القائمة
Extract text from PDF documents efficiently using poppler's pdftotext. Use when reading academic papers, extracting metadata, or searching PDF content.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when the user wants to convert a project's `paper/` directory into a git submodule pointing at a separate paper repo (typically for Overleaf linking). Handles removing any existing tracked `paper/` content, adding the submodule, writing a standardized README inside the submodule, and updating the parent repo's README.
Clean up PDF filenames by removing spaces, em dashes, and special characters
Create BibTeX entries from PDF papers and add to main.bib
Create a new Python script following project best practices. $ARGUMENTS
Create markdown summaries for PDF papers (creates BibTeX first if needed)
Clean README.md files in the entire repository or specified directories. $ARGUMENTS
| name | pdf-extraction |
| description | Extract text from PDF documents efficiently using poppler's pdftotext. Use when reading academic papers, extracting metadata, or searching PDF content. |
| allowed-tools | Bash, Read |
| user-invocable | false |
Extract text from PDF documents efficiently using poppler's pdftotext utility.
Use the extraction script at .claude/skills/pdf-extraction/scripts/pdf_extract.sh
For metadata extraction (title, authors, abstract, venue info):
.claude/skills/pdf-extraction/scripts/pdf_extract.sh first "{pdf_path}" 3
.claude/skills/pdf-extraction/scripts/pdf_extract.sh page "{pdf_path}" {page_num}
.claude/skills/pdf-extraction/scripts/pdf_extract.sh range "{pdf_path}" {start} {end}
Returns matching lines with line numbers:
.claude/skills/pdf-extraction/scripts/pdf_extract.sh search "{pdf_path}" "query"
Identifies which pages contain specific content:
.claude/skills/pdf-extraction/scripts/pdf_extract.sh search-pages "{pdf_path}" "Method"
Only for short papers (<8 pages):
.claude/skills/pdf-extraction/scripts/pdf_extract.sh all "{pdf_path}"
search-pages to locate key sections (Methods, Results, Limitations, Discussion, Conclusion)