Agent-Skills.md

Agent Skills: distill

Distill session episodes into persistent memory patterns

UncategorizedID: c-daly/agent-swarm/distill

Repository

c-daly/agent-swarm
c-daly

Install this agent skill to your local

pnpm dlx add-skill https://github.com/c-daly/agent-swarm/tree/HEAD/skills/distill

Skill Files

Browse the full folder contents for distill.

Download Skill

Loading file tree…

skills/distill/SKILL.md

Skill Metadata

Name
distill
Description
Distill session episodes into persistent memory patterns

Usage

/distill           # Distill episodes at current scope
/distill show      # Show current memory
/distill episodes  # Show pending episodes

How It Works

  1. Extract patterns from .context/EPISODES.md learnings
  2. Classify as pattern, pitfall, preference, or approach
  3. Match against existing .context/MEMORY.md patterns
  4. Reinforce matches (increases confidence), add new, decay old, prune low

CLI

python3 ~/.claude/plugins/agent-swarm/context/memory.py distill .   # Distill
python3 ~/.claude/plugins/agent-swarm/context/memory.py show .      # Show
python3 ~/.claude/plugins/agent-swarm/context/memory.py episodes .  # Pending

Confidence

  • Reinforcement: each observation increases confidence
  • Decay: patterns not seen in 30+ days lose confidence
  • Pruning: below 0.2 removed

Logging

Agents log learnings with: LEARNING: [description] Captured by post-task hooks -> EPISODES.md.