dsh-composition
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-composition
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-composition in DeepSeek Harness to install the plugin; the full source is available at https://github.com/uckkk/dsh-composition . After installation, register the bundle in your profile package.json to activate it.
About this plugin
dsh-composition is a memory plugin that supplies composition-rule references to your sessions. Whenever a conversation touches on compositional principles, frame layout, or visual proportion, the plugin injects its pre-loaded rule knowledge into the context so answers are grounded rather than generic.
Under the hood it is written in pure Node.js with zero network calls and no external services. Once installed, the tools it registers are ready to invoke in any session without environment variables or background processes.
It suits photographers, graphic designers, illustrators, and any visual creator who frequently discusses composition, as well as teams that prefer AI advice on framing rules to be specific and professional. Because everything runs offline, it also works well in environments where data must never leave the local machine.
Use Cases
- Ask the AI to cite rule of thirds or golden ratio when discussing photographic composition
- Request layout advice grounded in balance, contrast, and rhythm principles
- Analyze element placement and visual flow in illustrations or posters
Best For
- Photographers and illustrators who frequently discuss frame layout
- Graphic designers who want specific, professional composition guidance
- Creative teams that require all data to stay on local machines
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.