- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add first-fluke/oh-my-agent --skill oma-pdf -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add first-fluke/oh-my-agent --skill oma-pdf -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add first-fluke/oh-my-agent --skill oma-pdf -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add first-fluke/oh-my-agent --skill oma-pdf -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/first-fluke/oh-my-agent/tree/HEAD/.agents/skills/oma-pdf來自發布者
Convert PDF files into structured Markdown or another requested extraction format while preserving readable document structure for LLM context, RAG, or downstream review.
oma-hwpinput_path: PDF file or folder pathoutput_dir: optional target directoryformat: optional output format, default markdownocr_languages: optional OCR language list for scanned or image-based PDFsextraction_options: optional flags for tagged structure, image extraction, or hybrid conversionuvx opendataloader-pdf for standard conversionuvx --from "opendataloader-pdf[hybrid]" opendataloader-pdf-hybrid for OCR or hybrid conversion (the hybrid server is a console script of the [hybrid] extra, not a standalone package)uvx mdformat for Markdown normalizationfile, wc, or pdfinfo--use-struct-tree.--table-method cluster or --markdown-with-html before escalating to hybrid mode.--to-stdout) so repeated runs do not overwrite the same basename.pdf.route-selection per ../_shared/runtime/route-selection.md (mode, and the probe or output defect that required it).output_dir and the expected output filename. Defaults come from the pdf: section of .agents/oma-config.yaml, falling back to config/pdf-config.yaml for unset keys; explicit user options override both, and output.overwrite: false requires confirmation before replacing an existing output file. Check file size and warn when the input is large enough to risk slow conversion or memory pressure.uvx opendataloader-pdf "{input_path}" -f text --pages 1-3 --to-stdout -q # text-layer probe (no temp files)
uvx opendataloader-pdf "{input_path}" --format markdown --output-dir "{output_dir}"
For scanned/image-based PDFs, start OCR first and then convert through hybrid mode. Attempt OCR only when the hybrid server is available or can be started:
uvx --from "opendataloader-pdf[hybrid]" opendataloader-pdf-hybrid --port 5002 --force-ocr --ocr-lang "{languages}"
uvx opendataloader-pdf --hybrid docling-fast --hybrid-mode full "{input_path}" --format markdown --output-dir "{output_dir}"
uvx mdformat "{output_path}"
On-request flags — --sanitize (PII masking), --pages (range extraction), --threads (parallel pages), --detect-strikethrough, hybrid --enrich-formula / --enrich-picture-description — are detailed in resources/execution-protocol.md. The two enrichment flags require client-side --hybrid-mode full.
Reads the input PDFs and does not modify the source PDF. Creates or overwrites extraction output in the output directory, depending on configuration and user intent. Runs uvx subprocesses and, for OCR, may start a local hybrid server on the configured port. Large or scanned PDFs may consume significant CPU, memory, or time.
resources/execution-protocol.md rather than duplicating every variant here.resources/execution-protocol.mdpdf: section of .agents/oma-config.yaml first, then fall back to config/pdf-config.yaml for any key it does not set. User overrides belong in .agents/oma-config.yaml, since oma update overwrites the skill config.../_shared/core/context-loading.md../_shared/core/quality-principles.mdExtract PDF text, headings, tables, and images into Markdown using opendataloader-pdf. Use for PDF parsing, not PDF layout creation.
---name: oma-pdfdescription: Extract PDF text, headings, tables, and images into Markdown using opendataloader-pdf. Use for PDF parsing…---# .agents/skills/oma-pdf/SKILL.md常見問題
從發布者下載 .agents/skills/oma-pdf/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/first-fluke/oh-my-agent。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。