← DeepSeek Harness Plugins
DeepSeek Harness PluginIndexed

DSH-FormatForge

DeepSeek Harness plugin for converting 30+ file formats (PDF, DOCX, XLSX, etc.) into structured AI-readable data via drag-and-drop or tools.

VisionDeveloper ToolsSkills & Workflows
10GitHub Stars1ForksUpdated2026-10-02

Install

$ dsh plugin --profile desktop add "$(pwd)/packages/dsh-formatforge"

Plugin 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.

source-grounded
DSH-FormatForge is a DeepSeek Harness plugin that converts over 30 file formats (such as PDF, DOCX, PPTX, XLSX, EML, EPUB, and TOML) into structured Markdown and JSON. It enables seamless drag-and-drop file ingestion within the DSH desktop interface, registers chat tools like ff_translate and ff_formats, and features an enhance protocol that prompts the active session model to handle unextracted content like scanned images without external API calls.

Key Capabilities

  • Supports document and data conversion across 30+ formats including PDF, DOCX, PPTX, XLSX, and TOML
  • Provides direct drag-and-drop file ingestion in the DSH web/desktop UI with progress toasts
  • Registers conversational DSH tools including ff_translate, ff_formats, ff_result, ff_batch, and ff_diff
  • Outputs structured Markdown and protocol JSON into a dedicated local inbox directory (~/.dsh/formatforge/inbox/)
  • Includes an enhance protocol signaling active LLMs to recover or OCR unscannable text natively
  • Supports pagination, offset, and quality reporting for large document translations

Useful For

  • Extracting text and tables from binary documents like PDF and Word directly within DSH chat sessions
  • Batch translating local document directories into structured formats for AI analysis
  • Parsing spreadsheets and config files into LLM-digestible Markdown tables without third-party APIs

Who It Fits

  • DeepSeek Harness desktop and web users working with local documents and spreadsheets
  • Developers needing programmatic document extraction tools inside DSH workflows
  • Researchers and analysts querying multi-format data directly in conversation

Documented Limitations

  • Requires a local Python 3.10+ runtime and backend parser environment
  • Scanned PDF parsing without text layers requires local OCR engines (Tesseract, PaddleOCR, or EasyOCR)
  • UI drag-and-drop interception relies on host internal DOM event handling without a public contract
  • Mixed clipboard paste operations prioritize files and drop text inputs

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Not Found

No root package.json was captured in the latest GitHub snapshot.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
Tianbuyu-wwx/DSH-FormatForge
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
221b11e · 2026-10-06

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
10GitHub stars
Forks
1
Open issues
7
Last commit
2026-10-02
Last release
2026-10-02
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app