Developer implementation guide for building hierarchical (folded) memory into an Agent. Three-layer architecture where recent turns stay detailed, older content compresses into episodes, and the oldest distills into durable semantic facts. Use when compact-memory-implementation is not retaining enough, or when agents need to recall decisions from many sessions ago.
$npx -y skills add simbajigege/book2skills --skill folded-memory-implementationInstalls into the current project.
Run `npx skills use "https://github.com/simbajigege/book2skills" --skill "simbajigege/book2skills/folded-memory-implementation"` 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/simbajigege/book2skills" that are relevant to the current task. Run `npx skills add "https://github.com/simbajigege/book2skills"` and select the relevant skills, then follow their instructions.