Develop Python modules for custom processing of LLM chat completions in Harbor Boost.
npx skills add https://github.com/av/harbor --skill boost-modules
Please help me install this Agent Skill. Skill: boost-modules Source: https://github.com/av/harbor/tree/main/skills/boost-modules Command: npx skills add https://github.com/av/harbor --skill boost-modules
This Skill unit addresses the need for custom module creation within Harbor Boost, an optimizing LLM proxy. It simplifies the process of building Python modules that intercept or transform LLM chat completions, enabling advanced processing like reasoning chains, prompt injection, structured outputs, artifacts, and custom workflows.
To create a custom module for Harbor Boost, write a Python file with the structure defined in the SKILL.md file and place it in the 'custom_modules' directory. Restart the container and test the module through the API.
High-intent search queries and answers about installing and using this skill.
To create custom modules for LLM chat completion processing, write a Python file following the defined structure and place it in the 'custom_modules' directory. This allows you to intercept and transform LLM responses within the Harbor Boost proxy.
Custom LLM proxy modules are used to intercept and transform chat completions, enabling advanced processing like reasoning chains, prompt injection, structured outputs, artifacts, and custom workflows to extend LLM behavior.
Yes, you can implement prompt injection and reasoning chains by developing Python modules for the Harbor Boost proxy. These modules act as middleware to modify and extend LLM chat completions based on your custom logic.
Yes, a Python environment is required to build Harbor Boost custom modules. You must write Python files, place them in the 'custom_modules' directory, restart the container, and test the module through the API.
You add chat completion middleware to an LLM proxy by writing a Python module with the specified structure and deploying it to the 'custom_modules' directory. Restart the container to activate the middleware for API interactions.
The best way to transform LLM outputs through a proxy is by creating Python modules for Harbor Boost. This approach lets you intercept chat completions and apply custom workflows, structured outputs, or prompt modifications directly.
avDevelop Python-based Boost modules for Harbor's LLM proxy pipeline.
manifest-networkRestart a deployed Manifest app lease via secure HTTPS calls and verify pre- and post-restart status.
mcauduro0Analyze and optimize LLM prompts with Python scripts.
fgarofalo56Provide a unified API for over 100 LLM providers with fallback mechanisms.
