patterns
Design patterns for the Langroid multi-agent LLM framework. Covers
Use this skill when you learn one or more design pattern(s) in the
$ npx -y skills add langroid/langroid --skill add-pattern --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/add-patternContext preview
The summary Claude sees to decide when to auto-load this skill.
Use this skill when you learn one or more design pattern(s) in the
name: add-pattern description: Use this skill when you learn one or more design pattern(s) in the Langroid (multi) agent framework, and want to make a note for future reference for yourself. Use this either autonomously, or when asked by the user to record a new pattern.
When you learn a new Langroid design pattern, do the following:
1. Add an entry in the sibling `patterns/SKILL.md` file in the appropriate category section, containing a DESCRIPTION of the goal of the pattern (i.e. what it enables you to implement), accompanied by a `- Reference:` pointer to a markdown DOCUMENT in the `patterns/` directory.
IMPORTANT - The DESCRIPTION should be clear enough that future YOU can effectively use it to MATCH design problems you may encounter in future.
2. In that DOCUMENT, describe the idea of the implementation along with code examples. Follow the format of existing pattern files (Problem, Solution, Complete Code Example, Key Points, When to Use).
This is just a teaser; there's much more, like function-calling/tools, Multi-Agent Collaboration, Structured Information Extraction, DocChatAgent (RAG), SQLChatAgent, non-OpenAI local/remote LLMs, etc. Scroll down or see docs for more.
Repo: langroid/langroid