Bruce Doc Converter CLI
The bdc CLI for agents: Word, Excel, PowerPoint and PDF become Markdown, and Markdown with Mermaid becomes a Word document.
- 60 ★ on the repository
- Last commit
Extended access
Why this level
- The CLI reads and writes documents in the given folders, and `bdc setup-node` installs Node.js dependencies on the machine.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/bruce-doc-converterDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The CLI reads and writes documents in the given folders, and `bdc setup-node` installs Node.js dependencies on the machine.
This is third-party code. Review the repository files before installing.
What it does
Bruce Doc Converter gives an agent two-way document conversion. `bdc convert` turns Word, Excel, PowerPoint and PDF into model-friendly Markdown and exports Markdown to Word, rendering Mermaid diagrams itself. The batch mode `bdc batch` walks a whole directory. Output goes to stdout as JSON by default and progress to stderr. The `--strict` mode rejects a result when content is lost: empty pages, formulas without cache, images that failed to embed, Mermaid failures. The `--content` option sets full text, a preview or none, and `--manifest` writes per-file results to a separate JSONL. The repository includes the `bruce-doc-converter-skill` skill with diagnostics and install notes.
Who it is for. People preparing documents for an agent: analysts and technical writers who need to read office files and produce Word reports.
Good fit when
- A PDF report and an Excel sheet must become Markdown for an agent to parse.
- Markdown notes with Mermaid diagrams must come out as a formatted Word document.
- A folder of hundreds of files is walked with one command and a per-file manifest.
- Content loss is unacceptable: `--strict` returns an error instead of a silent skip.
Not a fit when
- An exact complex layout is needed: scans without a text layer and formulas come out with warnings.
- The environment has no Node.js: exporting Markdown to Word needs separate Node dependencies.
- Output to PDF or PowerPoint is needed: only Word is supported.
Example request
Convert budget.xlsx and report.docx with bdc in --strict mode and show which parts of the files were skipped.Limitations
Python 3.8 or newer is required. Exporting Markdown to Word needs Node.js and a one-time `bdc setup-node`, which installs dependencies via `npm ci --ignore-scripts` to avoid running third-party package scripts. Mermaid diagrams are rendered by a Chrome, Edge or Chromium found on the machine, and no browser is downloaded. An empty page is hard to tell from a scan, so both raise a warning and `--strict` rejects the result. `--max-results` works only together with `--manifest`.
How to disable. Remove the package with `pipx uninstall bruce-doc-converter` or `uv tool uninstall bruce-doc-converter`, and delete the skill folder from the agent skills directory.
FAQ
How do I install bdc?
With the first README option: `pipx install bruce-doc-converter`. Fallbacks: `uv tool install bruce-doc-converter`, `pip3 install --user bruce-doc-converter` or a `venv` install.
What is needed for Word export?
Run `bdc setup-node` once: it installs Node.js dependencies without running third-party scripts. Mermaid uses a local Chrome, Edge or Chromium.
How do I avoid losing content?
Add `--strict`: empty pages, formulas without cache, images that failed to embed and Mermaid failures turn into a rejection instead of silent loss.
How do I process a whole folder?
With `bdc batch /path/to/folder`; with `--manifest` per-file results go to a separate JSONL, and `--jsonl` prints a line after each file.
In what form does the result arrive?
JSON on stdout. The `--content` option sets full text, a preview or none.
Discussion
No questions or reviews yet.
Related
CLI toolsA Firecrawl skill and CLI that lets your agent convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF to Markdown on your own machine
A skill and CLI that turn Markdown into DOCX, PDF, PPTX, XLSX, PNG and about a dozen more formats, all computed locally
doc-cleaner converts PDF, Office, Keynote, Numbers and EPUB into clean Markdown with intact tables and Big5 and CP950 encodings.
A skill plus the docx program: the agent fills forms, edits tables and reviews Word files with tracked changes
The Word to Markdown MCP server: an agent turns a .docx file into clean Markdown locally, with images, tables and footnotes.
A CLI that lets an agent create and edit Word, Excel and PowerPoint: a single binary, no Office install, no extra libraries
README in short
The README defines an agent contract: one JSON envelope per command, diagnostics with codes such as `MATH_NOT_CONVERTED` and retryable errors with a `next_command` field.