From langroid
Records design patterns learned in the Langroid multi-agent framework for future reference. Automatically invoked when a new pattern is discovered or when asked.
How this skill is triggered — by the user, by Claude, or both
Slash command
/langroid:add-patternThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When you learn a new Langroid design pattern, do the following:
When you learn a new Langroid design pattern, do the following:
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.
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).
npx claudepluginhub johnny-rice/claude-code-tools --plugin langroidRecords design patterns learned in the Langroid multi-agent framework for future reference. Automatically invoked when a new pattern is discovered or when asked.
Designs effective prompts for LLM agents using structured input/output formats, chain-of-thought reasoning, few-shot examples, and system prompt architecture. Covers Claude-specific patterns and multi-turn conversation design.
Searches project memory via progressive filtering with MEMORY.md index and grep for task-relevant patterns before non-trivial work; stores structured problem-solution insights after completion.