Manual-first workflow skill for redesigning, debugging, hardening, or productionizing LLM prompts and system prompts. Use when the user needs end-to-end prompt work such as stabilizing behavior, migrating across models, or preparing a prompt for production. Do not use for quick technique lookup or for general LLM-powered coding tasks.
$npx -y skills add liqiongyu/my-agents --skill prompt-engineeringInstalls into the current project.
Run `npx skills use "https://github.com/liqiongyu/my-agents" --skill "liqiongyu/my-agents/prompt-engineering"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/liqiongyu/my-agents" that are relevant to the current task. Run `npx skills add "https://github.com/liqiongyu/my-agents"` and select the relevant skills, then follow their instructions.