rcode-memory-distill
CommunityCompress Memory Bank context fast.
Software Engineering#markdown#context loading#token optimization#memory bank#distillation#llm workflow
Authorhanzlahabib
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It turns a large Memory Bank into a compact, fast-loading distillation so an AI can recover project context without burning tokens on repeated source reads.
Core Features & Use Cases
- Regenerates two outputs: a full project distillate and a stack-only distillate.
- Preserves every fact, decision, constraint, and relationship while stripping presentation overhead for token efficiency.
- Uses source digests to skip work when files have not changed, making repeated runs safe and predictable.
- Fits projects that need rapid context restoration from Memory Bank notes, people profiles, milestones, or incident records.
Quick Start
Ask the assistant to distill the Memory Bank and regenerate the project and stack distillates from the files under .rcode/memory.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: rcode-memory-distill Download link: https://github.com/hanzlahabib/rcode/archive/main.zip#rcode-memory-distill Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 537,000+ vetted skills library on demand.