MIT-licensed legal-tech toolkit that redraws litigation diagrams and builds case timelines as reproducible, A4-ready SVG/PNG/PPTX/VSDX/drawio figures on DeepSeek Harness.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-01
License
MIT
01What can it help you accomplish?
Redraw an existing litigation diagram into a presentation-ready, court-material-grade figure
SVG · PNG · PPTX · VSDX · drawio — five editable formats
Legal professionals and litigators who need court-ready diagrams from rough drafts
Generate an accurate case timeline directly from case material
A structured, accurate case timeline diagram
Legal professionals who need a reliable timeline from messy case files
02How to install into DeepSeek Harness
Prerequisites
- Python 3 — the project declares zero third-party dependencies (standard library only)
Installation steps
- 01
Install the plugin as a DeepSeek Harness (dsh) skill / Claude Skill
- 02
Invoke it from your agent session to draw or redraw a litigation diagram
Verify the integration
- Confirm the skill produces an SVG / PNG / PPTX output from a sample diagram
Rollback
- Remove the skill from the dsh skill directory to disable it
03DSH integration and capability boundaries
Distributed as a DeepSeek Harness (dsh) plugin / Claude Skill; the README carries a 'DeepSeek Harness supported' badge and the repo is tagged dsh-plugin
Litigation visualization redraw
an existing diagram (hand-drawn, screenshot, AI-generated, Mermaid, or plain text)→SVG · PNG · PPTX · VSDX · drawio
Timeline master
raw case material→an accurate case timeline
Deterministic A4 layout engine
material analysis produced by the model→print-ready layout with per-card word capacity computed from A4 paper dimensions
computes position, size, layers and per-card text capacity deterministically from A4 paper physical size
04Who is it for? When not to use it?
Good for
- Legal professionals and litigators who need court-ready diagrams from rough drafts
- Legal professionals who need a reliable timeline from messy case files
Not for
- Every word on the diagram must be traceable to the original source sentence; only deletion is allowed, no rewriting, and commitments/agreements are kept off the main axis.
05Compatibility, maintenance and safety notes
- Every word on the diagram must be traceable to the original source sentence; only deletion is allowed, no rewriting, and commitments/agreements are kept off the main axis.
- Layout is computed deterministically, so the same material yields the same diagram regardless of which model runs it or how many times.
- A4 printing is a design premise, so generated figures are sized for A4 output.
MIT · actively maintained (latest release v2.0.1, 2026-08-23)
06Frequently asked questions
What does New Litigation Visualization do?
It turns rough or messy legal material into court-ready figures: one module redraws an existing diagram into five editable formats, and another (Timeline Master) draws an accurate case timeline straight from case files.
Which output formats does it support?
SVG, PNG, PPTX, VSDX and drawio — five editable formats you can drop into court material.
Does it run on DeepSeek Harness?
Yes. The project carries a 'DeepSeek Harness supported' badge and is published as a dsh plugin / Claude Skill; it also works with Claude Code and Codex.
Why is the output reproducible?
Layout (position, size, layers, word capacity) is computed by a deterministic script from A4 paper dimensions, so the same material always yields the same diagram — even with a weaker model.
07Related DSH workflows
archify
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
openviking
by volcengine
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
nocobase
by nocobase
NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.
learn-harness-engineering
by walkinglabs
Harness engineering beginner tutorial, from 0 to 1
08Data and sources
DeepSeek Harness supported
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-01. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.