dsh-preset-library
Run the following command in DeepSeek Harness:
dsh plugin install LiweiDonVee/dsh-preset-library
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install LiweiDonVee/dsh-preset-library in your terminal to install the plugin (source: https://github.com/LiweiDonVee/dsh-preset-library), then restart DSH and open it via Settings → Preset Library.
About this plugin
When your DeepSeek Harness preset collection grows large enough that you can no longer tell what is what, rewriting each preset to add tags or wiring is both tedious and error-prone. dsh-preset-library lets you search, tag, and organise the entire collection without touching the presets themselves.
The interface offers compact grid, list, and grouped views alongside bulk tagging, status filters, and one-level parent/child affiliations. Metadata is versioned, validated, and written atomically with revision-conflict checks, so bulk edits never silently clobber one another. The UI ships in both English and Chinese.
It suits DSH users who have accumulated a sizable preset library and need batch tag management plus shallow hierarchy. Keep in mind the plugin targets DSH 0.1.2-rc.1 specifically—newer versions are uncertified—and parent/child relationships are limited to a single level for now.
Use Cases
- Filtering a DSH preset collection of dozens or hundreds by tag or status
- Applying topical tags to a batch of presets and wiring one-level parent/child links
- Preserving metadata revision history before and after bulk operations to prevent accidental overwrites
Best For
- DSH users whose preset library has outgrown per-preset manual tagging
- Teams or individuals wanting a lightweight one-level hierarchy without editing presets
- Users on the DSH 0.1.x line who prefer managing collections through metadata
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.