distill

Extract actions, facts, and decisions from conversations into structured JSON.

120|6|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/ascorbic/macrodata --skill distill-ascorbic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: distill
Source: https://github.com/ascorbic/macrodata/tree/main/plugins/macrodata/skills/distill
Command: npx skills add https://github.com/ascorbic/macrodata --skill distill-ascorbic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill extracts distilled actions, facts, and decisions from today's conversations to feed memory consolidation and create a compact, actionable knowledge base.

Core Features & Use Cases

  • Coordinated distillation: Spawns a sub-agent per conversation to prevent context blowup and ensure focused extraction of actionable items.
  • Structured output: Produces a deterministic JSON payload with distilled_actions, facts, and decisions for journaling and state updates.
  • Use Case: After a team discussion, distill the day's chats into concise action items and knowledge updates for the project journal.

Quick Start

Run the distill skill to process today's conversations and generate a distilled report.

Frequently Asked Questions about distill

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

FAQPage Schema
How do I extract action items and decisions from daily conversations?▼

You can distill daily conversations into a structured JSON payload that extracts distilled actions, facts, and decisions. This process creates a compact knowledge base suitable for journaling and state updates.

What is the best way to build a compact knowledge base from chat logs?▼

The best way to build a compact knowledge base from chat logs is by coordinating sub-agents for each conversation to keep context bounded and ensure focused extraction of actionable items without context blowup.

How does distill handle context blowup when processing multiple chats?▼

Distill prevents context blowup by spawning a dedicated sub-agent per conversation. This mechanism keeps context bounded and ensures focused extraction of actionable items during knowledge distillation.

Can I extract structured JSON from standup and team discussions?▼

Yes, you can extract a deterministic JSON payload from standup and team discussions. The output contains distilled actions, facts, and decisions structured specifically for journaling and state updates.

Do I need any dependencies to distill conversations into a knowledge base?▼

No dependencies are required to distill conversations into a knowledge base. The skill operates independently to spawn sub-agents and return structured JSON payloads for memory consolidation.