dsh-markitdown
Convert PDF, Word, Excel, PowerPoint, HTML, EPUB, and web URLs into Markdown for DeepSeek Harness.
Install
$ dsh plugin --profile web add github:jiekesu967/dsh-markitdownPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Converts PDF, Word (.docx), Excel (.xlsx), PowerPoint (.pptx), EPUB, and HTML documents into clean Markdown.
- Converts structured and data formats including CSV, TSV, JSON, XML, and Jupyter notebooks (.ipynb).
- Fetches and converts content directly from HTTP/HTTPS URLs.
- Multi-engine resolution chain automatically probing `markitdown` CLI, `uvx markitdown`, python module, or embedded built-in converter.
- Enforces strict input size limits, zip bomb decompression caps, and output character truncation safeguards.
- Integrates with the DSH workspace filesystem seam for sandbox compliance and read-before-write safety.
Useful For
- Allowing LLMs to extract and analyze data from uploaded PDFs, spreadsheets, and slide decks.
- Ingesting documentation, web pages, and EPUB files directly into a Markdown format the agent can reason over.
- Running document-to-markdown workflows in environments with or without a local Python setup.
Who It Fits
- DeepSeek Harness users processing multi-format office documents and reports.
- Developers building document extraction and summarization workflows in DSH.
- Users running lightweight DSH instances seeking dependency-free document conversion fallbacks.
Documented Limitations
- PDF layout extraction, OCR, and audio transcription require an external MarkItDown installation (`markitdown[all]` or `uvx`) and are not supported by the built-in fallback engine.
- Subprocess execution is launched directly with `shell: false`, rejecting `.bat` or `.cmd` shims on Windows.
- Document conversion I/O runs with the privileges of the active host process.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 4 development, 3 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- jiekesu967/dsh-markitdown
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 2542aba · 2026-09-30
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-09-30
- Last release
- 2026-09-30
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Preview, create, and edit spreadsheets, docs, slides, and canvases in DeepSeek Harness powered by Univer.
View plugin →Multi-model workflow teams and DAG orchestration GUI for DeepSeek Harness Web profile.
View plugin →A standalone, local persistent-memory system for AI agents, with DeepSeek Harness support provided through the separate dsh-mnemon plugin.
View plugin →Compatibility bridge and host ABI enabling unmodified Pi plugins to run natively on DeepSeek Harness.
View plugin →