genoffice — Claude Code skill: what it does, how to install
A Claude Code skill for creating and editing Office files locally via the GenOffice CLI. Generates slide decks or formula spreadsheets from raw inputs and converts file formats.
Apache-2.0 ★ 12,746 updated 2026-11-11
npx skills add genspark-ai/genoffice --skill genoffice -a claude-codeWhat genoffice does
Through the genoffice CLI, the agent builds pptx decks from a brief with a checked outline and per-page spec, or xlsx workbooks with formulas from CSV and JSON. It writes docx files from Markdown or HTML and converts between pdf, docx, xlsx, pptx, md, html and csv. genoffice info <file> inspects existing files first.
Commands run headless on GenOffice's own engines. Passing --json outputs a single status object with exit codes from 0 to 4. Document processing stays on your machine, except for search, image and media, which send the query or referenced file to the provider configured in GenOffice.
The skill requires the GenOffice app with CLI >=0.9.0, or calls fail with exit code 4. When genoffice is missing from PATH, the launcher path sits inside ~/.genoffice/launcher (or %USERPROFILE%\.genoffice\launcher on Windows). Commands also exit with code 2 if the output path already exists or the target file is open in the GenOffice window.
What it helps with
- Build a pptx presentation from a brief using a checked outline and per-page spec
- Generate an xlsx workbook with formulas from CSV or JSON data
- Convert documents between pdf, docx, xlsx, pptx, md, html and csv
- Inspect an existing Office file's structure and apply targeted edits
Example prompts for the agent
- Create a
deck.pptxpresentation from this brief and open it in GenOffice. - Turn
sales.csvinto anxlsxworkbook with monthly summary formulas. - Read the headings in
contract.docx, rewrite the second section and export to PDF.
How to install genoffice
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill genoffice -a claude-code2Manually: put the files in place
~/.claude/skills/genoffice/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/genoffice/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill genoffice -a codex2Manually: put the files in place
.agents/skills/genoffice/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill genoffice -a cursor2Manually: put the files in place
.cursor/skills/genoffice/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install genspark-ai/genoffice skills/genoffice2Manually: put the files in place
.github/skills/genoffice/SKILL.md1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill genoffice -a gemini-cli2Platform CLI
gemini skills install https://github.com/genspark-ai/genoffice --path skills/genofficeManually: put the files in place
.devin/skills/genoffice/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about genoffice
How do I install genoffice in Claude Code?
Run npx skills add genspark-ai/genoffice --skill genoffice -a claude-code. You also need the GenOffice desktop app installed locally with CLI >=0.9.0.
What does genoffice do?
It lets the agent use the GenOffice CLI to build pptx, xlsx, docx and PDF files, inspect existing document structure and apply targeted edits. It also converts files between pdf, docx, xlsx, pptx, md, html and csv.
Does genoffice process files locally or send them to the cloud?
Document creation, reading, editing and conversion run locally on GenOffice's own engines. Only search, image and media send your query or referenced file to the provider configured in GenOffice.
Source text
SKILL.md · Apache-2.0
---
name: genoffice
description: Create, convert, read and edit Office documents locally with GenOffice's command line. Build a new presentation (pptx) from a brief through a checked outline, per-page spec and render pipeline, a new spreadsheet (xlsx) from CSV or JSON data with formulas, a new Word document (docx) from Markdown or HTML, or a PDF; convert between pdf, docx, xlsx, pptx, md, html and csv; read the structure and text of an existing file (including the user's own docx / xlsx / pptx as source material) and apply structured edits to it. Use whenever the user asks for a slide deck, presentation, spreadsheet, workbook, report, Word document or any real Office file, a format conversion, a rewrite of part of an existing document, or wants the result opened in the GenOffice editor. Documents are processed locally; only search, image and media send the query or the referenced file to the provider configured in GenOffice.
metadata:
version: 2.70.0
cli: '>=0.9.0'
---
# genoffice — GenOffice from the terminal
`genoffice` is installed with GenOffice. Run `genoffice --version` first. If the command is not found, GenOffice writes the launcher directory to `~/.genoffice/launcher` (Windows: `%USERPROFILE%\.genoffice\launcher`) on every start: read that one line and run `"<dir>/genoffice"` from bash or `"<dir>\genoffice.cmd"` from PowerShell / cmd, quoted, in place of `genoffice` below. Default locations when that file is missing: macOS `/Applications/GenOffice.app/Contents/Resources/cli`, Windows `%LOCALAPPDATA%\Programs\GenOffice\resources\cli`, Linux `/opt/GenOffice/resources/cli`. Every command runs headless on the app's own engines; only `search`, `image` and `media` send data off the machine, to the provider configured in GenOffice.
Always add `--json` when a program reads the output: one JSON object on stdout, `{ "status": "ok" | "partial", "command", "summary", "output_path"?, "warnings"?, "detail"? }` (`partial`: an `apply` with `--best-effort` / `--stop-on-error` wrote the file but lost ops) or `{ "status": "error", "code", "error", "message", "suggestion"?, "detail"? }`. Exit codes: `0` ok, `1` usage or rejected ops, `2` file not found / output exists / file open in GenOffice, `3` conversion failed, `4` app not available. `error` is the machine-readable reason (table under "When a command fails"), `suggestion` the next step in one sentence, including `did you mean "…"?` when a command, option, op name, element id or sheet name is one typo away. `detail` carries facts as fields (`failures[]` with `index`, `op`, `error`, `reason`, `valid_range`, `available`, `supported`, `usage`; `sheets`, `options`, `commands`); never parse `message`.
## Commands
| Command | What it does |
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `genoffice info <file> [--password <pw>]` | Metadata and structure summary (docx blocks and headings, pptx slides, xlsx sheets, pdf pages) |
| `genoffice convert <file> --to <fmt> [--out <path>] [--force]` | `pdf→docx/pptx/xlsx`, `csv→xlsx`, `xls/xlsb/ods→xlsx`, `md→docx/html`, `docx→html/md`, `html→docx`, `xlsx→csv` (`--sheet`), and `docx/xlsx/pptx/md/html→pdf` |
| `genoffice create --type pptx --ops <file> --out <path>` | New deck from a list of slide ops |
| `genoffice create --type pptx --spec <dir\|file> [--outline <file>] --out <path> [--render [dir]] [--audit]` | New deck from page spec files (one per slide, name order) or one deck spec file: px-positioned text, shapes and images (the designed-deck path, see below) |
| `genoffice create --type xlsx --from <data.csv \| table.json> [--header] [--decimal ,] --out <path>` | New workbook from CSV or a 2-D array / `{sheets:[{name,rows}]}`; `"=..."` cells are formulas; `--header` freezes row 1 and filters the range |
| `genoffice create --type docx --from <text.md \| fragment.html> [--no-generator-fields] --out <path>` | New Word document from Markdown or a restricted-HTML fragment |
| `genoffice create --type pdf --from <document> --out <path>` | PDF printed by the GenOffice renderer from any md/html/docx/xlsx/pptx file |
| `genoffice slides read <pptx> [--slide n] [--full \| --max-chars n] [--layouts] [--units in\|cm\|pt\|px]` / `genoffice slides apply <pptx> --ops <file> [--dry-run]` | Inspect ids, geometry (`box` and `size` in EMU, or converted with `unit` named when `--units` is given) and text previews (clipped to 300 characters, ending in `…(+n chars)` with `truncated: true`; `--max-chars` moves the cap, `--full`: whole text, every table row, speaker notes), then edit with ops Text elements carry `effective` (first run's font size/family/color/bold/italic and paragraph align) with `src` naming where each value comes from: `run`, `paragraph defRPr`, `shape lstStyle`, `layout placeholder`, `master placeholder`, `master titleStyle`/`bodyStyle`, `presentation defaultTextStyle`, `theme major`/`minor`; `setFont` writes the run level and overrides all of them, `applyTheme` changes the theme fonts and colors. Elements with a hyperlink carry `link` (`url`, `slide` jump or a PowerPoint `action`: `nextslide` / `previousslide` / `firstslide` / `lastslide` / `lastslideviewed` / `endshow`); `setLink` and `setText` run `link` fields write the same three kinds. |
| `genoffice slides audit <pptx> [--slide n]` / `genoffice slides render <pptx> --out <dir> [--scale 2]` | Geometry audit (`out_of_bounds`, `off_slide`, `text_overflow`, `text_overflow_width`, `overlap`, `picture_distorted` = box aspect off the cropped source by >5%): `issues[]` with a `code`, `level`, `path` (`s_n/e_*`) and, except for overlap, a `suggest` `setTransform` op you can pass to `slides apply` as is; one PNG per slide to look at |
| `genoffice render <file> --out <dir> [--page n] [--scale 2] [--el e_12 [--pad px]] [--grid [--cols 4] [--tile 320]]` | One PNG per page of a docx, xlsx, pptx, md, html or pdf file, laid out by the GenOffice renderer: look at it before reporting a document or workbook as done; `--el` (pptx) also writes the page cropped to one element (`<stem>-NN-e_12.png`, ids from `slides read`) so a small box is legible; `--grid` also writes every page onto one contact sheet (`<stem>-grid.png`, row-major, tile positions in `grid.tiles`) to see a whole deck at once |
| `genoffice slides check <outline.json\|page.json>` / `genoffice slides replace <pptx> --slide n --spec <page.json>` | Validate a deck outline (exit 1 on errors) or build-and-audit one page file and check it against its outline entry and style.md; rebuild one slide from its page file, other slides untouched |
| `genoffice sheet read <xlsx> [--sheet name] [--range A1:D20] [--cols A,C:E] [--max-rows n] [--where formula\|error\|empty\|number\|text] [--stats] [--formats]` / `genoffice sheet apply <xlsx> --ops <file> \| --cells <file>` / `genoffice sheet check <xlsx>` | Read a range plus `features` (panes, filter, charts, tables, rule counts for the sheet; merges and links in the range; `--formats` adds cell formats, widths, heights); keep the output small with `--cols` (only those columns, named in `columns`), `--max-rows` (`rowsShown` / `rowsTotal` and a `note` with the `--range` to continue), `--where` (only cells of one kind as `{ref, value, formula}`, no grid) or `--stats` (counts, used range and the sheet list, no cells); edit with the workbook DSL or by cell address; `check` lists formula errors, references to missing sheets, broken defined names, chart ranges off the data, `###` columns (with a `set_col_width` suggestion), placeholder text and existing rules |
| `genoffice sheet links <xlsx> [--update] [--break indices]` | External `[n]` links: list them (stored path, resolved path, whether the file exists, source sheet names); `--update` re-reads reachable sources and writes the computed values as the formulas' cached `<v>` (formula text untouched; unreachable links keep their cache); `--break indices` turns those formulas into their cached literals, removes the links' parts and renumbers the surviving `[m]` |
| `genoffice docs read <docx> [--range a-b] [--html] [--full \ / `genoffice docs compare <original.docx> <revised.docx> --out <redline.docx> [--author name] [--date <iso>] [--granularity word | char] [--ignore formatting,case,whitespace]` | --max-chars n] [--comments] [--revisions] [--header-footer] [--sections] [--fields] [--notes] [--properties]`/`genoffice docs apply <docx> --ops <file> [--dry-run]`/`genoffice docs check <docx>`; `compare` writes the redline of two documents — the revised one with the differences as tracked insertions and deletions (`--author`, `--date`, `--granularity word | char`, `--ignore formatting,case,whitespace`), which `--json` reports as counts | Read blocks by index (previews are clipped to 200 characters and end in `…(+n chars)` with `truncated: true`; `--max-chars` moves the cap, `--full` lifts it; plus comment threads, tracked changes, header/footer text, page setup per section, fields with their cached results, footnotes/endnotes, document properties), then edit with ops (incl. `set_properties` for the core/app/custom document metadata — custom values may be strings, numbers or booleans, an existing typed property keeps its vt type (i4/i8/r8/bool/filetime/date) when the value fits, and `--properties` also reports each custom value's `customTypes`; a `create --type docx` file carries Word-like docProps/core.xml + app.xml — `wrap_content_control` / `unwrap_content_control` for block-level w:sdt controls — the read items carry `contentControl` (outermost) plus `contentControls` (outer → inner chain) and `inlineContentControls` for run-level controls, and unwrap takes a nested tag too, `applyStyle`, `insertField` for SEQ / REF / DATE / PAGE… fields, `insertBookmark`, `updateFields`), restricted HTML, `insert_image` / `insert_picture` (sized, floating) / `insert_text_box`, `insert_chart` / `edit_chart`, `set_header_footer`, `set_watermark` (text, or a washed-out picture via `image`), `define_style`, `set_page_setup` / `insert_section_break`, `add_comment` / `reply_comment` / `resolve_comment` / `delete_comment`, `accept_changes` / `reject_changes` (selector: `all`, `ids` from `--revisions`, `author`, `type`, `blockIndex`, `blockRange`, `before`; `apply --track [--author name]` records the batch's own edits as tracked changes), `insert_footnote` / `insert_endnote` / `edit_note` / `delete_note`; `--styles` lists style ids; `check` lists fields without results (a fresh TOC), references to missing bookmarks, a TOC that no longer matches the headings, missing images, empty charts or headings, level skips, placeholder text, pending tracked changes and open comments |
| `genoffice merge <template.docx\|pptx\|xlsx> --data <values.json \| inline JSON> --out <path> [--force] [--strict]` | Fill `{{key}}` placeholders in a Word, PowerPoint or Excel template from a JSON object (nested objects flatten to dotted keys `a.b`; whitespace inside the braces is tolerated) through the engines' own find/replace (Word, PowerPoint: text, tables, speaker notes) and typed `set_cell` writes (Excel: a whole-cell placeholder takes the value's type, a number stays a number; substituted text stays text even when it starts with `=`). `detail.used_keys`, `detail.unused_keys` and `detail.unresolved_placeholders[]` (`{placeholder, key, reason: no_key \| split_placeholder \| unreachable_nested, location}` — block index / slide + element id / sheet + cell) tell what happened; unresolved placeholders stay in place with a `unresolved_placeholder` warning unless `--strict` makes them an error. `split_placeholder` = Word split the `{{…}}` over runs with different formatting; retype it in the template in one run (PowerPoint fills a placeholder that spans runs). `unreachable_nested` = inside a nested pptx group (or a table in a group), which deck `findReplace` does not reach; ungroup it. A Word table nothing fills is left untouched |
| `genoffice pdf read <pdf> [--page n \| --range a-b] [--password <pw>] [--full \| --max-chars n]` | Text layer of a PDF page by page: 1-based `page`, `width_pt` / `height_pt`, `text` clipped to 4000 characters ending in `…(+n chars)` with `truncated: true` (`--max-chars` moves the cap, `--full` lifts it and reads every page), plus page count, `encrypted` and title / author / producer metadata; without `--page` / `--range` the first 20 pages come back and `detail.truncated` names the rest; scanned pages have empty text (`convert --to docx` runs OCR)...
© genspark-ai · Apache-2.0 · genspark-ai/genoffice