Anthropic's official collection of Agent Skills: folders with instructions and scripts that Claude loads for a task. A good reference for writing your own.
All repositories
Prompting & contextmicrosoft
LLMLingua
Compresses long prompts and context up to 20x with little quality loss by dropping low-value tokens. Saves money and speeds up responses.
Who it is for
For those paying for long contexts who want to shrink them.
How to start
- Install:
pip install llmlingua. - Create
PromptCompressor()fromllmlingua. - Call
compress_prompt(prompt, instruction="", question="", target_token=200)and use the result in your request.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+103Sep 6 — Oct 6
Author's description
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
More in «Prompting & context»
Formerly Awesome ChatGPT Prompts: a huge community library of prompts plus an interactive book on prompting. You can deploy your own private copy.
A collection of system prompts and tool descriptions from popular AI products: Cursor, Devin, Windsurf, Lovable, Manus and others. Useful for studying how pros build them.
A detailed guide to prompt engineering: techniques from few-shot to chains of thought, papers, lectures and notebooks. Recently extended with context engineering and agents.
A collection of examples and guides for the OpenAI API: from basic requests to function calling and RAG. Most code is Python.
Recipes from Anthropic as notebooks: tools, RAG, multimodality, subagents and other techniques for working with Claude. The code is ready to copy into your projects.