为每个文件选择 routeParsedFile，写入 upsert_parsed_filesPipelineRun 结构时，读 references/tool-contracts.mdcaixu-data-mcp.create_or_load_librarycaixu-data-mcp.create_pipeline_runcaixu-ocr-mcp.list_local_filescaixu-ocr-mcp.read_local_text_filecaixu-ocr-mcp.extract_parser_textcaixu-ocr-mcp.extract_visual_textcaixu-ocr-mcp.render_pdf_pagescaixu-data-mcp.upsert_parsed_filescaixu-data-mcp.append_pipeline_stepcaixu-data-mcp.complete_pipeline_runinput_root or explicit local fileslibrary_id?owner_hint?library_id，先调 create_or_load_library。ingest run；之后每个关键动作都要追加 step。list_local_files 展开目录，再让 agent 为每个文件选择 text | parser_lite | parser_export | ocr | vlm | skip。ParsedFile，再统一写入 upsert_parsed_files。ToolResult 风格结果，至少包含：
data.library_iddata.run_iddata.file_idsdata.parsed_countdata.failed_countdata.warning_countdata.skipped_countdata.parsed_filesdata.failed_filesdata.warning_filesdata.skipped_filesbuild-asset-library。list_local_files。asset_card 抽取、归并、生命周期判断、打包或提交。suggested_route，但必须留下 step 和 warning。skip，不要硬塞进 parser/OCR。upsert_parsed_files 失败，返回结构化存储错误，并停止推荐下一步。