skill
llm-condense
An agent skill that removes conversational overhead from LLM responses.
Set up
Skills are installed by placing their folder where your agent loads skills.
The download comes from github.com/MorrowShore/llm-condense itself, not from our server, so what you get is exactly what its author published.
Install instructions come from the README
Skills do not use an MCP config. Follow the steps in the README below.
README
synced Oct 26, 2026llm-condense
A skill for concise, professional AI responses. Preserves accuracy, natural grammar, and necessary detail. Inspired by Caveman, without the persona.
Save tokens and speed up operations with no impact on code quality.
Install & Use In Project (recommended)
Tell your AI the following:
Install the LLM-Condense skill (https://github.com/MorrowShore/llm-condense), start using the skill, and add a reminder in the project's agents.md to always use the skill.
Install & Use Globally
Tell your AI the following:
Install the LLM-Condense skill (https://github.com/MorrowShore/llm-condense) globally so it becomes accessible to all current and future projects, start using the skill, and add a reminder in the global agents.md to always use the skill in every project.