distill

Distill episodic session learnings from EPISODES.md into persistent memory patterns in MEMORY.md.

Updated Jan 4, 2026
One-click install
npx skills add https://github.com/c-daly/agent-swarm --skill distill
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: distill
Source: https://github.com/c-daly/agent-swarm/tree/main/skills/distill
Command: npx skills add https://github.com/c-daly/agent-swarm --skill distill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill converts episodic session learnings into durable memory patterns, enabling automatic consolidation and retrieval across tasks.

Core Features & Use Cases

  • Episodic-to-memory distillation: Transform learnings from EPISODES.md into structured memory representations.
  • Memory management: Produce .context/MEMORY.md and support reinforcement/decay to keep memory relevant.
  • Automation: Trigger distillation via /distill and view current memory or pending episodes.

Quick Start

Use the distill command to distill current episodes:

  • /distill
  • /distill show
  • /distill episodes

Frequently Asked Questions about distill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert episodic learnings into persistent memory patterns?

Episodic-to-memory distillation transforms session learnings stored in EPISODES.md into structured memory patterns saved to MEMORY.md. Use the /distill command to automatically consolidate and organize learnings for future retrieval across tasks.

What does the /distill command do?

The /distill command triggers automatic distillation of current episodes into memory patterns. Run /distill show to view current memory, or /distill episodes to see pending episodes awaiting consolidation.

How does memory management and reinforcement work with distillation?

Memory management supports reinforcement to strengthen patterns, decay to deprioritize old learnings, and pruning to remove irrelevant entries. This keeps memory relevant and prevents outdated patterns from cluttering future reasoning.

When should I use automated memory distillation instead of manual note-taking?

Automated distillation is best when you need durable cross-session learning consolidation. It extracts and classifies episodic learnings into patterns systematically, whereas manual notes risk fragmentation and retrieval friction across multiple tasks.

Can I trigger distillation automatically or only manually?

Distillation supports automatic triggers via the /distill command as well as manual invocation. The Skill monitors pending episodes and can consolidate learnings on demand to keep memory synchronized with session activity.