dsh-recipe
Run the following command in DeepSeek Harness:
dsh plugin install 863683348/dsh-recipe
Paste the following prompt into your AI chat to install this plugin:
Install it in DeepSeek Harness by running dsh plugin install 863683348/dsh-recipe; source code: https://github.com/863683348/dsh-recipe
About this plugin
In the DSH plugin ecosystem, a single plugin solves a single point problem, but what users actually need is a full environment - a browser dev setup, an academic writing stack, a notification suite. dsh-recipe bundles multiple plugins into scene recipes so you can describe what you want in one sentence and get a complete, ordered install sequence instead of hunting and installing one by one.
Four core actions power the plugin: list browses all available recipes, search matches recipes against a natural-language need, apply expands a recipe into an ordered plugin manifest with install commands, and compose merges multiple recipes with deduplication while preserving dependency order. The recipe format is plain JSON; all search, expansion, and composition logic runs locally with zero network calls, zero external dependencies, and no write operations.
It is ideal for developers already managing plugins with DSH who want to spin up standardized environments quickly. Whether unifying a team dev setup, tailoring an academic writing toolchain, or wiring up a notification stack in one pass, dsh-recipe turns installing plugins into choosing an environment.
Use Cases
- Describe a need in one sentence and get a full ordered install sequence
- Merge multiple recipes with dedup to build a unified environment
- Search by natural language to instantly find the right plugin kit
Best For
- Developers who already manage plugins with DSH
- Teams that need to spin up standardized environments fast
- Heavy plugin users who want to cut down on hunting and installing one by one
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.