DSH Plugin Development Assistant
Paste the following prompt into your AI chat to install this skill:
To install the DSH Plugin Development Assistant, please refer to the official guide at https://skillhub.cn/install/skillhub.md and install @davtime/dsh-plugin-studio as instructed.
About this skill
Solving the Problem
Developing DeepSeek Harness plugins often requires familiarity with underlying configurations and framework terms like bundle-client or cordis.patch.yml, creating a code gap between natural language requirements and runnable plugins. For users who merely describe functionality (e.g.,
Use Cases
- When a user needs to add a custom command to the DSH platform for specific data processing but wants to avoid manual complex configuration coding, using the assistant to quickly generate a runnable plugin.
- Developing a frontend plugin with a settings panel to manage user preferences in the DSH Web interface, yet lacking frontend development experience and requiring natural language guidance.
- After plugin installation, encountering slot crashes or service injection failures that need quick diagnosis and repair based on symptoms to restore plugin functionality.
- Preparing to publish a developed plugin to a git repository or npm, but unsure about specific steps for packaging, verification, and distribution, requiring end-to-end guidance.
Best For
- Plugin engineers responsible for maintaining the DSH ecosystem, needing to quickly customize commands, services, or UI plugins for different business teams to support workflows.
- Product managers with natural language feature descriptions but lacking coding skills, wanting to directly generate runnable DSH plugin prototypes for testing.
- Operations personnel encountering plugin loading failures, needing symptom-based troubleshooting and repair to ensure DSH platform stability.
- Open-source contributors aiming to publish their DSH plugins to the community, but requiring guidance through the complete process from development to release.
Related Skills
Automatically indexes Gradle-cached AAR/JAR dependency classes and returns library coordinates, versions, and public APIs by fully qualified name, using only the Python standard library.
Codifies AMT and YourMT3 training conventions, script patterns, hyperparameters, precision, checkpoints, and NaN safeguards.
Retrieve relevant chunks from a customer-managed PKM dataset by dataset_id and return concise, source-annotated answers.
Convert PRDs, user stories, or functional specs into prioritized test-point checklists covering functional, business-rule, boundary, exception, and non-functional dimensions.