CazzPatent
AI patent-disclosure drafting bundle for DeepSeek Harness, combining an 8-stage Skill workflow with Cordis-wrapped Python tools.
Install
$ dsh plugin --profile demo add github:YangCazz/CazzPatent#<sha>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.
Key Capabilities
- Guides technical proposals through environment checking, material parsing, patent-point mining, prior-art search, drafting, review, learning, and export.
- Provides a DSH Skill with stage prompts, templates, scripts, and self-improving memory files.
- Registers schema-validated Python tool wrappers through a Cordis plugin.
- Converts LaTeX expressions to editable Word OMML equations.
- Generates and validates diagrams, with HTML/SVG and PNG outputs described in the README.
- Exports disclosure materials in Markdown, DOCX, and PDF workflows.
- Supports configurable Python path, scripts directory, and default tool timeout.
Useful For
- Preparing a patent-disclosure draft from a technical proposal.
- Creating DOCX and PDF disclosure deliverables.
- Producing diagrams for patent disclosure materials.
- Using reusable iteration-derived rules in later drafting workflows.
Who It Fits
- DeepSeek Harness users preparing technical patent disclosures.
- Patent drafting teams and reviewers who need structured draft materials.
- Developers configuring Cordis tools backed by Python scripts.
Documented Limitations
- Requires a Python 3.10+ environment according to the README badge.
- The Skill toolchain requires dependencies from requirements.txt; diagram-related setup instructs users to install Playwright Chromium.
- PDF export relies on available Word COM, LibreOffice, or weasyprint fallback tooling.
- The plugin's default per-run timeout is 300000 ms unless overridden.
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.
GitHub reports the repository license as MIT.
No root package.json was captured in the latest GitHub snapshot.
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
- YangCazz/CazzPatent
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 1cf7dc7 · 2026-09-23
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
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-09
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Verifiable research-report engine for DeepSeek Harness with content-addressed evidence ledgers and tamper-evident sealed reports.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →