Weekly Reflect

Consolidate recent activity into a compact memory digest and prune stale entries.

Updated Jun 2, 2026
One-click install
npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill weekly-reflect-atrium-hermes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Weekly Reflect
Source: https://github.com/Atrium-Hermes/atrium-lighthouse/tree/main/skills/reflect
Command: npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill weekly-reflect-atrium-hermes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps autonomous agents stay focused by consolidating recent activity into a compact memory snapshot, pruning stale entries, and organizing topics for quick recall and safer long-term memory management.

Core Features & Use Cases

  • Read memory/MEMORY.md to understand current memory state.
  • Read recent logs in memory/logs/ and articles/ to surface recent activity.
  • Consolidate learnings into memory topics and summarize overall skill health.
  • Reorganize memory by moving detailed notes into memory/topics/ and trim the short index.
  • Log results to memory/logs/${today}.md and notify when complete.

Quick Start

Instruct the agent to run the weekly reflect cycle to prune stale memory and consolidate topics.

Frequently Asked Questions about Weekly Reflect

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

FAQPage Schema
How do I prune stale memory and consolidate agent logs for autonomous workflows?

To prune stale memory and consolidate agent logs, use the weekly reflection cycle to read recent logs, summarize activity into topics, and trim the short index. This creates a compact memory snapshot for safer long-term management.

What is memory consolidation for long-running agents and when is it needed?

Memory consolidation for long-running agents is the process of reorganizing detailed notes into topic files and pruning stale data. It is needed when autonomous workflows accumulate excessive logs, causing agents to lose focus and recall efficiency.

How do I reorganize memory topics and trim the short index in autonomous agents?

To reorganize memory topics, instruct the agent to run the reflection cycle. It moves detailed notes from the main memory file into memory/topics/ directories, trims the short index, and logs results to memory/logs/ with a completion notification.

Do I need specific file access to perform daily memory reflection and activity consolidation?

Yes, daily memory reflection requires access to memory/MEMORY.md, recent logs in memory/logs/, and articles/ directories. Output is stored in memory/logs/ and a notify call is triggered upon completion.

What's the best way to identify memory gaps and refresh agent health during long-running tasks?

The best way to identify memory gaps and refresh agent health is to consolidate recent learnings into memory topics and summarize overall skill health. This surfaces gaps and prunes stale data into an actionable memory digest.