Przejdź do treści
Biblioteka skilli
Dokumenty i biuro · Konwersja i formaty

office-parser

/office-parser

Odczytuje dokumenty Word, PowerPoint i Excel strumieniowo, dzieląc je na fragmenty do dalszej pracy z treścią i danymi.

Repozytorium
Crannia ↗
Licencja
Apache-2.0
Ostatnia zmiana repozytorium
14.11.2026

Ocena i bezpieczeństwo

85/ 100Klasa: dobry
Format20 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść25 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
80
Skrypty
41
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 14.11.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co sprawdzić przed instalacją
  • 41 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.

Skrypty: __init__.py, _excel_io.py, cell_validation.py, excel_query.py, excel_tools.py, excel_transform.py, handler.py, layout_spec.py, ppt_tools.py, pptx_export/__init__.py, pptx_export/console_encoding.py, pptx_export/resource_paths.py, pptx_export/svg_finalize/__init__.py, pptx_export/svg_finalize/align_embed_images.py, pptx_export/svg_finalize/crop_images.py, pptx_export/svg_finalize/embed_icons.py, pp

Co robi i kiedy

Odczytuje dokumenty Word, PowerPoint i Excel strumieniowo, dzieląc je na fragmenty do dalszej pracy z treścią i danymi.

Oryginalny opis (EN)

Parse Microsoft Office documents — Word (.docx), PowerPoint (.pptx), and Excel (.xlsx) — with streaming extraction and chunking. Use when working with Office documents, spreadsheets, presentations, or when the user mentions docx, pptx, xlsx, Word, Excel, PowerPoint, Office files.

Jak działa

  1. When to use
  2. Tools
  3. Write Tools (v0.8.0+)
  4. Shared tools
  5. Notes
Sekcje z nagłówków SKILL.md, w oryginale · 70 linii, 410 słów
Podgląd SKILL.md
---
name: office-parser
description: Parse Microsoft Office documents — Word (.docx), PowerPoint (.pptx), and Excel (.xlsx) — with streaming extraction and chunking. Use when working with Office documents, spreadsheets, presentations, or when the user mentions docx, pptx, xlsx, Word, Excel, PowerPoint, Office files.
metadata:
  kind: skill
  loader: manifest.yaml
  tools: parse_docx, parse_pptx, parse_xlsx, extract_document_structure, create_document, add_block, add_slide, export_document, get_workbook_metadata, read_excel_data, write_excel_data, apply_formula, validate_formula_syntax, format_excel_range, create_excel_chart, create_excel_pivot, create_excel_table, copy_worksheet, delete_worksheet, rename_worksheet, merge_excel_cells, unmerge_excel_cells, get_merged_cells, copy_excel_range, delete_excel_range, insert_excel_rows, insert_excel_columns, delete_excel_rows, delete_excel_columns, get_document_info, get_document_text, get_document_outline, list_available_documents, copy_document, merge_documents, add_word_heading, add_word_paragraph, apply_table_of_contents, delete_paragraph, search_and_replace_text, insert_content_near_text, format_paragraph_text, create_custom_style, format_word_table, set_table_cell_shading, apply_table_alternating_rows, highlight_table_header, merge_table_cells, merge_table_cells_horizontal, merge_table_cells_vertical, set_table_cell_alignment, set_table_alignment_all, set_table_column_width, set_table_width, auto_fit_table, format_table_cell_text, set_table_cell_padding, get_all_comments, get_comments_by_author, get_comments_for_paragraph, add_footnote, convert_to_pdf, convert_from_pdf, mock_image, create_svg_slide, svgs_to_pptx, set_slide_design, get_design_context, extract_archive, freeze_excel_panes, set_excel_conditional_format, add_excel_data_validation, profile_excel_data, find_excel_value, get_excel_comments, sort_excel_range, filter_excel_data, remove_excel_duplicates, protect_excel_sheet, set_excel_hyperlink, export_excel_to_csv, merge_excel_workbooks, recalculate_excel_formulas, plot_excel_data, add_table_rows, add_table_columns, delete_table_rows, delete_table_columns
  mcp_note: >
    Directory name is office_parser (underscore) for Python import compatibility.
    SKILL.md name uses office-parser (hyphen) per agentskills.io standard.
    A thin adapter layer (see MCP_ADAPTATION.md) will map these when
    publishing to the MCP ecosystem.
---

# Office Document Parser Skill

## When to use
Use this skill when the user needs to read, search, or summarize Microsoft Office documents.
Supports Word (.docx), PowerPoint (.pptx), and Excel (.xlsx) formats.

## Tools

### parse_docx
Stream-parse a Word document. Paragraphs are read one at a time via python-docx iterator,
accumulated into pseudo-pages (50 paragraphs each), and fed through the unified chunker.
Tables are also extracted and included inline.

### parse_pptx
Extract text from PowerPoint slides. Each slide is treated as one page. Text from all
shapes on each slide is collected, then chunked by the unified chunker.

### parse_xlsx
Stream-read an Excel spreadsheet using openpyxl read_only mode. Rows are read one at a time
via `iter_rows()`, accumulated into pseudo-pages (100 rows each), and chunked.
Optionally specify a sheet name; defaults to the active sheet.

### extract_document_structure
Extract document outline/structure from Word or PowerPoint files. For Word (.docx):
returns heading hierarchy (level, text, paragraph position). For PowerPoint (.pptx):
returns slide numbers, titles, layout types, and text preview. Use to quickly
understand document organization before doing a full parse.

## Write Tools (v0.8.0+)

### create_document
Initialize a new document session for creating Word, PowerPoint, or Excel files.
Returns a `session_id` used by all subsequent write operations.

### add_block
Append a content block to a Word document under construction. Supports: heading
(level 1-3), paragraph, table (rows of cells), list (ordered/unordered), image
(from file), and page_break. Max 20 blocks per document.

### add_slide
Append a slide to a PowerPoint presentation. Slide types: title (title+subtitle),
content (title+bullets), image (title+picture), table (title+data rows).

### write_sheet
Write rows of data to an Excel workbook sheet. Call repeatedly to add more data,
then `export_workbook` to render.

### finalize_document
Lock a document session for export. After this, no more `add_block`/`add_slide`
calls will succeed.

### export_document
Render a Word (.docx) or PowerPoint (.pptx) from accumulated blocks and save
to disk. Auto-finalizes if not already done.

### export_workbook
Render an Excel (.xlsx) workbook from accumulated sheets and save to disk.

## Shared tools
After parsing with any tool above, use these shared tools (from file-parser skill):
- **search_chunks**: BM25 keyword search across parsed content
- **summarize_document**: Iterative aggregation summary

## Notes
- File path resolution: bare filenames are auto-resolved under `workspace/`
- All paths validated by SecurityGuard before any file is opened
- openpyxl read_only mode ensures Excel files are never fully loaded into memory
- python-docx and python-pptx iterate one element at a time — no bulk reads
Pliki w paczce (80)
  • GUIDANCE.md 2 KB
  • SKILL.md 5 KB
  • __init__.py 1 KB
  • _excel_io.py 19 KB
  • cell_validation.py 5 KB
  • excel_query.py 22 KB
  • excel_tools.py 100 KB
  • excel_transform.py 39 KB
  • handler.py 127 KB
  • layout_spec.py 10 KB
  • manifest.yaml 127 KB
  • ppt_tools.py 30 KB
  • session.py 10 KB
  • soffice.py 3 KB
  • word_tools.py 119 KB
  • pptx_export/__init__.py 1 KB
  • pptx_export/console_encoding.py 1 KB
  • pptx_export/resource_paths.py 3 KB
  • pptx_export/svg_finalize/__init__.py 1 KB
  • pptx_export/svg_finalize/align_embed_images.py 20 KB
  • pptx_export/svg_finalize/crop_images.py 12 KB
  • pptx_export/svg_finalize/embed_icons.py 18 KB
  • pptx_export/svg_finalize/embed_images.py 10 KB
  • pptx_export/svg_finalize/fix_image_aspect.py 14 KB
  • pptx_export/svg_finalize/flatten_tspan.py 29 KB
  • pptx_export/svg_finalize/svg_rect_to_path.py 11 KB
  • pptx_export/svg_to_pptx/__init__.py 1 KB
  • pptx_export/svg_to_pptx/tspan_flattener.py 2 KB
  • pptx_export/svg_to_pptx/use_expander.py 4 KB
  • pptx_export/svg_to_pptx/drawingml/__init__.py 1 KB
  • pptx_export/svg_to_pptx/drawingml/context.py 7 KB
  • pptx_export/svg_to_pptx/drawingml/converter.py 29 KB
  • pptx_export/svg_to_pptx/drawingml/elements.py 86 KB
  • pptx_export/svg_to_pptx/drawingml/paths.py 13 KB
  • pptx_export/svg_to_pptx/drawingml/styles.py 21 KB
  • pptx_export/svg_to_pptx/drawingml/utils.py 26 KB
  • pptx_export/svg_to_pptx/pptx_package/__init__.py 1 KB
  • pptx_export/svg_to_pptx/pptx_package/builder.py 52 KB
  • pptx_export/svg_to_pptx/pptx_package/dimensions.py 4 KB
  • pptx_export/svg_to_pptx/pptx_package/discovery.py 3 KB
  • pptx_export/svg_to_pptx/pptx_package/media.py 4 KB
  • pptx_export/svg_to_pptx/pptx_package/narration.py 8 KB
  • pptx_export/svg_to_pptx/pptx_package/notes.py 8 KB
  • pptx_export/svg_to_pptx/pptx_package/slide_xml.py 5 KB
  • references/LICENSE-Office-Word-MCP-Server.txt 1 KB
  • references/LICENSE-excel-mcp-server.txt 1 KB
  • references/layout_library.md 31 KB
  • references/spec_lock.md 7 KB
  • references/ppt-master/LICENSE 1 KB
  • references/ppt-master/SKILL.md 76 KB
  • references/ppt-master/SOURCE.md 6 KB
  • references/ppt-master/references/executor-base.md 47 KB
  • references/ppt-master/references/shared-standards.md 54 KB
  • references/ppt-master/references/strategist.md 92 KB
  • references/ppt-master/references/template-designer.md 25 KB
  • references/ppt-master/references/visual-review.md 15 KB
  • references/ppt-master/references/visual-styles/_index.md 9 KB
  • references/ppt-master/references/visual-styles/blueprint.md 3 KB
  • references/ppt-master/references/visual-styles/brutalist.md 2 KB
  • references/ppt-master/references/visual-styles/chalkboard.md 2 KB
  • references/ppt-master/references/visual-styles/dark-tech.md 2 KB
  • references/ppt-master/references/visual-styles/data-journalism.md 2 KB
  • references/ppt-master/references/visual-styles/editorial.md 2 KB
  • references/ppt-master/references/visual-styles/glassmorphism.md 2 KB
  • references/ppt-master/references/visual-styles/ink-notes.md 2 KB
  • references/ppt-master/references/visual-styles/ink-wash.md 2 KB
  • references/ppt-master/references/visual-styles/memphis.md 2 KB
  • references/ppt-master/references/visual-styles/paper-cut.md 2 KB
  • references/ppt-master/references/visual-styles/photo-editorial.md 2 KB
  • references/ppt-master/references/visual-styles/pixel-art.md 2 KB
  • references/ppt-master/references/visual-styles/sketch-notes.md 2 KB
  • references/ppt-master/references/visual-styles/soft-rounded.md 2 KB
  • references/ppt-master/references/visual-styles/swiss-minimal.md 2 KB
  • references/ppt-master/references/visual-styles/vintage-poster.md 2 KB
  • references/ppt-master/references/visual-styles/zine.md 2 KB
  • references/ppt-master/workflows/beautify-pptx.md 27 KB
  • references/ppt-master/workflows/customize-animations.md 13 KB
  • references/ppt-master/workflows/native-enhance-pptx.md 12 KB
  • references/ppt-master/workflows/template-fill-pptx.md 24 KB
  • references/ppt-master/workflows/visual-review.md 12 KB

Wersje

W bazie nie ma innych skilli o nazwie office-parser.

Migawka bazy z 13.11.2026 · wersja paczki a428c6de48af (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 95document-processing
    Tworzy, edytuje i analizuje dokumenty biurowe (PDF, DOCX, PPTX, XLSX): wyciąga tekst, wypełnia formularze, tworzy dokumenty i analizuje dane.
  • 100office
    Tworzy, czyta, zmienia i sprawdza dokumenty Word, Excel i PowerPoint, a także starsze formaty plików biurowych.
  • 90office-documents
    Tworzy i konwertuje pliki Word, Excel, PowerPoint i PDF, a przed oddaniem sprawdza je w formacie i przelicza arkusze.
  • 100document-processing-expert
    Czyta, generuje i modyfikuje dokumenty biurowe i PDF z poziomu kodu: ekstrakcja z PDF i formularze, Word, Excel i PowerPoint, a także scalanie i dzielenie plików.
  • 100office
    Tworzy, edytuje i konwertuje lokalne pliki Word, PowerPoint, Excel i PDF, w tym arkusze z formułami, śledzenie zmian i scalanie PDF.
  • 100ms-office-python
    Obsługuje pracę z Microsoft Office i Microsoft 365 z Pythona: Excel, Word, PowerPoint, Microsoft Graph, uwierzytelnianie w Entra ID oraz utwardzanie, i kieruje do skilli szczegółowych tej rodziny.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.